upgrade Unstructured version

fix: fix tongyi models blocking mode with incremental_output=stream (#13620 )
fix document extractor node incorrectly processing doc and ppt files (#12902 )
2026-01-08 23:34:11 +00:00 · 2025-02-13 15:08:34 +08:00 · 2025-02-13 10:24:05 +08:00 · 2025-02-12 18:04:28 +08:00 · 2025-02-12 15:02:11 +08:00 · 2025-02-12 13:53:51 +08:00
390 changed files with 7757 additions and 4308 deletions
--- a/.github/workflows/api-tests.yml
+++ b/.github/workflows/api-tests.yml
@@ -26,6 +26,9 @@ jobs:
    steps:
      - name: Checkout code
        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          persist-credentials: false

      - name: Setup Poetry and Python ${{ matrix.python-version }}
        uses: ./.github/actions/setup-poetry
--- a/.github/workflows/build-push.yml
+++ b/.github/workflows/build-push.yml
@@ -79,10 +79,12 @@ jobs:
          cache-to: type=gha,mode=max,scope=${{ matrix.service_name }}

      - name: Export digest
+        env:
+          DIGEST: ${{ steps.build.outputs.digest }}
        run: |
          mkdir -p /tmp/digests
-          digest="${{ steps.build.outputs.digest }}"
-          touch "/tmp/digests/${digest#sha256:}"
+          sanitized_digest=${DIGEST#sha256:}
+          touch "/tmp/digests/${sanitized_digest}"

      - name: Upload digest
        uses: actions/upload-artifact@v4
@@ -132,10 +134,15 @@ jobs:

      - name: Create manifest list and push
        working-directory: /tmp/digests
+        env:
+          IMAGE_NAME: ${{ env[matrix.image_name_env] }}
        run: |
          docker buildx imagetools create $(jq -cr '.tags | map("-t " + .) | join(" ")' <<< "$DOCKER_METADATA_OUTPUT_JSON") \
-            $(printf '${{ env[matrix.image_name_env] }}@sha256:%s ' *)
+            $(printf "$IMAGE_NAME@sha256:%s " *)

      - name: Inspect image
+        env:
+          IMAGE_NAME: ${{ env[matrix.image_name_env] }}
+          IMAGE_VERSION: ${{ steps.meta.outputs.version }}
        run: |
-          docker buildx imagetools inspect ${{ env[matrix.image_name_env] }}:${{ steps.meta.outputs.version }}
+          docker buildx imagetools inspect "$IMAGE_NAME:$IMAGE_VERSION"
--- a/.github/workflows/db-migration-test.yml
+++ b/.github/workflows/db-migration-test.yml
@@ -19,6 +19,9 @@ jobs:
    steps:
      - name: Checkout code
        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          persist-credentials: false

      - name: Setup Poetry and Python
        uses: ./.github/actions/setup-poetry
--- a/.github/workflows/docker-build.yml
+++ b/.github/workflows/docker-build.yml
@@ -0,0 +1,47 @@
+name: Build docker image
+
+on:
+  pull_request:
+    branches:
+      - "main"
+    paths:
+      - api/Dockerfile
+      - web/Dockerfile
+
+concurrency:
+  group: docker-build-${{ github.head_ref || github.run_id }}
+  cancel-in-progress: true
+
+jobs:
+  build-docker:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        include:
+          - service_name: "api-amd64"
+            platform: linux/amd64
+            context: "api"
+          - service_name: "api-arm64"
+            platform: linux/arm64
+            context: "api"
+          - service_name: "web-amd64"
+            platform: linux/amd64
+            context: "web"
+          - service_name: "web-arm64"
+            platform: linux/arm64
+            context: "web"
+    steps:
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v3
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Build Docker Image
+        uses: docker/build-push-action@v6
+        with:
+          push: false
+          context: "{{defaultContext}}:${{ matrix.context }}"
+          platforms: ${{ matrix.platform }}
+          cache-from: type=gha
+          cache-to: type=gha,mode=max
--- a/.github/workflows/expose_service_ports.sh
+++ b/.github/workflows/expose_service_ports.sh
@@ -9,6 +9,6 @@ yq eval '.services["pgvecto-rs"].ports += ["5431:5432"]' -i docker/docker-compos
 yq eval '.services["elasticsearch"].ports += ["9200:9200"]' -i docker/docker-compose.yaml
 yq eval '.services.couchbase-server.ports += ["8091-8096:8091-8096"]' -i docker/docker-compose.yaml
 yq eval '.services.couchbase-server.ports += ["11210:11210"]' -i docker/docker-compose.yaml
-yq eval '.services.tidb.ports += ["4000:4000"]' -i docker/docker-compose.yaml
+yq eval '.services.tidb.ports += ["4000:4000"]' -i docker/tidb/docker-compose.yaml

 echo "Ports exposed for sandbox, weaviate, tidb, qdrant, chroma, milvus, pgvector, pgvecto-rs, elasticsearch, couchbase"
--- a/.github/workflows/style.yml
+++ b/.github/workflows/style.yml
@@ -17,6 +17,9 @@ jobs:
    steps:
      - name: Checkout code
        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          persist-credentials: false

      - name: Check changed files
        id: changed-files
@@ -59,6 +62,9 @@ jobs:
    steps:
      - name: Checkout code
        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          persist-credentials: false

      - name: Check changed files
        id: changed-files
@@ -89,6 +95,9 @@ jobs:
    steps:
      - name: Checkout code
        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          persist-credentials: false

      - name: Check changed files
        id: changed-files
@@ -117,6 +126,9 @@ jobs:
    steps:
      - name: Checkout code
        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          persist-credentials: false

      - name: Check changed files
        id: changed-files
--- a/.github/workflows/tool-test-sdks.yaml
+++ b/.github/workflows/tool-test-sdks.yaml
@@ -26,6 +26,9 @@ jobs:

    steps:
      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          persist-credentials: false

      - name: Use Node.js ${{ matrix.node-version }}
        uses: actions/setup-node@v4
--- a/.github/workflows/translate-i18n-base-on-english.yml
+++ b/.github/workflows/translate-i18n-base-on-english.yml
@@ -16,6 +16,7 @@ jobs:
      - uses: actions/checkout@v4
        with:
          fetch-depth: 2 # last 2 commits
+          persist-credentials: false

      - name: Check for file changes in i18n/en-US
        id: check_files
--- a/.github/workflows/vdb-tests.yml
+++ b/.github/workflows/vdb-tests.yml
@@ -28,6 +28,9 @@ jobs:
    steps:
      - name: Checkout code
        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          persist-credentials: false

      - name: Setup Poetry and Python ${{ matrix.python-version }}
        uses: ./.github/actions/setup-poetry
@@ -51,7 +54,15 @@ jobs:
      - name: Expose Service Ports
        run: sh .github/workflows/expose_service_ports.sh

-      - name: Set up Vector Stores (TiDB, Weaviate, Qdrant, PGVector, Milvus, PgVecto-RS, Chroma, MyScale, ElasticSearch, Couchbase)
+      - name: Set up Vector Store (TiDB)
+        uses: hoverkraft-tech/compose-action@v2.0.2
+        with:
+          compose-file: docker/tidb/docker-compose.yaml
+          services: |
+            tidb
+            tiflash
+
+      - name: Set up Vector Stores (Weaviate, Qdrant, PGVector, Milvus, PgVecto-RS, Chroma, MyScale, ElasticSearch, Couchbase)
        uses: hoverkraft-tech/compose-action@v2.0.2
        with:
          compose-file: |
@@ -67,7 +78,9 @@ jobs:
            pgvector
            chroma
            elasticsearch
-            tidb
+
+      - name: Check TiDB Ready
+        run: poetry run -P api python api/tests/integration_tests/vdb/tidb_vector/check_tiflash_ready.py

      - name: Test Vector Stores
        run: poetry run -P api bash dev/pytest/pytest_vdb.sh
--- a/.github/workflows/web-tests.yml
+++ b/.github/workflows/web-tests.yml
@@ -22,6 +22,9 @@ jobs:
    steps:
      - name: Checkout code
        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          persist-credentials: false

      - name: Check changed files
        id: changed-files
--- a/.gitignore
+++ b/.gitignore
@@ -163,6 +163,7 @@ docker/volumes/db/data/*
 docker/volumes/redis/data/*
 docker/volumes/weaviate/*
 docker/volumes/qdrant/*
+docker/tidb/volumes/*
 docker/volumes/etcd/*
 docker/volumes/minio/*
 docker/volumes/milvus/*
--- a/README.md
+++ b/README.md
@@ -25,6 +25,9 @@
    <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
        <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
            alt="follow on X(Twitter)"></a>
+    <a href="https://www.linkedin.com/company/langgenius/" target="_blank">
+        <img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
+            alt="follow on LinkedIn"></a>
    <a href="https://hub.docker.com/u/langgenius" target="_blank">
        <img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
    <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
@@ -105,6 +108,72 @@ Please refer to our [FAQ](https://docs.dify.ai/getting-started/install-self-host
 **7. Backend-as-a-Service**: 
  All of Dify's offerings come with corresponding APIs, so you could effortlessly integrate Dify into your own business logic.

+## Feature Comparison
+<table style="width: 100%;">
+  <tr>
+    <th align="center">Feature</th>
+    <th align="center">Dify.AI</th>
+    <th align="center">LangChain</th>
+    <th align="center">Flowise</th>
+    <th align="center">OpenAI Assistants API</th>
+  </tr>
+  <tr>
+    <td align="center">Programming Approach</td>
+    <td align="center">API + App-oriented</td>
+    <td align="center">Python Code</td>
+    <td align="center">App-oriented</td>
+    <td align="center">API-oriented</td>
+  </tr>
+  <tr>
+    <td align="center">Supported LLMs</td>
+    <td align="center">Rich Variety</td>
+    <td align="center">Rich Variety</td>
+    <td align="center">Rich Variety</td>
+    <td align="center">OpenAI-only</td>
+  </tr>
+  <tr>
+    <td align="center">RAG Engine</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+  </tr>
+  <tr>
+    <td align="center">Agent</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+    <td align="center">✅</td>
+  </tr>
+  <tr>
+    <td align="center">Workflow</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+  </tr>
+  <tr>
+    <td align="center">Observability</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+    <td align="center">❌</td>
+  </tr>
+  <tr>
+    <td align="center">Enterprise Feature (SSO/Access control)</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+    <td align="center">❌</td>
+    <td align="center">❌</td>
+  </tr>
+  <tr>
+    <td align="center">Local Deployment</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+  </tr>
+</table>

 ## Using Dify

--- a/README_AR.md
+++ b/README_AR.md
@@ -21,6 +21,9 @@
    <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
        <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
            alt="follow on X(Twitter)"></a>
+    <a href="https://www.linkedin.com/company/langgenius/" target="_blank">
+        <img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
+            alt="follow on LinkedIn"></a>
    <a href="https://hub.docker.com/u/langgenius" target="_blank">
        <img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
    <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
--- a/README_CN.md
+++ b/README_CN.md
@@ -21,6 +21,9 @@
    <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
        <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
            alt="follow on X(Twitter)"></a>
+    <a href="https://www.linkedin.com/company/langgenius/" target="_blank">
+        <img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
+            alt="follow on LinkedIn"></a>
    <a href="https://hub.docker.com/u/langgenius" target="_blank">
        <img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
    <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
--- a/README_ES.md
+++ b/README_ES.md
@@ -21,6 +21,9 @@
    <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
        <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
            alt="seguir en X(Twitter)"></a>
+    <a href="https://www.linkedin.com/company/langgenius/" target="_blank">
+        <img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
+            alt="seguir en LinkedIn"></a>
    <a href="https://hub.docker.com/u/langgenius" target="_blank">
        <img alt="Descargas de Docker" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
    <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
--- a/README_FR.md
+++ b/README_FR.md
@@ -21,6 +21,9 @@
    <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
        <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
            alt="suivre sur X(Twitter)"></a>
+    <a href="https://www.linkedin.com/company/langgenius/" target="_blank">
+        <img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
+            alt="suivre sur LinkedIn"></a>
    <a href="https://hub.docker.com/u/langgenius" target="_blank">
        <img alt="Tirages Docker" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
    <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
--- a/README_JA.md
+++ b/README_JA.md
@@ -21,6 +21,9 @@
    <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
        <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
            alt="X(Twitter)でフォロー"></a>
+    <a href="https://www.linkedin.com/company/langgenius/" target="_blank">
+        <img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
+            alt="LinkedInでフォロー"></a>
    <a href="https://hub.docker.com/u/langgenius" target="_blank">
        <img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
    <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
--- a/README_KL.md
+++ b/README_KL.md
@@ -21,6 +21,9 @@
    <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
        <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
            alt="follow on X(Twitter)"></a>
+    <a href="https://www.linkedin.com/company/langgenius/" target="_blank">
+        <img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
+            alt="follow on LinkedIn"></a>
    <a href="https://hub.docker.com/u/langgenius" target="_blank">
        <img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
    <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
@@ -84,9 +87,7 @@ Dify is an open-source LLM app development platform. Its intuitive interface com

 ## Feature Comparison
 <table style="width: 100%;">
-  <tr
-
->
+  <tr>
    <th align="center">Feature</th>
    <th align="center">Dify.AI</th>
    <th align="center">LangChain</th>
--- a/README_KR.md
+++ b/README_KR.md
@@ -21,6 +21,9 @@
    <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
        <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
            alt="follow on X(Twitter)"></a>
+    <a href="https://www.linkedin.com/company/langgenius/" target="_blank">
+        <img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
+            alt="follow on LinkedIn"></a>
    <a href="https://hub.docker.com/u/langgenius" target="_blank">
        <img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
    <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
--- a/README_PT.md
+++ b/README_PT.md
@@ -25,6 +25,9 @@
    <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
        <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
            alt="follow on X(Twitter)"></a>
+    <a href="https://www.linkedin.com/company/langgenius/" target="_blank">
+        <img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
+            alt="follow on LinkedIn"></a>
    <a href="https://hub.docker.com/u/langgenius" target="_blank">
        <img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
    <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
--- a/README_SI.md
+++ b/README_SI.md
@@ -22,6 +22,9 @@
    <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
        <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
            alt="follow on X(Twitter)"></a>
+    <a href="https://www.linkedin.com/company/langgenius/" target="_blank">
+        <img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
+            alt="follow on LinkedIn"></a>
    <a href="https://hub.docker.com/u/langgenius" target="_blank">
        <img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
    <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
@@ -103,6 +106,73 @@ Prosimo, glejte naša pogosta vprašanja [FAQ](https://docs.dify.ai/getting-star
 **7. Backend-as-a-Service**: 
  AVse ponudbe Difyja so opremljene z ustreznimi API-ji, tako da lahko Dify brez težav integrirate v svojo poslovno logiko.

+## Primerjava Funkcij
+
+<table style="width: 100%;">
+  <tr>
+    <th align="center">Funkcija</th>
+    <th align="center">Dify.AI</th>
+    <th align="center">LangChain</th>
+    <th align="center">Flowise</th>
+    <th align="center">OpenAI Assistants API</th>
+  </tr>
+  <tr>
+    <td align="center">Programski pristop</td>
+    <td align="center">API + usmerjeno v aplikacije</td>
+    <td align="center">Python koda</td>
+    <td align="center">Usmerjeno v aplikacije</td>
+    <td align="center">Usmerjeno v API</td>
+  </tr>
+  <tr>
+    <td align="center">Podprti LLM-ji</td>
+    <td align="center">Bogata izbira</td>
+    <td align="center">Bogata izbira</td>
+    <td align="center">Bogata izbira</td>
+    <td align="center">Samo OpenAI</td>
+  </tr>
+  <tr>
+    <td align="center">RAG pogon</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+  </tr>
+  <tr>
+    <td align="center">Agent</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+    <td align="center">✅</td>
+  </tr>
+  <tr>
+    <td align="center">Potek dela</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+  </tr>
+  <tr>
+    <td align="center">Spremljanje</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+    <td align="center">❌</td>
+  </tr>
+  <tr>
+    <td align="center">Funkcija za podjetja (SSO/nadzor dostopa)</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+    <td align="center">❌</td>
+    <td align="center">❌</td>
+  </tr>
+  <tr>
+    <td align="center">Lokalna namestitev</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+  </tr>
+</table>

 ## Uporaba Dify

@@ -184,4 +254,4 @@ Zaradi zaščite vaše zasebnosti se izogibajte objavljanju varnostnih vprašanj

 ## Licenca

-To skladišče je na voljo pod [odprtokodno licenco Dify](LICENSE) , ki je v bistvu Apache 2.0 z nekaj dodatnimi omejitvami.
+To skladišče je na voljo pod [odprtokodno licenco Dify](LICENSE) , ki je v bistvu Apache 2.0 z nekaj dodatnimi omejitvami.
--- a/README_TR.md
+++ b/README_TR.md
@@ -21,6 +21,9 @@
    <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
        <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
            alt="X(Twitter)'da takip et"></a>
+    <a href="https://www.linkedin.com/company/langgenius/" target="_blank">
+        <img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
+            alt="LinkedIn'da takip et"></a>
    <a href="https://hub.docker.com/u/langgenius" target="_blank">
        <img alt="Docker Çekmeleri" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
    <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
@@ -62,8 +65,6 @@ Görsel bir arayüz üzerinde güçlü AI iş akışları oluşturun ve test edi
 ![providers-v5](https://github.com/langgenius/dify/assets/13230914/5a17bdbe-097a-4100-8363-40255b70f6e3)


-Özür dilerim, haklısınız. Daha anlamlı ve akıcı bir çeviri yapmaya çalışayım. İşte güncellenmiş çeviri:
-
 **3. Prompt IDE**: 
  Komut istemlerini oluşturmak, model performansını karşılaştırmak ve sohbet tabanlı uygulamalara metin-konuşma gibi ek özellikler eklemek için kullanıcı dostu bir arayüz.

@@ -150,8 +151,6 @@ Görsel bir arayüz üzerinde güçlü AI iş akışları oluşturun ve test edi
 ## Dify'ı Kullanma

 - **Cloud </br>**
-İşte verdiğiniz metnin Türkçe çevirisi, kod bloğu içinde:
- 
 Herkesin sıfır kurulumla denemesi için bir [Dify Cloud](https://dify.ai) hizmeti sunuyoruz. Bu hizmet, kendi kendine dağıtılan versiyonun tüm yeteneklerini sağlar ve sandbox planında 200 ücretsiz GPT-4 çağrısı içerir.

 - **Dify Topluluk Sürümünü Kendi Sunucunuzda Barındırma</br>**
@@ -177,8 +176,6 @@ GitHub'da Dify'a yıldız verin ve yeni sürümlerden anında haberdar olun.
 >- RAM >= 4GB

 </br>
-İşte verdiğiniz metnin Türkçe çevirisi, kod bloğu içinde:
-
 Dify sunucusunu başlatmanın en kolay yolu, [docker-compose.yml](docker/docker-compose.yaml) dosyamızı çalıştırmaktır. Kurulum komutunu çalıştırmadan önce, makinenizde [Docker](https://docs.docker.com/get-docker/) ve [Docker Compose](https://docs.docker.com/compose/install/)'un kurulu olduğundan emin olun:

 ```bash
--- a/README_VI.md
+++ b/README_VI.md
@@ -21,6 +21,9 @@
    <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
        <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
            alt="theo dõi trên X(Twitter)"></a>
+    <a href="https://www.linkedin.com/company/langgenius/" target="_blank">
+        <img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
+            alt="theo dõi trên LinkedIn"></a>
    <a href="https://hub.docker.com/u/langgenius" target="_blank">
        <img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
    <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
--- a/api/Dockerfile
+++ b/api/Dockerfile
@@ -48,16 +48,18 @@ ENV TZ=UTC

 WORKDIR /app/api

-RUN apt-get update \
-    && apt-get install -y --no-install-recommends curl nodejs libgmp-dev libmpfr-dev libmpc-dev \
-    # if you located in China, you can use aliyun mirror to speed up
-    # && echo "deb http://mirrors.aliyun.com/debian testing main" > /etc/apt/sources.list \
-    && echo "deb http://deb.debian.org/debian testing main" > /etc/apt/sources.list \
-    && apt-get update \
-    # For Security
-    && apt-get install -y --no-install-recommends expat=2.6.4-1 libldap-2.5-0=2.5.19+dfsg-1 perl=5.40.0-8 libsqlite3-0=3.46.1-1 zlib1g=1:1.3.dfsg+really1.3.1-1+b1 \
-    # install a chinese font to support the use of tools like matplotlib
-    && apt-get install -y fonts-noto-cjk \
+RUN \
+    apt-get update \
+    # Install dependencies
+    && apt-get install -y --no-install-recommends \
+        # basic environment
+        curl nodejs libgmp-dev libmpfr-dev libmpc-dev \
+        # For Security
+        expat libldap-2.5-0 perl libsqlite3-0 zlib1g \
+        # install a chinese font to support the use of tools like matplotlib
+        fonts-noto-cjk \
+        # install libmagic to support the use of python-magic guess MIMETYPE
+        libmagic1 \
    && apt-get autoremove -y \
    && rm -rf /var/lib/apt/lists/*

@@ -76,7 +78,6 @@ COPY . /app/api/
 COPY docker/entrypoint.sh /entrypoint.sh
 RUN chmod +x /entrypoint.sh

-
 ARG COMMIT_SHA
 ENV COMMIT_SHA=${COMMIT_SHA}

--- a/api/README.md
+++ b/api/README.md
@@ -37,7 +37,13 @@

 4. Create environment.

-   Dify API service uses [Poetry](https://python-poetry.org/docs/) to manage dependencies. You can execute `poetry shell` to activate the environment.
+   Dify API service uses [Poetry](https://python-poetry.org/docs/) to manage dependencies. First, you need to add the poetry shell plugin, if you don't have it already, in order to run in a virtual environment. [Note: Poetry shell is no longer a native command so you need to install the poetry plugin beforehand]
+
+   ```bash
+   poetry self add poetry-plugin-shell
+   ```
+   
+   Then, You can execute `poetry shell` to activate the environment.

 5. Install dependencies

--- a/api/configs/feature/init.py
+++ b/api/configs/feature/init.py
@@ -315,8 +315,8 @@ class HttpConfig(BaseSettings):
    )

    RESPECT_XFORWARD_HEADERS_ENABLED: bool = Field(
-        description="Enable or disable the X-Forwarded-For Proxy Fix middleware from Werkzeug"
-        " to respect X-* headers to redirect clients",
+        description="Enable handling of X-Forwarded-For, X-Forwarded-Proto, and X-Forwarded-Port headers"
+        " when the app is behind a single trusted reverse proxy.",
        default=False,
    )

@@ -498,6 +498,11 @@ class AuthConfig(BaseSettings):
        default=86400,
    )

+    FORGOT_PASSWORD_LOCKOUT_DURATION: PositiveInt = Field(
+        description="Time (in seconds) a user must wait before retrying password reset after exceeding the rate limit.",
+        default=86400,
+    )
+

 class ModerationConfig(BaseSettings):
    """
--- a/api/configs/feature/hosted_service/init.py
+++ b/api/configs/feature/hosted_service/init.py
@@ -1,9 +1,40 @@
 from typing import Optional

-from pydantic import Field, NonNegativeInt
+from pydantic import Field, NonNegativeInt, computed_field
 from pydantic_settings import BaseSettings


+class HostedCreditConfig(BaseSettings):
+    HOSTED_MODEL_CREDIT_CONFIG: str = Field(
+        description="Model credit configuration in format 'model:credits,model:credits', e.g., 'gpt-4:20,gpt-4o:10'",
+        default="",
+    )
+
+    def get_model_credits(self, model_name: str) -> int:
+        """
+        Get credit value for a specific model name.
+        Returns 1 if model is not found in configuration (default credit).
+
+        :param model_name: The name of the model to search for
+        :return: The credit value for the model
+        """
+        if not self.HOSTED_MODEL_CREDIT_CONFIG:
+            return 1
+
+        try:
+            credit_map = dict(
+                item.strip().split(":", 1) for item in self.HOSTED_MODEL_CREDIT_CONFIG.split(",") if ":" in item
+            )
+
+            # Search for matching model pattern
+            for pattern, credit in credit_map.items():
+                if pattern.strip() == model_name:
+                    return int(credit)
+            return 1  # Default quota if no match found
+        except (ValueError, AttributeError):
+            return 1  # Return default quota if parsing fails
+
+
 class HostedOpenAiConfig(BaseSettings):
    """
    Configuration for hosted OpenAI service
@@ -202,5 +233,7 @@ class HostedServiceConfig(
    HostedZhipuAIConfig,
    # moderation
    HostedModerationConfig,
+    # credit config
+    HostedCreditConfig,
 ):
    pass
--- a/api/configs/packaging/init.py
+++ b/api/configs/packaging/init.py
@@ -9,7 +9,7 @@ class PackagingInfo(BaseSettings):

    CURRENT_VERSION: str = Field(
        description="Dify version",
-        default="0.15.2",
+        default="0.15.3",
    )

    COMMIT_SHA: str = Field(
--- a/api/constants/init.py
+++ b/api/constants/init.py
@@ -15,7 +15,7 @@ AUDIO_EXTENSIONS.extend([ext.upper() for ext in AUDIO_EXTENSIONS])

 if dify_config.ETL_TYPE == "Unstructured":
    DOCUMENT_EXTENSIONS = ["txt", "markdown", "md", "mdx", "pdf", "html", "htm", "xlsx", "xls"]
-    DOCUMENT_EXTENSIONS.extend(("docx", "csv", "eml", "msg", "pptx", "xml", "epub"))
+    DOCUMENT_EXTENSIONS.extend(("doc", "docx", "csv", "eml", "msg", "pptx", "xml", "epub"))
    if dify_config.UNSTRUCTURED_API_URL:
        DOCUMENT_EXTENSIONS.append("ppt")
    DOCUMENT_EXTENSIONS.extend([ext.upper() for ext in DOCUMENT_EXTENSIONS])
--- a/api/controllers/common/helpers.py
+++ b/api/controllers/common/helpers.py
@@ -1,12 +1,32 @@
 import mimetypes
 import os
+import platform
 import re
 import urllib.parse
+import warnings
 from collections.abc import Mapping
 from typing import Any
 from uuid import uuid4

 import httpx
+
+try:
+    import magic
+except ImportError:
+    if platform.system() == "Windows":
+        warnings.warn(
+            "To use python-magic guess MIMETYPE, you need to run `pip install python-magic-bin`", stacklevel=2
+        )
+    elif platform.system() == "Darwin":
+        warnings.warn("To use python-magic guess MIMETYPE, you need to run `brew install libmagic`", stacklevel=2)
+    elif platform.system() == "Linux":
+        warnings.warn(
+            "To use python-magic guess MIMETYPE, you need to run `sudo apt-get install libmagic1`", stacklevel=2
+        )
+    else:
+        warnings.warn("To use python-magic guess MIMETYPE, you need to install `libmagic`", stacklevel=2)
+    magic = None  # type: ignore
+
 from pydantic import BaseModel

 from configs import dify_config
@@ -47,6 +67,13 @@ def guess_file_info_from_response(response: httpx.Response):
        # If guessing fails, use Content-Type from response headers
        mimetype = response.headers.get("Content-Type", "application/octet-stream")

+    # Use python-magic to guess MIME type if still unknown or generic
+    if mimetype == "application/octet-stream" and magic is not None:
+        try:
+            mimetype = magic.from_buffer(response.content[:1024], mime=True)
+        except magic.MagicException:
+            pass
+
    extension = os.path.splitext(filename)[1]

    # Ensure filename has an extension
--- a/api/controllers/console/auth/error.py
+++ b/api/controllers/console/auth/error.py
@@ -59,3 +59,9 @@ class EmailCodeAccountDeletionRateLimitExceededError(BaseHTTPException):
    error_code = "email_code_account_deletion_rate_limit_exceeded"
    description = "Too many account deletion emails have been sent. Please try again in 5 minutes."
    code = 429
+
+
+class EmailPasswordResetLimitError(BaseHTTPException):
+    error_code = "email_password_reset_limit"
+    description = "Too many failed password reset attempts. Please try again in 24 hours."
+    code = 429
--- a/api/controllers/console/auth/forgot_password.py
+++ b/api/controllers/console/auth/forgot_password.py
@@ -6,7 +6,13 @@ from flask_restful import Resource, reqparse  # type: ignore

 from constants.languages import languages
 from controllers.console import api
-from controllers.console.auth.error import EmailCodeError, InvalidEmailError, InvalidTokenError, PasswordMismatchError
+from controllers.console.auth.error import (
+    EmailCodeError,
+    EmailPasswordResetLimitError,
+    InvalidEmailError,
+    InvalidTokenError,
+    PasswordMismatchError,
+)
 from controllers.console.error import AccountInFreezeError, AccountNotFound, EmailSendIpLimitError
 from controllers.console.wraps import setup_required
 from events.tenant_event import tenant_was_created
@@ -62,6 +68,10 @@ class ForgotPasswordCheckApi(Resource):

        user_email = args["email"]

+        is_forgot_password_error_rate_limit = AccountService.is_forgot_password_error_rate_limit(args["email"])
+        if is_forgot_password_error_rate_limit:
+            raise EmailPasswordResetLimitError()
+
        token_data = AccountService.get_reset_password_data(args["token"])
        if token_data is None:
            raise InvalidTokenError()
@@ -70,8 +80,10 @@ class ForgotPasswordCheckApi(Resource):
            raise InvalidEmailError()

        if args["code"] != token_data.get("code"):
+            AccountService.add_forgot_password_error_rate_limit(args["email"])
            raise EmailCodeError()

+        AccountService.reset_forgot_password_error_rate_limit(args["email"])
        return {"is_valid": True, "email": token_data.get("email")}


--- a/api/controllers/console/datasets/datasets.py
+++ b/api/controllers/console/datasets/datasets.py
@@ -620,7 +620,6 @@ class DatasetRetrievalSettingApi(Resource):
        match vector_type:
            case (
                VectorType.RELYT
-                | VectorType.PGVECTOR
                | VectorType.TIDB_VECTOR
                | VectorType.CHROMA
                | VectorType.TENCENT
--- a/api/controllers/console/explore/message.py
+++ b/api/controllers/console/explore/message.py
@@ -50,7 +50,7 @@ class MessageListApi(InstalledAppResource):

        try:
            return MessageService.pagination_by_first_id(
-                app_model, current_user, args["conversation_id"], args["first_id"], args["limit"], "desc"
+                app_model, current_user, args["conversation_id"], args["first_id"], args["limit"]
            )
        except services.errors.conversation.ConversationNotExistsError:
            raise NotFound("Conversation Not Exists.")
--- a/api/controllers/inner_api/workspace/workspace.py
+++ b/api/controllers/inner_api/workspace/workspace.py
@@ -1,3 +1,5 @@
+import json
+
 from flask_restful import Resource, reqparse  # type: ignore

 from controllers.console.wraps import setup_required
@@ -29,4 +31,34 @@ class EnterpriseWorkspace(Resource):
        return {"message": "enterprise workspace created."}


+class EnterpriseWorkspaceNoOwnerEmail(Resource):
+    @setup_required
+    @inner_api_only
+    def post(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument("name", type=str, required=True, location="json")
+        args = parser.parse_args()
+
+        tenant = TenantService.create_tenant(args["name"], is_from_dashboard=True)
+
+        tenant_was_created.send(tenant)
+
+        resp = {
+            "id": tenant.id,
+            "name": tenant.name,
+            "encrypt_public_key": tenant.encrypt_public_key,
+            "plan": tenant.plan,
+            "status": tenant.status,
+            "custom_config": json.loads(tenant.custom_config) if tenant.custom_config else {},
+            "created_at": tenant.created_at.isoformat() + "Z" if tenant.created_at else None,
+            "updated_at": tenant.updated_at.isoformat() + "Z" if tenant.updated_at else None,
+        }
+
+        return {
+            "message": "enterprise workspace created.",
+            "tenant": resp,
+        }
+
+
 api.add_resource(EnterpriseWorkspace, "/enterprise/workspace")
+api.add_resource(EnterpriseWorkspaceNoOwnerEmail, "/enterprise/workspace/ownerless")
--- a/api/controllers/service_api/dataset/document.py
+++ b/api/controllers/service_api/dataset/document.py
@@ -18,6 +18,7 @@ from controllers.service_api.app.error import (
 from controllers.service_api.dataset.error import (
    ArchivedDocumentImmutableError,
    DocumentIndexingError,
+    InvalidMetadataError,
 )
 from controllers.service_api.wraps import DatasetApiResource, cloud_edition_billing_resource_check
 from core.errors.error import ProviderTokenNotInitError
@@ -50,6 +51,9 @@ class DocumentAddByTextApi(DatasetApiResource):
            "indexing_technique", type=str, choices=Dataset.INDEXING_TECHNIQUE_LIST, nullable=False, location="json"
        )
        parser.add_argument("retrieval_model", type=dict, required=False, nullable=False, location="json")
+        parser.add_argument("doc_type", type=str, required=False, nullable=True, location="json")
+        parser.add_argument("doc_metadata", type=dict, required=False, nullable=True, location="json")
+
        args = parser.parse_args()
        dataset_id = str(dataset_id)
        tenant_id = str(tenant_id)
@@ -61,6 +65,28 @@ class DocumentAddByTextApi(DatasetApiResource):
        if not dataset.indexing_technique and not args["indexing_technique"]:
            raise ValueError("indexing_technique is required.")

+        # Validate metadata if provided
+        if args.get("doc_type") or args.get("doc_metadata"):
+            if not args.get("doc_type") or not args.get("doc_metadata"):
+                raise InvalidMetadataError("Both doc_type and doc_metadata must be provided when adding metadata")
+
+            if args["doc_type"] not in DocumentService.DOCUMENT_METADATA_SCHEMA:
+                raise InvalidMetadataError(
+                    "Invalid doc_type. Must be one of: " + ", ".join(DocumentService.DOCUMENT_METADATA_SCHEMA.keys())
+                )
+
+            if not isinstance(args["doc_metadata"], dict):
+                raise InvalidMetadataError("doc_metadata must be a dictionary")
+
+            # Validate metadata schema based on doc_type
+            if args["doc_type"] != "others":
+                metadata_schema = DocumentService.DOCUMENT_METADATA_SCHEMA[args["doc_type"]]
+                for key, value in args["doc_metadata"].items():
+                    if key in metadata_schema and not isinstance(value, metadata_schema[key]):
+                        raise InvalidMetadataError(f"Invalid type for metadata field {key}")
+            # set to MetaDataConfig
+            args["metadata"] = {"doc_type": args["doc_type"], "doc_metadata": args["doc_metadata"]}
+
        text = args.get("text")
        name = args.get("name")
        if text is None or name is None:
@@ -107,6 +133,8 @@ class DocumentUpdateByTextApi(DatasetApiResource):
            "doc_language", type=str, default="English", required=False, nullable=False, location="json"
        )
        parser.add_argument("retrieval_model", type=dict, required=False, nullable=False, location="json")
+        parser.add_argument("doc_type", type=str, required=False, nullable=True, location="json")
+        parser.add_argument("doc_metadata", type=dict, required=False, nullable=True, location="json")
        args = parser.parse_args()
        dataset_id = str(dataset_id)
        tenant_id = str(tenant_id)
@@ -115,6 +143,32 @@ class DocumentUpdateByTextApi(DatasetApiResource):
        if not dataset:
            raise ValueError("Dataset is not exist.")

+        # indexing_technique is already set in dataset since this is an update
+        args["indexing_technique"] = dataset.indexing_technique
+
+        # Validate metadata if provided
+        if args.get("doc_type") or args.get("doc_metadata"):
+            if not args.get("doc_type") or not args.get("doc_metadata"):
+                raise InvalidMetadataError("Both doc_type and doc_metadata must be provided when adding metadata")
+
+            if args["doc_type"] not in DocumentService.DOCUMENT_METADATA_SCHEMA:
+                raise InvalidMetadataError(
+                    "Invalid doc_type. Must be one of: " + ", ".join(DocumentService.DOCUMENT_METADATA_SCHEMA.keys())
+                )
+
+            if not isinstance(args["doc_metadata"], dict):
+                raise InvalidMetadataError("doc_metadata must be a dictionary")
+
+            # Validate metadata schema based on doc_type
+            if args["doc_type"] != "others":
+                metadata_schema = DocumentService.DOCUMENT_METADATA_SCHEMA[args["doc_type"]]
+                for key, value in args["doc_metadata"].items():
+                    if key in metadata_schema and not isinstance(value, metadata_schema[key]):
+                        raise InvalidMetadataError(f"Invalid type for metadata field {key}")
+
+            # set to MetaDataConfig
+            args["metadata"] = {"doc_type": args["doc_type"], "doc_metadata": args["doc_metadata"]}
+
        if args["text"]:
            text = args.get("text")
            name = args.get("name")
@@ -161,6 +215,30 @@ class DocumentAddByFileApi(DatasetApiResource):
            args["doc_form"] = "text_model"
        if "doc_language" not in args:
            args["doc_language"] = "English"
+
+        # Validate metadata if provided
+        if args.get("doc_type") or args.get("doc_metadata"):
+            if not args.get("doc_type") or not args.get("doc_metadata"):
+                raise InvalidMetadataError("Both doc_type and doc_metadata must be provided when adding metadata")
+
+            if args["doc_type"] not in DocumentService.DOCUMENT_METADATA_SCHEMA:
+                raise InvalidMetadataError(
+                    "Invalid doc_type. Must be one of: " + ", ".join(DocumentService.DOCUMENT_METADATA_SCHEMA.keys())
+                )
+
+            if not isinstance(args["doc_metadata"], dict):
+                raise InvalidMetadataError("doc_metadata must be a dictionary")
+
+            # Validate metadata schema based on doc_type
+            if args["doc_type"] != "others":
+                metadata_schema = DocumentService.DOCUMENT_METADATA_SCHEMA[args["doc_type"]]
+                for key, value in args["doc_metadata"].items():
+                    if key in metadata_schema and not isinstance(value, metadata_schema[key]):
+                        raise InvalidMetadataError(f"Invalid type for metadata field {key}")
+
+            # set to MetaDataConfig
+            args["metadata"] = {"doc_type": args["doc_type"], "doc_metadata": args["doc_metadata"]}
+
        # get dataset info
        dataset_id = str(dataset_id)
        tenant_id = str(tenant_id)
@@ -228,6 +306,29 @@ class DocumentUpdateByFileApi(DatasetApiResource):
        if "doc_language" not in args:
            args["doc_language"] = "English"

+        # Validate metadata if provided
+        if args.get("doc_type") or args.get("doc_metadata"):
+            if not args.get("doc_type") or not args.get("doc_metadata"):
+                raise InvalidMetadataError("Both doc_type and doc_metadata must be provided when adding metadata")
+
+            if args["doc_type"] not in DocumentService.DOCUMENT_METADATA_SCHEMA:
+                raise InvalidMetadataError(
+                    "Invalid doc_type. Must be one of: " + ", ".join(DocumentService.DOCUMENT_METADATA_SCHEMA.keys())
+                )
+
+            if not isinstance(args["doc_metadata"], dict):
+                raise InvalidMetadataError("doc_metadata must be a dictionary")
+
+            # Validate metadata schema based on doc_type
+            if args["doc_type"] != "others":
+                metadata_schema = DocumentService.DOCUMENT_METADATA_SCHEMA[args["doc_type"]]
+                for key, value in args["doc_metadata"].items():
+                    if key in metadata_schema and not isinstance(value, metadata_schema[key]):
+                        raise InvalidMetadataError(f"Invalid type for metadata field {key}")
+
+            # set to MetaDataConfig
+            args["metadata"] = {"doc_type": args["doc_type"], "doc_metadata": args["doc_metadata"]}
+
        # get dataset info
        dataset_id = str(dataset_id)
        tenant_id = str(tenant_id)
--- a/api/controllers/web/message.py
+++ b/api/controllers/web/message.py
@@ -91,7 +91,7 @@ class MessageListApi(WebApiResource):

        try:
            return MessageService.pagination_by_first_id(
-                app_model, end_user, args["conversation_id"], args["first_id"], args["limit"], "desc"
+                app_model, end_user, args["conversation_id"], args["first_id"], args["limit"]
            )
        except services.errors.conversation.ConversationNotExistsError:
            raise NotFound("Conversation Not Exists.")
--- a/api/core/app/apps/advanced_chat/app_generator.py
+++ b/api/core/app/apps/advanced_chat/app_generator.py
@@ -140,9 +140,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
            app_config=app_config,
            file_upload_config=file_extra_config,
            conversation_id=conversation.id if conversation else None,
-            inputs=conversation.inputs
-            if conversation
-            else self._prepare_user_inputs(
+            inputs=self._prepare_user_inputs(
                user_inputs=inputs, variables=app_config.variables, tenant_id=app_model.tenant_id
            ),
            query=query,
--- a/api/core/app/apps/agent_chat/app_generator.py
+++ b/api/core/app/apps/agent_chat/app_generator.py
@@ -148,9 +148,7 @@ class AgentChatAppGenerator(MessageBasedAppGenerator):
            model_conf=ModelConfigConverter.convert(app_config),
            file_upload_config=file_extra_config,
            conversation_id=conversation.id if conversation else None,
-            inputs=conversation.inputs
-            if conversation
-            else self._prepare_user_inputs(
+            inputs=self._prepare_user_inputs(
                user_inputs=inputs, variables=app_config.variables, tenant_id=app_model.tenant_id
            ),
            query=query,
--- a/api/core/app/apps/agent_chat/app_runner.py
+++ b/api/core/app/apps/agent_chat/app_runner.py
@@ -202,7 +202,7 @@ class AgentChatAppRunner(AppRunner):
        # change function call strategy based on LLM model
        llm_model = cast(LargeLanguageModel, model_instance.model_type_instance)
        model_schema = llm_model.get_model_schema(model_instance.model, model_instance.credentials)
-        if not model_schema or not model_schema.features:
+        if not model_schema:
            raise ValueError("Model schema not found")

        if {ModelFeature.MULTI_TOOL_CALL, ModelFeature.TOOL_CALL}.intersection(model_schema.features or []):
--- a/api/core/app/apps/chat/app_generator.py
+++ b/api/core/app/apps/chat/app_generator.py
@@ -141,9 +141,7 @@ class ChatAppGenerator(MessageBasedAppGenerator):
            model_conf=ModelConfigConverter.convert(app_config),
            file_upload_config=file_extra_config,
            conversation_id=conversation.id if conversation else None,
-            inputs=conversation.inputs
-            if conversation
-            else self._prepare_user_inputs(
+            inputs=self._prepare_user_inputs(
                user_inputs=inputs, variables=app_config.variables, tenant_id=app_model.tenant_id
            ),
            query=query,
--- a/api/core/app/task_pipeline/workflow_cycle_manage.py
+++ b/api/core/app/task_pipeline/workflow_cycle_manage.py
@@ -842,4 +842,4 @@ class WorkflowCycleManage:
        if node_execution_id not in self._workflow_node_executions:
            raise ValueError(f"Workflow node execution not found: {node_execution_id}")
        cached_workflow_node_execution = self._workflow_node_executions[node_execution_id]
-        return cached_workflow_node_execution
+        return session.merge(cached_workflow_node_execution)
--- a/api/core/helper/ssrf_proxy.py
+++ b/api/core/helper/ssrf_proxy.py
@@ -11,15 +11,6 @@ from configs import dify_config

 SSRF_DEFAULT_MAX_RETRIES = dify_config.SSRF_DEFAULT_MAX_RETRIES

-proxy_mounts = (
-    {
-        "http://": httpx.HTTPTransport(proxy=dify_config.SSRF_PROXY_HTTP_URL),
-        "https://": httpx.HTTPTransport(proxy=dify_config.SSRF_PROXY_HTTPS_URL),
-    }
-    if dify_config.SSRF_PROXY_HTTP_URL and dify_config.SSRF_PROXY_HTTPS_URL
-    else None
-)
-
 BACKOFF_FACTOR = 0.5
 STATUS_FORCELIST = [429, 500, 502, 503, 504]

@@ -51,7 +42,11 @@ def make_request(method, url, max_retries=SSRF_DEFAULT_MAX_RETRIES, **kwargs):
            if dify_config.SSRF_PROXY_ALL_URL:
                with httpx.Client(proxy=dify_config.SSRF_PROXY_ALL_URL) as client:
                    response = client.request(method=method, url=url, **kwargs)
-            elif proxy_mounts:
+            elif dify_config.SSRF_PROXY_HTTP_URL and dify_config.SSRF_PROXY_HTTPS_URL:
+                proxy_mounts = {
+                    "http://": httpx.HTTPTransport(proxy=dify_config.SSRF_PROXY_HTTP_URL),
+                    "https://": httpx.HTTPTransport(proxy=dify_config.SSRF_PROXY_HTTPS_URL),
+                }
                with httpx.Client(mounts=proxy_mounts) as client:
                    response = client.request(method=method, url=url, **kwargs)
            else:
--- a/api/core/model_runtime/entities/init.py
+++ b/api/core/model_runtime/entities/init.py
@@ -1,4 +1,4 @@
-from .llm_entities import LLMResult, LLMResultChunk, LLMResultChunkDelta, LLMUsage
+from .llm_entities import LLMMode, LLMResult, LLMResultChunk, LLMResultChunkDelta, LLMUsage
 from .message_entities import (
    AssistantPromptMessage,
    AudioPromptMessageContent,
@@ -23,6 +23,7 @@ __all__ = [
    "AudioPromptMessageContent",
    "DocumentPromptMessageContent",
    "ImagePromptMessageContent",
+    "LLMMode",
    "LLMResult",
    "LLMResultChunk",
    "LLMResultChunkDelta",
--- a/api/core/model_runtime/entities/llm_entities.py
+++ b/api/core/model_runtime/entities/llm_entities.py
@@ -1,5 +1,5 @@
 from decimal import Decimal
-from enum import Enum
+from enum import StrEnum
 from typing import Optional

 from pydantic import BaseModel
@@ -8,7 +8,7 @@ from core.model_runtime.entities.message_entities import AssistantPromptMessage,
 from core.model_runtime.entities.model_entities import ModelUsage, PriceInfo


-class LLMMode(Enum):
+class LLMMode(StrEnum):
    """
    Enum class for large language model mode.
    """
--- a/api/core/model_runtime/model_providers/__base/ai_model.py
+++ b/api/core/model_runtime/model_providers/__base/ai_model.py
@@ -221,13 +221,12 @@ class AIModel(ABC):
        :param credentials: model credentials
        :return: model schema
        """
-        # get predefined models (predefined_models)
-        models = self.predefined_models()
-
-        model_map = {model.model: model for model in models}
-        if model in model_map:
-            return model_map[model]
+        # Try to get model schema from predefined models
+        for predefined_model in self.predefined_models():
+            if model == predefined_model.model:
+                return predefined_model

+        # Try to get model schema from credentials
        if credentials:
            model_schema = self.get_customizable_model_schema_from_credentials(model, credentials)
            if model_schema:
--- a/api/core/model_runtime/model_providers/__base/large_language_model.py
+++ b/api/core/model_runtime/model_providers/__base/large_language_model.py
@@ -400,6 +400,32 @@ if you are not sure about the structure.
                    ),
                )

+    def _wrap_thinking_by_reasoning_content(self, delta: dict, is_reasoning: bool) -> tuple[str, bool]:
+        """
+        If the reasoning response is from delta.get("reasoning_content"), we wrap
+        it with HTML think tag.
+
+        :param delta: delta dictionary from LLM streaming response
+        :param is_reasoning: is reasoning
+        :return: tuple of (processed_content, is_reasoning)
+        """
+
+        content = delta.get("content") or ""
+        reasoning_content = delta.get("reasoning_content")
+
+        if reasoning_content:
+            if not is_reasoning:
+                content = "<think>\n" + reasoning_content
+                is_reasoning = True
+            else:
+                content = reasoning_content
+        elif is_reasoning and content:
+            # do not end reasoning when content is empty
+            # there may be more reasoning_content later that follows previous reasoning closely
+            content = "\n</think>" + content
+            is_reasoning = False
+        return content, is_reasoning
+
    def _invoke_result_generator(
        self,
        model: str,
--- a/api/core/model_runtime/model_providers/_position.yaml
+++ b/api/core/model_runtime/model_providers/_position.yaml
@@ -1,4 +1,5 @@
 - openai
+- deepseek
 - anthropic
 - azure_openai
 - google
@@ -32,7 +33,6 @@
 - localai
 - volcengine_maas
 - openai_api_compatible
- deepseek
 - hunyuan
 - siliconflow
 - perfxcloud
--- a/api/core/model_runtime/model_providers/azure_ai_studio/azure_ai_studio.yaml
+++ b/api/core/model_runtime/model_providers/azure_ai_studio/azure_ai_studio.yaml
@@ -51,6 +51,40 @@ model_credential_schema:
      show_on:
        - variable: __model_type
          value: llm
+    - variable: mode
+      show_on:
+        - variable: __model_type
+          value: llm
+      label:
+        en_US: Completion mode
+      type: select
+      required: false
+      default: chat
+      placeholder:
+        zh_Hans: 选择对话类型
+        en_US: Select completion mode
+      options:
+        - value: completion
+          label:
+            en_US: Completion
+            zh_Hans: 补全
+        - value: chat
+          label:
+            en_US: Chat
+            zh_Hans: 对话
+    - variable: context_size
+      label:
+        zh_Hans: 模型上下文长度
+        en_US: Model context size
+      required: true
+      show_on:
+        - variable: __model_type
+          value: llm
+      type: text-input
+      default: "4096"
+      placeholder:
+        zh_Hans: 在此输入您的模型上下文长度
+        en_US: Enter your Model context size
    - variable: jwt_token
      required: true
      label:
--- a/api/core/model_runtime/model_providers/azure_ai_studio/llm/llm.py
+++ b/api/core/model_runtime/model_providers/azure_ai_studio/llm/llm.py
@@ -1,9 +1,9 @@
 import logging
-from collections.abc import Generator
+from collections.abc import Generator, Sequence
 from typing import Any, Optional, Union

 from azure.ai.inference import ChatCompletionsClient
-from azure.ai.inference.models import StreamingChatCompletionsUpdate
+from azure.ai.inference.models import StreamingChatCompletionsUpdate, SystemMessage, UserMessage
 from azure.core.credentials import AzureKeyCredential
 from azure.core.exceptions import (
    ClientAuthenticationError,
@@ -20,7 +20,7 @@ from azure.core.exceptions import (
 )

 from core.model_runtime.callbacks.base_callback import Callback
-from core.model_runtime.entities.llm_entities import LLMResult, LLMResultChunk, LLMResultChunkDelta, LLMUsage
+from core.model_runtime.entities.llm_entities import LLMMode, LLMResult, LLMResultChunk, LLMResultChunkDelta, LLMUsage
 from core.model_runtime.entities.message_entities import (
    AssistantPromptMessage,
    PromptMessage,
@@ -30,6 +30,7 @@ from core.model_runtime.entities.model_entities import (
    AIModelEntity,
    FetchFrom,
    I18nObject,
+    ModelPropertyKey,
    ModelType,
    ParameterRule,
    ParameterType,
@@ -60,10 +61,10 @@ class AzureAIStudioLargeLanguageModel(LargeLanguageModel):
        self,
        model: str,
        credentials: dict,
-        prompt_messages: list[PromptMessage],
+        prompt_messages: Sequence[PromptMessage],
        model_parameters: dict,
-        tools: Optional[list[PromptMessageTool]] = None,
-        stop: Optional[list[str]] = None,
+        tools: Optional[Sequence[PromptMessageTool]] = None,
+        stop: Optional[Sequence[str]] = None,
        stream: bool = True,
        user: Optional[str] = None,
    ) -> Union[LLMResult, Generator]:
@@ -82,8 +83,8 @@ class AzureAIStudioLargeLanguageModel(LargeLanguageModel):
        """

        if not self.client:
-            endpoint = credentials.get("endpoint")
-            api_key = credentials.get("api_key")
+            endpoint = str(credentials.get("endpoint"))
+            api_key = str(credentials.get("api_key"))
            self.client = ChatCompletionsClient(endpoint=endpoint, credential=AzureKeyCredential(api_key))

        messages = [{"role": msg.role.value, "content": msg.content} for msg in prompt_messages]
@@ -94,6 +95,7 @@ class AzureAIStudioLargeLanguageModel(LargeLanguageModel):
            "temperature": model_parameters.get("temperature", 0),
            "top_p": model_parameters.get("top_p", 1),
            "stream": stream,
+            "model": model,
        }

        if stop:
@@ -255,10 +257,16 @@ class AzureAIStudioLargeLanguageModel(LargeLanguageModel):
        :return:
        """
        try:
-            endpoint = credentials.get("endpoint")
-            api_key = credentials.get("api_key")
+            endpoint = str(credentials.get("endpoint"))
+            api_key = str(credentials.get("api_key"))
            client = ChatCompletionsClient(endpoint=endpoint, credential=AzureKeyCredential(api_key))
-            client.get_model_info()
+            client.complete(
+                messages=[
+                    SystemMessage(content="I say 'ping', you say 'pong'"),
+                    UserMessage(content="ping"),
+                ],
+                model=model,
+            )
        except Exception as ex:
            raise CredentialsValidateFailedError(str(ex))

@@ -327,7 +335,10 @@ class AzureAIStudioLargeLanguageModel(LargeLanguageModel):
            fetch_from=FetchFrom.CUSTOMIZABLE_MODEL,
            model_type=ModelType.LLM,
            features=[],
-            model_properties={},
+            model_properties={
+                ModelPropertyKey.CONTEXT_SIZE: int(credentials.get("context_size", "4096")),
+                ModelPropertyKey.MODE: credentials.get("mode", LLMMode.CHAT),
+            },
            parameter_rules=rules,
        )

--- a/api/core/model_runtime/model_providers/azure_openai/azure_openai.yaml
+++ b/api/core/model_runtime/model_providers/azure_openai/azure_openai.yaml
@@ -53,6 +53,9 @@ model_credential_schema:
      type: select
      required: true
      options:
+        - label:
+            en_US: 2024-12-01-preview
+          value: 2024-12-01-preview
        - label:
            en_US: 2024-10-01-preview
          value: 2024-10-01-preview
@@ -135,6 +138,18 @@ model_credential_schema:
          show_on:
            - variable: __model_type
              value: llm
+        - label:
+            en_US: o3-mini
+          value: o3-mini
+          show_on:
+            - variable: __model_type
+              value: llm
+        - label:
+            en_US: o3-mini-2025-01-31
+          value: o3-mini-2025-01-31
+          show_on:
+            - variable: __model_type
+              value: llm
        - label:
            en_US: o1-preview
          value: o1-preview
--- a/api/core/model_runtime/model_providers/bedrock/bedrock.yaml
+++ b/api/core/model_runtime/model_providers/bedrock/bedrock.yaml
@@ -44,6 +44,7 @@ provider_credential_schema:
      label:
        en_US: AWS Region
        zh_Hans: AWS 地区
+        ja_JP: AWS リージョン
      type: select
      default: us-east-1
      options:
@@ -51,62 +52,86 @@ provider_credential_schema:
          label:
            en_US: US East (N. Virginia)
            zh_Hans: 美国东部 (弗吉尼亚北部)
+            ja_JP: 米国 (バージニア北部)
        - value: us-east-2
          label:
            en_US: US East (Ohio)
-            zh_Hans: 美国东部 (弗吉尼亚北部)
+            zh_Hans: 美国东部 (俄亥俄)
+            ja_JP: 米国 (オハイオ)
        - value: us-west-2
          label:
            en_US: US West (Oregon)
            zh_Hans: 美国西部 (俄勒冈州)
+            ja_JP: 米国 (オレゴン)
        - value: ap-south-1
          label:
            en_US: Asia Pacific (Mumbai)
            zh_Hans: 亚太地区（孟买）
+            ja_JP: アジアパシフィック (ムンバイ)
        - value: ap-southeast-1
          label:
            en_US: Asia Pacific (Singapore)
            zh_Hans: 亚太地区 (新加坡)
+            ja_JP: アジアパシフィック (シンガポール)
        - value: ap-southeast-2
          label:
            en_US: Asia Pacific (Sydney)
            zh_Hans: 亚太地区 (悉尼)
+            ja_JP: アジアパシフィック (シドニー)
        - value: ap-northeast-1
          label:
            en_US: Asia Pacific (Tokyo)
            zh_Hans: 亚太地区 (东京)
+            ja_JP: アジアパシフィック (東京)
        - value: ap-northeast-2
          label:
            en_US: Asia Pacific (Seoul)
            zh_Hans: 亚太地区（首尔）
+            ja_JP: アジアパシフィック (ソウル)
        - value: ca-central-1
          label:
            en_US: Canada (Central)
            zh_Hans: 加拿大（中部）
+            ja_JP: カナダ (中部)
        - value: eu-central-1
          label:
            en_US: Europe (Frankfurt)
            zh_Hans: 欧洲 (法兰克福)
+            ja_JP: 欧州 (フランクフルト)
        - value: eu-west-1
          label:
            en_US: Europe (Ireland)
            zh_Hans: 欧洲（爱尔兰）
+            ja_JP: 欧州 (アイルランド)
        - value: eu-west-2
          label:
            en_US: Europe (London)
            zh_Hans: 欧洲西部 (伦敦)
+            ja_JP: 欧州 (ロンドン)
        - value: eu-west-3
          label:
            en_US: Europe (Paris)
            zh_Hans: 欧洲（巴黎）
+            ja_JP: 欧州 (パリ)
        - value: sa-east-1
          label:
            en_US: South America (São Paulo)
            zh_Hans: 南美洲（圣保罗）
+            ja_JP: 南米 (サンパウロ)
        - value: us-gov-west-1
          label:
            en_US: AWS GovCloud (US-West)
            zh_Hans: AWS GovCloud (US-West)
+            ja_JP: AWS GovCloud (米国西部)
+    - variable: bedrock_endpoint_url
+      label:
+        zh_Hans: Bedrock Endpoint URL
+        en_US: Bedrock Endpoint URL
+      type: text-input
+      required: false
+      placeholder:
+        zh_Hans: 在此输入您的 Bedrock Endpoint URL, 如：https://123456.cloudfront.net
+        en_US: Enter your Bedrock Endpoint URL, e.g. https://123456.cloudfront.net
    - variable: model_for_validation
      required: false
      label:
--- a/api/core/model_runtime/model_providers/bedrock/get_bedrock_client.py
+++ b/api/core/model_runtime/model_providers/bedrock/get_bedrock_client.py
@@ -13,6 +13,7 @@ def get_bedrock_client(service_name: str, credentials: Mapping[str, str]):
    client_config = Config(region_name=region_name)
    aws_access_key_id = credentials.get("aws_access_key_id")
    aws_secret_access_key = credentials.get("aws_secret_access_key")
+    bedrock_endpoint_url = credentials.get("bedrock_endpoint_url")

    if aws_access_key_id and aws_secret_access_key:
        # use aksk to call bedrock
@@ -21,6 +22,7 @@ def get_bedrock_client(service_name: str, credentials: Mapping[str, str]):
            config=client_config,
            aws_access_key_id=aws_access_key_id,
            aws_secret_access_key=aws_secret_access_key,
+            **({"endpoint_url": bedrock_endpoint_url} if bedrock_endpoint_url else {}),
        )
    else:
        # use iam without aksk to call
--- a/api/core/model_runtime/model_providers/cohere/llm/llm.py
+++ b/api/core/model_runtime/model_providers/cohere/llm/llm.py
@@ -677,16 +677,17 @@ class CohereLargeLanguageModel(LargeLanguageModel):

        :return: model schema
        """
-        # get model schema
-        models = self.predefined_models()
-        model_map = {model.model: model for model in models}
-
        mode = credentials.get("mode")
+        base_model_schema = None
+        for predefined_model in self.predefined_models():
+            if (
+                mode == "chat" and predefined_model.model == "command-light-chat"
+            ) or predefined_model.model == "command-light":
+                base_model_schema = predefined_model
+                break

-        if mode == "chat":
-            base_model_schema = model_map["command-light-chat"]
-        else:
-            base_model_schema = model_map["command-light"]
+        if not base_model_schema:
+            raise ValueError("Model not found")

        base_model_schema = cast(AIModelEntity, base_model_schema)

--- a/api/core/model_runtime/model_providers/google/llm/_position.yaml
+++ b/api/core/model_runtime/model_providers/google/llm/_position.yaml
@@ -1,4 +1,7 @@
+- gemini-2.0-flash-001
 - gemini-2.0-flash-exp
+- gemini-2.0-flash-lite-preview-02-05
+- gemini-2.0-pro-exp-02-05
 - gemini-2.0-flash-thinking-exp-1219
 - gemini-2.0-flash-thinking-exp-01-21
 - gemini-1.5-pro
--- a/api/core/model_runtime/model_providers/google/llm/gemini-2.0-flash-001.yaml
+++ b/api/core/model_runtime/model_providers/google/llm/gemini-2.0-flash-001.yaml
@@ -0,0 +1,41 @@
+model: gemini-2.0-flash-001
+label:
+  en_US: Gemini 2.0 Flash 001
+model_type: llm
+features:
+  - agent-thought
+  - vision
+  - tool-call
+  - stream-tool-call
+  - document
+  - video
+  - audio
+model_properties:
+  mode: chat
+  context_size: 1048576
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: top_p
+    use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
+  - name: max_output_tokens
+    use_template: max_tokens
+    default: 8192
+    min: 1
+    max: 8192
+  - name: json_schema
+    use_template: json_schema
+pricing:
+  input: '0.00'
+  output: '0.00'
+  unit: '0.000001'
+  currency: USD
--- a/api/core/model_runtime/model_providers/google/llm/gemini-2.0-flash-lite-preview-02-05.yaml
+++ b/api/core/model_runtime/model_providers/google/llm/gemini-2.0-flash-lite-preview-02-05.yaml
@@ -0,0 +1,41 @@
+model: gemini-2.0-flash-lite-preview-02-05
+label:
+  en_US: Gemini 2.0 Flash Lite Preview 0205
+model_type: llm
+features:
+  - agent-thought
+  - vision
+  - tool-call
+  - stream-tool-call
+  - document
+  - video
+  - audio
+model_properties:
+  mode: chat
+  context_size: 1048576
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: top_p
+    use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
+  - name: max_output_tokens
+    use_template: max_tokens
+    default: 8192
+    min: 1
+    max: 8192
+  - name: json_schema
+    use_template: json_schema
+pricing:
+  input: '0.00'
+  output: '0.00'
+  unit: '0.000001'
+  currency: USD
--- a/api/core/model_runtime/model_providers/google/llm/gemini-2.0-pro-exp-02-05.yaml
+++ b/api/core/model_runtime/model_providers/google/llm/gemini-2.0-pro-exp-02-05.yaml
@@ -0,0 +1,41 @@
+model: gemini-2.0-pro-exp-02-05
+label:
+  en_US: Gemini 2.0 pro exp 02-05
+model_type: llm
+features:
+  - agent-thought
+  - vision
+  - tool-call
+  - stream-tool-call
+  - document
+  - video
+  - audio
+model_properties:
+  mode: chat
+  context_size: 1048576
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: top_p
+    use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
+  - name: max_output_tokens
+    use_template: max_tokens
+    default: 8192
+    min: 1
+    max: 8192
+  - name: json_schema
+    use_template: json_schema
+pricing:
+  input: '0.00'
+  output: '0.00'
+  unit: '0.000001'
+  currency: USD
--- a/api/core/model_runtime/model_providers/groq/llm/_position.yaml
+++ b/api/core/model_runtime/model_providers/groq/llm/_position.yaml
@@ -1,3 +1,4 @@
+- deepseek-r1-distill-llama-70b
 - llama-3.1-405b-reasoning
 - llama-3.3-70b-versatile
 - llama-3.1-70b-versatile
--- a/api/core/model_runtime/model_providers/groq/llm/deepseek-r1-distill-llama-70b.yaml
+++ b/api/core/model_runtime/model_providers/groq/llm/deepseek-r1-distill-llama-70b.yaml
@@ -0,0 +1,36 @@
+model: deepseek-r1-distill-llama-70b
+label:
+  en_US: DeepSeek R1 Distill Llama 70b
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 128000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: top_p
+    use_template: top_p
+  - name: max_tokens
+    use_template: max_tokens
+    default: 512
+    min: 1
+    max: 8192
+  - name: response_format
+    label:
+      zh_Hans: 回复格式
+      en_US: Response Format
+    type: string
+    help:
+      zh_Hans: 指定模型必须输出的格式
+      en_US: specifying the format that the model must output
+    required: false
+    options:
+      - text
+      - json_object
+pricing:
+  input: '3.00'
+  output: '3.00'
+  unit: '0.000001'
+  currency: USD
--- a/api/core/model_runtime/model_providers/novita/_assets/icon_l_en.svg
+++ b/api/core/model_runtime/model_providers/novita/_assets/icon_l_en.svg
@@ -1,19 +1,11 @@
-<svg width="162" height="36" viewBox="0 0 162 36" fill="none" xmlns="http://www.w3.org/2000/svg">
-<path fill-rule="evenodd" clip-rule="evenodd" d="M2 0C0.895431 0 0 0.895432 0 2V29.1891C0 30.2937 0.895433 31.1891 2 31.1891H5.51171L16.0608 35.1377C16.7145 35.3824 17.4114 34.8991 17.4114 34.2012V11.3669C17.4114 10.533 16.894 9.78665 16.1131 9.49405L5.51171 5.52152H25.58V31.1891H29.0917C30.1963 31.1891 31.0917 30.2937 31.0917 29.1891V2C31.0917 0.895431 30.1963 0 29.0917 0H2ZM14.6022 23.7351C15.0558 23.956 15.4239 23.6812 15.4239 23.1185C15.4239 22.5557 15.0558 21.9204 14.6022 21.6995C14.1486 21.4775 13.7804 21.7545 13.7804 22.3161C13.7804 22.8777 14.1486 23.513 14.6022 23.7351Z" fill="white"/>
-<path fill-rule="evenodd" clip-rule="evenodd" d="M2 0C0.895431 0 0 0.895432 0 2V29.1891C0 30.2937 0.895433 31.1891 2 31.1891H5.51171L16.0608 35.1377C16.7145 35.3824 17.4114 34.8991 17.4114 34.2012V11.3669C17.4114 10.533 16.894 9.78665 16.1131 9.49405L5.51171 5.52152H25.58V31.1891H29.0917C30.1963 31.1891 31.0917 30.2937 31.0917 29.1891V2C31.0917 0.895431 30.1963 0 29.0917 0H2ZM14.6022 23.7351C15.0558 23.956 15.4239 23.6812 15.4239 23.1185C15.4239 22.5557 15.0558 21.9204 14.6022 21.6995C14.1486 21.4775 13.7804 21.7545 13.7804 22.3161C13.7804 22.8777 14.1486 23.513 14.6022 23.7351Z" fill="url(#paint0_linear_1473_71)"/>
-<path d="M55.9397 27.8804H59.0566V19.0803C59.0566 14.9105 56.381 12.7172 52.8228 12.7172C51.0023 12.7172 49.3197 13.4483 48.2991 14.6668V12.9609H45.1546V27.8804H48.2991V19.5406C48.2991 16.8059 49.8162 15.3978 52.1332 15.3978C54.4226 15.3978 55.9397 16.8059 55.9397 19.5406V27.8804Z" fill="#11101A"/>
-<path fill-rule="evenodd" clip-rule="evenodd" d="M69.7881 12.7172C74.1187 12.7172 77.539 15.7228 77.539 20.4071C77.539 25.0915 74.0083 28.1241 69.6502 28.1241C65.3196 28.1241 62.0372 25.0915 62.0372 20.4071C62.0372 15.7228 65.4575 12.7172 69.7881 12.7172ZM69.7342 15.3979C67.362 15.3979 65.2381 17.0225 65.2381 20.4071C65.2381 23.7918 67.2793 25.4435 69.6514 25.4435C71.996 25.4435 74.313 23.7918 74.313 20.4071C74.313 17.0225 72.0788 15.3979 69.7342 15.3979Z" fill="#11101A"/>
-<path d="M78.861 12.9609L84.6259 27.8804H88.3772L94.1697 12.9609H90.8321L86.5291 25.1185L82.2261 12.9609H78.861Z" fill="#11101A"/>
-<path fill-rule="evenodd" clip-rule="evenodd" d="M100.13 9.00761C100.13 10.1178 99.2477 10.9842 98.1443 10.9842C97.0134 10.9842 96.1308 10.1178 96.1308 9.00761C96.1308 7.89745 97.0134 7.03098 98.1443 7.03098C99.2477 7.03098 100.13 7.89745 100.13 9.00761ZM99.6882 27.8804H96.5437V12.9609H99.6882V27.8804Z" fill="#11101A"/>
-<path d="M104.322 23.7376C104.322 26.7702 106.004 27.8804 108.708 27.8804H111.19V25.308H109.259C107.935 25.308 107.494 24.8477 107.494 23.7376V15.479H111.19V12.9609H107.494V9.25128H104.322V12.9609H102.529V15.479H104.322V23.7376Z" fill="#11101A"/>
-<path fill-rule="evenodd" clip-rule="evenodd" d="M120.154 28.1241C116.209 28.1241 113.037 24.9561 113.037 20.353C113.037 15.7498 116.209 12.7172 120.209 12.7172C122.774 12.7172 124.539 13.9086 125.477 15.1271V12.9609H128.649V27.8804H125.477V25.6601C124.512 26.9327 122.691 28.1241 120.154 28.1241ZM120.87 25.4435C123.242 25.4435 125.476 23.6293 125.476 20.4071C125.476 17.212 123.242 15.3979 120.87 15.3979C118.526 15.3979 116.264 17.1308 116.264 20.353C116.264 23.5752 118.526 25.4435 120.87 25.4435Z" fill="#11101A"/>
-<path d="M136.043 26.0933C136.043 24.9832 135.16 24.1167 134.057 24.1167C132.926 24.1167 132.043 24.9832 132.043 26.0933C132.043 27.2035 132.926 28.07 134.057 28.07C135.16 28.07 136.043 27.2035 136.043 26.0933Z" fill="#11101A"/>
-<path fill-rule="evenodd" clip-rule="evenodd" d="M145.502 28.1241C141.558 28.1241 138.386 24.9561 138.386 20.353C138.386 15.7498 141.558 12.7172 145.557 12.7172C148.123 12.7172 149.888 13.9086 150.826 15.1271V12.9609H153.998V27.8804H150.826V25.6601C149.86 26.9327 148.04 28.1241 145.502 28.1241ZM146.219 25.4435C148.591 25.4435 150.825 23.6293 150.825 20.4071C150.825 17.212 148.591 15.3979 146.219 15.3979C143.874 15.3979 141.612 17.1308 141.612 20.353C141.612 23.5752 143.874 25.4435 146.219 25.4435Z" fill="#11101A"/>
-<path fill-rule="evenodd" clip-rule="evenodd" d="M161.722 9.00761C161.722 10.1178 160.84 10.9842 159.736 10.9842C158.605 10.9842 157.723 10.1178 157.723 9.00761C157.723 7.89745 158.605 7.03098 159.736 7.03098C160.84 7.03098 161.722 7.89745 161.722 9.00761ZM161.28 27.8804H158.136V12.9609H161.28V27.8804Z" fill="#11101A"/>
+<svg width="88" height="24" viewBox="0 0 88 24" fill="none" xmlns="http://www.w3.org/2000/svg">
+<g clip-path="url(#clip0_1923_1287)">
+<path d="M24 18.8323V18.8326H14.3246L9.16716 13.6751V18.8326H0V18.8314L9.16716 9.66422V4H9.16774L24 18.8323Z" fill="black"/>
+</g>
+<path fill-rule="evenodd" clip-rule="evenodd" d="M73.2505 16.8061H76.5869V18.9145H73.9391C72.0857 18.9145 70.9202 17.8952 70.9202 15.9977V10.3921H69.0316V8.26609H70.9202L71.4677 5.47209H73.2329V8.26609H76.5869V10.3921H73.2505V16.8061ZM33.8133 4.85699L38.6679 15.681H38.809V4.85699H41.3333V18.9145H37.52L32.6654 8.09046H32.5243V18.9145H30V4.85699H33.8133ZM47.812 19.1254C44.7225 19.1254 42.7457 16.9641 42.7457 13.6079C42.7457 10.2517 44.6873 8.05518 47.812 8.05518C50.9367 8.05518 52.8429 10.1635 52.8429 13.6079C52.8429 17.0523 50.9014 19.1254 47.812 19.1254ZM47.812 17.017C49.1891 17.017 50.3363 16.5423 50.3715 15.1894V12.0265C50.3715 10.6383 49.2068 10.1635 47.812 10.1635C46.4172 10.1635 45.2171 10.6383 45.2171 12.0265V15.1894C45.2524 16.5599 46.4348 17.017 47.812 17.017ZM55.5444 8.24846L58.2979 16.6826H58.439L61.1926 8.24846H63.7346L59.9389 18.8968H56.7966L53.0186 8.24846H55.5429H55.5444ZM65.0419 8.26609H67.3722V18.9145H65.0419V8.26609ZM64.9001 4.85699H67.5126V6.86027H64.9001V4.85699ZM82.3064 19.143C79.4639 19.143 77.6458 16.9817 77.6458 13.6079C77.6458 10.2341 79.4286 8.07282 82.3064 8.07282C83.6483 8.07282 84.7425 8.59973 85.3958 9.58373H85.5369L85.9962 8.26609H87.7614V18.9145H85.9962L85.5369 17.6314H85.3958C84.6896 18.5625 83.5072 19.1423 82.3064 19.1423V19.143ZM82.7826 17.017C84.1774 17.017 85.3951 16.5776 85.4304 15.1894V12.0265C85.4304 10.603 84.159 10.1988 82.7297 10.1988C81.3004 10.1988 80.1172 10.6383 80.1172 12.0265V15.1894C80.1525 16.5952 81.3709 17.017 82.7826 17.017Z" fill="black"/>
 <defs>
-<linearGradient id="paint0_linear_1473_71" x1="31" y1="-2" x2="0.975591" y2="14.2625" gradientUnits="userSpaceOnUse">
-<stop stop-color="#2622FF"/>
-<stop offset="1" stop-color="#A717FF"/>
-</linearGradient>
+<clipPath id="clip0_1923_1287">
+<rect width="24" height="14.8326" fill="white" transform="translate(0 4)"/>
+</clipPath>
 </defs>
 </svg>
--- a/api/core/model_runtime/model_providers/novita/_assets/icon_s_en.svg
+++ b/api/core/model_runtime/model_providers/novita/_assets/icon_s_en.svg
@@ -1,10 +1,3 @@
-<svg width="32" height="36" viewBox="0 0 32 36" fill="none" xmlns="http://www.w3.org/2000/svg">
-<path fill-rule="evenodd" clip-rule="evenodd" d="M2 0C0.895431 0 0 0.895432 0 2V29.1891C0 30.2937 0.895433 31.1891 2 31.1891H5.51171L16.0608 35.1377C16.7145 35.3824 17.4114 34.8991 17.4114 34.2012V11.3669C17.4114 10.533 16.894 9.78665 16.1131 9.49405L5.51171 5.52152H25.58V31.1891H29.0917C30.1963 31.1891 31.0917 30.2937 31.0917 29.1891V2C31.0917 0.895431 30.1963 0 29.0917 0H2ZM14.6022 23.7351C15.0558 23.956 15.4239 23.6812 15.4239 23.1185C15.4239 22.5557 15.0558 21.9204 14.6022 21.6995C14.1486 21.4775 13.7804 21.7545 13.7804 22.3161C13.7804 22.8777 14.1486 23.513 14.6022 23.7351Z" fill="white"/>
-<path fill-rule="evenodd" clip-rule="evenodd" d="M2 0C0.895431 0 0 0.895432 0 2V29.1891C0 30.2937 0.895433 31.1891 2 31.1891H5.51171L16.0608 35.1377C16.7145 35.3824 17.4114 34.8991 17.4114 34.2012V11.3669C17.4114 10.533 16.894 9.78665 16.1131 9.49405L5.51171 5.52152H25.58V31.1891H29.0917C30.1963 31.1891 31.0917 30.2937 31.0917 29.1891V2C31.0917 0.895431 30.1963 0 29.0917 0H2ZM14.6022 23.7351C15.0558 23.956 15.4239 23.6812 15.4239 23.1185C15.4239 22.5557 15.0558 21.9204 14.6022 21.6995C14.1486 21.4775 13.7804 21.7545 13.7804 22.3161C13.7804 22.8777 14.1486 23.513 14.6022 23.7351Z" fill="url(#paint0_linear_1473_97)"/>
-<defs>
-<linearGradient id="paint0_linear_1473_97" x1="31" y1="-2" x2="0.975591" y2="14.2625" gradientUnits="userSpaceOnUse">
-<stop stop-color="#2622FF"/>
-<stop offset="1" stop-color="#A717FF"/>
-</linearGradient>
-</defs>
+<svg width="24" height="15" viewBox="0 0 24 15" fill="none" xmlns="http://www.w3.org/2000/svg">
+<path d="M24 14.8323V14.8326H14.3246L9.16716 9.67507V14.8326H0V14.8314L9.16716 5.66422V0H9.16774L24 14.8323Z" fill="black"/>
 </svg>
--- a/api/core/model_runtime/model_providers/novita/llm/L3-8B-Stheno-v3.2.yaml
+++ b/api/core/model_runtime/model_providers/novita/llm/L3-8B-Stheno-v3.2.yaml
@@ -0,0 +1,41 @@
+model: Sao10K/L3-8B-Stheno-v3.2
+label:
+  zh_Hans: L3 8B Stheno V3.2
+  en_US: L3 8B Stheno V3.2
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 8192
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    min: 0
+    max: 2
+    default: 1
+  - name: top_p
+    use_template: top_p
+    min: 0
+    max: 1
+    default: 1
+  - name: max_tokens
+    use_template: max_tokens
+    min: 1
+    max: 2048
+    default: 512
+  - name: frequency_penalty
+    use_template: frequency_penalty
+    min: -2
+    max: 2
+    default: 0
+  - name: presence_penalty
+    use_template: presence_penalty
+    min: -2
+    max: 2
+    default: 0
+pricing:
+  input: '0.0005'
+  output: '0.0005'
+  unit: '0.0001'
+  currency: USD
--- a/api/core/model_runtime/model_providers/novita/llm/_position.yaml
+++ b/api/core/model_runtime/model_providers/novita/llm/_position.yaml
@@ -0,0 +1,41 @@
+# Deepseek Models
+- deepseek/deepseek-r1
+- deepseek/deepseek_v3
+
+# LLaMA Models
+- meta-llama/llama-3.3-70b-instruct
+- meta-llama/llama-3.2-11b-vision-instruct
+- meta-llama/llama-3.2-3b-instruct
+- meta-llama/llama-3.2-1b-instruct
+- meta-llama/llama-3.1-70b-instruct
+- meta-llama/llama-3.1-8b-instruct
+- meta-llama/llama-3.1-8b-instruct-max
+- meta-llama/llama-3.1-8b-instruct-bf16
+- meta-llama/llama-3-70b-instruct
+- meta-llama/llama-3-8b-instruct
+
+# Mistral Models
+- mistralai/mistral-nemo
+- mistralai/mistral-7b-instruct
+
+# Qwen Models
+- qwen/qwen-2.5-72b-instruct
+- qwen/qwen-2-72b-instruct
+- qwen/qwen-2-vl-72b-instruct
+- qwen/qwen-2-7b-instruct
+
+# Other Models
+- sao10k/L3-8B-Stheno-v3.2
+- sao10k/l3-70b-euryale-v2.1
+- sao10k/l31-70b-euryale-v2.2
+- sao10k/l3-8b-lunaris
+- jondurbin/airoboros-l2-70b
+- cognitivecomputations/dolphin-mixtral-8x22b
+- google/gemma-2-9b-it
+- nousresearch/hermes-2-pro-llama-3-8b
+- sophosympatheia/midnight-rose-70b
+- gryphe/mythomax-l2-13b
+- nousresearch/nous-hermes-llama2-13b
+- openchat/openchat-7b
+- teknium/openhermes-2.5-mistral-7b
+- microsoft/wizardlm-2-8x22b
--- a/api/core/model_runtime/model_providers/novita/llm/airoboros-l2-70b.yaml
+++ b/api/core/model_runtime/model_providers/novita/llm/airoboros-l2-70b.yaml
@@ -1,7 +1,7 @@
 model: jondurbin/airoboros-l2-70b
 label:
-  zh_Hans: jondurbin/airoboros-l2-70b
-  en_US: jondurbin/airoboros-l2-70b
+  zh_Hans: Airoboros L2 70B
+  en_US: Airoboros L2 70B
 model_type: llm
 features:
  - agent-thought
--- a/api/core/model_runtime/model_providers/novita/llm/deepseek-r1.yaml
+++ b/api/core/model_runtime/model_providers/novita/llm/deepseek-r1.yaml
@@ -0,0 +1,41 @@
+model: deepseek/deepseek-r1
+label:
+  zh_Hans: DeepSeek R1
+  en_US: DeepSeek R1
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 64000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    min: 0
+    max: 2
+    default: 1
+  - name: top_p
+    use_template: top_p
+    min: 0
+    max: 1
+    default: 1
+  - name: max_tokens
+    use_template: max_tokens
+    min: 1
+    max: 2048
+    default: 512
+  - name: frequency_penalty
+    use_template: frequency_penalty
+    min: -2
+    max: 2
+    default: 0
+  - name: presence_penalty
+    use_template: presence_penalty
+    min: -2
+    max: 2
+    default: 0
+pricing:
+  input: '0.04'
+  output: '0.04'
+  unit: '0.0001'
+  currency: USD
--- a/api/core/model_runtime/model_providers/novita/llm/deepseek_v3.yaml
+++ b/api/core/model_runtime/model_providers/novita/llm/deepseek_v3.yaml
@@ -0,0 +1,41 @@
+model: deepseek/deepseek_v3
+label:
+  zh_Hans: DeepSeek V3
+  en_US: DeepSeek V3
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 64000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    min: 0
+    max: 2
+    default: 1
+  - name: top_p
+    use_template: top_p
+    min: 0
+    max: 1
+    default: 1
+  - name: max_tokens
+    use_template: max_tokens
+    min: 1
+    max: 2048
+    default: 512
+  - name: frequency_penalty
+    use_template: frequency_penalty
+    min: -2
+    max: 2
+    default: 0
+  - name: presence_penalty
+    use_template: presence_penalty
+    min: -2
+    max: 2
+    default: 0
+pricing:
+  input: '0.0089'
+  output: '0.0089'
+  unit: '0.0001'
+  currency: USD
--- a/api/core/model_runtime/model_providers/novita/llm/dolphin-mixtral-8x22b.yaml
+++ b/api/core/model_runtime/model_providers/novita/llm/dolphin-mixtral-8x22b.yaml
@@ -1,7 +1,7 @@
 model: cognitivecomputations/dolphin-mixtral-8x22b
 label:
-  zh_Hans: cognitivecomputations/dolphin-mixtral-8x22b
-  en_US: cognitivecomputations/dolphin-mixtral-8x22b
+  zh_Hans: Dolphin Mixtral 8x22B
+  en_US: Dolphin Mixtral 8x22B
 model_type: llm
 features:
  - agent-thought
--- a/api/core/model_runtime/model_providers/novita/llm/gemma-2-9b-it.yaml
+++ b/api/core/model_runtime/model_providers/novita/llm/gemma-2-9b-it.yaml
@@ -1,7 +1,7 @@
 model: google/gemma-2-9b-it
 label:
-  zh_Hans: google/gemma-2-9b-it
-  en_US: google/gemma-2-9b-it
+  zh_Hans: Gemma 2 9B
+  en_US: Gemma 2 9B
 model_type: llm
 features:
  - agent-thought
--- a/api/core/model_runtime/model_providers/novita/llm/hermes-2-pro-llama-3-8b.yaml
+++ b/api/core/model_runtime/model_providers/novita/llm/hermes-2-pro-llama-3-8b.yaml
@@ -1,7 +1,7 @@
 model: nousresearch/hermes-2-pro-llama-3-8b
 label:
-  zh_Hans: nousresearch/hermes-2-pro-llama-3-8b
-  en_US: nousresearch/hermes-2-pro-llama-3-8b
+  zh_Hans: Hermes 2 Pro Llama 3 8B
+  en_US: Hermes 2 Pro Llama 3 8B
 model_type: llm
 features:
  - agent-thought
--- a/api/core/model_runtime/model_providers/novita/llm/l3-70b-euryale-v2.1.yaml
+++ b/api/core/model_runtime/model_providers/novita/llm/l3-70b-euryale-v2.1.yaml
@@ -1,7 +1,7 @@
 model: sao10k/l3-70b-euryale-v2.1
 label:
-  zh_Hans: sao10k/l3-70b-euryale-v2.1
-  en_US: sao10k/l3-70b-euryale-v2.1
+  zh_Hans: "L3 70B Euryale V2.1\t"
+  en_US: "L3 70B Euryale V2.1\t"
 model_type: llm
 features:
  - agent-thought
--- a/api/core/model_runtime/model_providers/novita/llm/l3-8b-lunaris.yaml
+++ b/api/core/model_runtime/model_providers/novita/llm/l3-8b-lunaris.yaml
@@ -0,0 +1,41 @@
+model: sao10k/l3-8b-lunaris
+label:
+  zh_Hans: "Sao10k L3 8B Lunaris"
+  en_US: "Sao10k L3 8B Lunaris"
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 8192
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    min: 0
+    max: 2
+    default: 1
+  - name: top_p
+    use_template: top_p
+    min: 0
+    max: 1
+    default: 1
+  - name: max_tokens
+    use_template: max_tokens
+    min: 1
+    max: 2048
+    default: 512
+  - name: frequency_penalty
+    use_template: frequency_penalty
+    min: -2
+    max: 2
+    default: 0
+  - name: presence_penalty
+    use_template: presence_penalty
+    min: -2
+    max: 2
+    default: 0
+pricing:
+  input: '0.0005'
+  output: '0.0005'
+  unit: '0.0001'
+  currency: USD
--- a/api/core/model_runtime/model_providers/novita/llm/l31-70b-euryale-v2.2.yaml
+++ b/api/core/model_runtime/model_providers/novita/llm/l31-70b-euryale-v2.2.yaml
@@ -0,0 +1,41 @@
+model: sao10k/l31-70b-euryale-v2.2
+label:
+  zh_Hans: L31 70B Euryale V2.2
+  en_US: L31 70B Euryale V2.2
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 16000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    min: 0
+    max: 2
+    default: 1
+  - name: top_p
+    use_template: top_p
+    min: 0
+    max: 1
+    default: 1
+  - name: max_tokens
+    use_template: max_tokens
+    min: 1
+    max: 2048
+    default: 512
+  - name: frequency_penalty
+    use_template: frequency_penalty
+    min: -2
+    max: 2
+    default: 0
+  - name: presence_penalty
+    use_template: presence_penalty
+    min: -2
+    max: 2
+    default: 0
+pricing:
+  input: '0.0148'
+  output: '0.0148'
+  unit: '0.0001'
+  currency: USD
--- a/api/core/model_runtime/model_providers/novita/llm/llama-3-70b-instruct.yaml
+++ b/api/core/model_runtime/model_providers/novita/llm/llama-3-70b-instruct.yaml
@@ -1,7 +1,7 @@
 model: meta-llama/llama-3-70b-instruct
 label:
-  zh_Hans: meta-llama/llama-3-70b-instruct
-  en_US: meta-llama/llama-3-70b-instruct
+  zh_Hans: Llama3 70b Instruct
+  en_US: Llama3 70b Instruct
 model_type: llm
 features:
  - agent-thought
--- a/api/core/model_runtime/model_providers/novita/llm/llama-3-8b-instruct.yaml
+++ b/api/core/model_runtime/model_providers/novita/llm/llama-3-8b-instruct.yaml
@@ -1,7 +1,7 @@
 model: meta-llama/llama-3-8b-instruct
 label:
-  zh_Hans: meta-llama/llama-3-8b-instruct
-  en_US: meta-llama/llama-3-8b-instruct
+  zh_Hans: Llama 3 8B Instruct
+  en_US: Llama 3 8B Instruct
 model_type: llm
 features:
  - agent-thought
@@ -35,7 +35,7 @@ parameter_rules:
    max: 2
    default: 0
 pricing:
-  input: '0.00063'
-  output: '0.00063'
+  input: '0.0004'
+  output: '0.0004'
  unit: '0.0001'
  currency: USD
--- a/api/core/model_runtime/model_providers/novita/llm/llama-3.1-70b-instruct.yaml
+++ b/api/core/model_runtime/model_providers/novita/llm/llama-3.1-70b-instruct.yaml
@@ -1,13 +1,13 @@
 model: meta-llama/llama-3.1-70b-instruct
 label:
-  zh_Hans: meta-llama/llama-3.1-70b-instruct
-  en_US: meta-llama/llama-3.1-70b-instruct
+  zh_Hans: Llama 3.1 70B Instruct
+  en_US: Llama 3.1 70B Instruct
 model_type: llm
 features:
  - agent-thought
 model_properties:
  mode: chat
-  context_size: 8192
+  context_size: 32768
 parameter_rules:
  - name: temperature
    use_template: temperature
@@ -35,7 +35,7 @@ parameter_rules:
    max: 2
    default: 0
 pricing:
-  input: '0.0055'
-  output: '0.0076'
+  input: '0.0034'
+  output: '0.0039'
  unit: '0.0001'
  currency: USD
--- a/api/core/model_runtime/model_providers/novita/llm/llama-3.1-8b-instruct-bf16.yaml
+++ b/api/core/model_runtime/model_providers/novita/llm/llama-3.1-8b-instruct-bf16.yaml
@@ -0,0 +1,41 @@
+model: meta-llama/llama-3.1-8b-instruct-bf16
+label:
+  zh_Hans: Llama 3.1 8B Instruct BF16
+  en_US: Llama 3.1 8B Instruct BF16
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 8192
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    min: 0
+    max: 2
+    default: 1
+  - name: top_p
+    use_template: top_p
+    min: 0
+    max: 1
+    default: 1
+  - name: max_tokens
+    use_template: max_tokens
+    min: 1
+    max: 2048
+    default: 512
+  - name: frequency_penalty
+    use_template: frequency_penalty
+    min: -2
+    max: 2
+    default: 0
+  - name: presence_penalty
+    use_template: presence_penalty
+    min: -2
+    max: 2
+    default: 0
+pricing:
+  input: '0.0006'
+  output: '0.0006'
+  unit: '0.0001'
+  currency: USD
--- a/api/core/model_runtime/model_providers/novita/llm/llama-3.1-8b-instruct-max.yaml
+++ b/api/core/model_runtime/model_providers/novita/llm/llama-3.1-8b-instruct-max.yaml
@@ -0,0 +1,41 @@
+model: meta-llama/llama-3.1-8b-instruct-max
+label:
+  zh_Hans: "Llama3.1 8B Instruct Max\t"
+  en_US: "Llama3.1 8B Instruct Max\t"
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 16384
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    min: 0
+    max: 2
+    default: 1
+  - name: top_p
+    use_template: top_p
+    min: 0
+    max: 1
+    default: 1
+  - name: max_tokens
+    use_template: max_tokens
+    min: 1
+    max: 2048
+    default: 512
+  - name: frequency_penalty
+    use_template: frequency_penalty
+    min: -2
+    max: 2
+    default: 0
+  - name: presence_penalty
+    use_template: presence_penalty
+    min: -2
+    max: 2
+    default: 0
+pricing:
+  input: '0.0005'
+  output: '0.0005'
+  unit: '0.0001'
+  currency: USD
--- a/api/core/model_runtime/model_providers/novita/llm/llama-3.1-8b-instruct.yaml
+++ b/api/core/model_runtime/model_providers/novita/llm/llama-3.1-8b-instruct.yaml
@@ -1,13 +1,13 @@
 model: meta-llama/llama-3.1-8b-instruct
 label:
-  zh_Hans: meta-llama/llama-3.1-8b-instruct
-  en_US: meta-llama/llama-3.1-8b-instruct
+  zh_Hans: Llama 3.1 8B Instruct
+  en_US: Llama 3.1 8B Instruct
 model_type: llm
 features:
  - agent-thought
 model_properties:
  mode: chat
-  context_size: 8192
+  context_size: 16384
 parameter_rules:
  - name: temperature
    use_template: temperature
@@ -35,7 +35,7 @@ parameter_rules:
    max: 2
    default: 0
 pricing:
-  input: '0.001'
-  output: '0.001'
+  input: '0.0005'
+  output: '0.0005'
  unit: '0.0001'
  currency: USD
--- a/api/core/model_runtime/model_providers/novita/llm/llama-3.2-11b-vision-instruct.yaml
+++ b/api/core/model_runtime/model_providers/novita/llm/llama-3.2-11b-vision-instruct.yaml
@@ -0,0 +1,41 @@
+model: meta-llama/llama-3.2-11b-vision-instruct
+label:
+  zh_Hans: "Llama 3.2 11B Vision Instruct\t"
+  en_US: "Llama 3.2 11B Vision Instruct\t"
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 32768
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    min: 0
+    max: 2
+    default: 1
+  - name: top_p
+    use_template: top_p
+    min: 0
+    max: 1
+    default: 1
+  - name: max_tokens
+    use_template: max_tokens
+    min: 1
+    max: 2048
+    default: 512
+  - name: frequency_penalty
+    use_template: frequency_penalty
+    min: -2
+    max: 2
+    default: 0
+  - name: presence_penalty
+    use_template: presence_penalty
+    min: -2
+    max: 2
+    default: 0
+pricing:
+  input: '0.0006'
+  output: '0.0006'
+  unit: '0.0001'
+  currency: USD
--- a/api/core/model_runtime/model_providers/novita/llm/llama-3.2-1b-instruct.yaml
+++ b/api/core/model_runtime/model_providers/novita/llm/llama-3.2-1b-instruct.yaml
@@ -0,0 +1,41 @@
+model: meta-llama/llama-3.2-1b-instruct
+label:
+  zh_Hans: "Llama 3.2 1B Instruct\t"
+  en_US: "Llama 3.2 1B Instruct\t"
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 131000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    min: 0
+    max: 2
+    default: 1
+  - name: top_p
+    use_template: top_p
+    min: 0
+    max: 1
+    default: 1
+  - name: max_tokens
+    use_template: max_tokens
+    min: 1
+    max: 2048
+    default: 512
+  - name: frequency_penalty
+    use_template: frequency_penalty
+    min: -2
+    max: 2
+    default: 0
+  - name: presence_penalty
+    use_template: presence_penalty
+    min: -2
+    max: 2
+    default: 0
+pricing:
+  input: '0.0002'
+  output: '0.0002'
+  unit: '0.0001'
+  currency: USD
--- a/api/core/model_runtime/model_providers/novita/llm/Nous-Hermes-2-Mixtral-8x7B-DPO.yaml
+++ b/api/core/model_runtime/model_providers/novita/llm/Nous-Hermes-2-Mixtral-8x7B-DPO.yaml
@@ -1,7 +1,7 @@
-model: Nous-Hermes-2-Mixtral-8x7B-DPO
+model: meta-llama/llama-3.2-3b-instruct
 label:
-  zh_Hans: Nous-Hermes-2-Mixtral-8x7B-DPO
-  en_US: Nous-Hermes-2-Mixtral-8x7B-DPO
+  zh_Hans: Llama 3.2 3B Instruct
+  en_US: Llama 3.2 3B Instruct
 model_type: llm
 features:
  - agent-thought
@@ -35,7 +35,7 @@ parameter_rules:
    max: 2
    default: 0
 pricing:
-  input: '0.0027'
-  output: '0.0027'
+  input: '0.0003'
+  output: '0.0005'
  unit: '0.0001'
  currency: USD
--- a/api/core/model_runtime/model_providers/novita/llm/llama-3.3-70b-instruct.yaml
+++ b/api/core/model_runtime/model_providers/novita/llm/llama-3.3-70b-instruct.yaml
@@ -0,0 +1,41 @@
+model: meta-llama/llama-3.3-70b-instruct
+label:
+  zh_Hans: Llama 3.3 70B Instruct
+  en_US: Llama 3.3 70B Instruct
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 131072
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    min: 0
+    max: 2
+    default: 1
+  - name: top_p
+    use_template: top_p
+    min: 0
+    max: 1
+    default: 1
+  - name: max_tokens
+    use_template: max_tokens
+    min: 1
+    max: 2048
+    default: 512
+  - name: frequency_penalty
+    use_template: frequency_penalty
+    min: -2
+    max: 2
+    default: 0
+  - name: presence_penalty
+    use_template: presence_penalty
+    min: -2
+    max: 2
+    default: 0
+pricing:
+  input: '0.0039'
+  output: '0.0039'
+  unit: '0.0001'
+  currency: USD
--- a/api/core/model_runtime/model_providers/novita/llm/midnight-rose-70b.yaml
+++ b/api/core/model_runtime/model_providers/novita/llm/midnight-rose-70b.yaml
@@ -1,7 +1,7 @@
 model: sophosympatheia/midnight-rose-70b
 label:
-  zh_Hans: sophosympatheia/midnight-rose-70b
-  en_US: sophosympatheia/midnight-rose-70b
+  zh_Hans: Midnight Rose 70B
+  en_US: Midnight Rose 70B
 model_type: llm
 features:
  - agent-thought
--- a/api/core/model_runtime/model_providers/novita/llm/mistral-7b-instruct.yaml
+++ b/api/core/model_runtime/model_providers/novita/llm/mistral-7b-instruct.yaml
@@ -1,7 +1,7 @@
 model: mistralai/mistral-7b-instruct
 label:
-  zh_Hans: mistralai/mistral-7b-instruct
-  en_US: mistralai/mistral-7b-instruct
+  zh_Hans: Mistral 7B Instruct
+  en_US: Mistral 7B Instruct
 model_type: llm
 features:
  - agent-thought
--- a/api/core/model_runtime/model_providers/novita/llm/mistral-nemo.yaml
+++ b/api/core/model_runtime/model_providers/novita/llm/mistral-nemo.yaml
@@ -0,0 +1,41 @@
+model: mistralai/mistral-nemo
+label:
+  zh_Hans: Mistral Nemo
+  en_US: Mistral Nemo
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 131072
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    min: 0
+    max: 2
+    default: 1
+  - name: top_p
+    use_template: top_p
+    min: 0
+    max: 1
+    default: 1
+  - name: max_tokens
+    use_template: max_tokens
+    min: 1
+    max: 2048
+    default: 512
+  - name: frequency_penalty
+    use_template: frequency_penalty
+    min: -2
+    max: 2
+    default: 0
+  - name: presence_penalty
+    use_template: presence_penalty
+    min: -2
+    max: 2
+    default: 0
+pricing:
+  input: '0.0017'
+  output: '0.0017'
+  unit: '0.0001'
+  currency: USD
--- a/api/core/model_runtime/model_providers/novita/llm/mythomax-l2-13b.yaml
+++ b/api/core/model_runtime/model_providers/novita/llm/mythomax-l2-13b.yaml
@@ -1,7 +1,7 @@
 model: gryphe/mythomax-l2-13b
 label:
-  zh_Hans: gryphe/mythomax-l2-13b
-  en_US: gryphe/mythomax-l2-13b
+  zh_Hans: Mythomax L2 13B
+  en_US: Mythomax L2 13B
 model_type: llm
 features:
  - agent-thought
@@ -35,7 +35,7 @@ parameter_rules:
    max: 2
    default: 0
 pricing:
-  input: '0.00119'
-  output: '0.00119'
+  input: '0.0009'
+  output: '0.0009'
  unit: '0.0001'
  currency: USD
--- a/api/core/model_runtime/model_providers/novita/llm/nous-hermes-llama2-13b.yaml
+++ b/api/core/model_runtime/model_providers/novita/llm/nous-hermes-llama2-13b.yaml
@@ -1,7 +1,7 @@
 model: nousresearch/nous-hermes-llama2-13b
 label:
-  zh_Hans: nousresearch/nous-hermes-llama2-13b
-  en_US: nousresearch/nous-hermes-llama2-13b
+  zh_Hans: Nous Hermes Llama2 13B
+  en_US: Nous Hermes Llama2 13B
 model_type: llm
 features:
  - agent-thought
--- a/api/core/model_runtime/model_providers/novita/llm/openchat-7b.yaml
+++ b/api/core/model_runtime/model_providers/novita/llm/openchat-7b.yaml
@@ -1,7 +1,7 @@
-model: lzlv_70b
+model: openchat/openchat-7b
 label:
-  zh_Hans: lzlv_70b
-  en_US: lzlv_70b
+  zh_Hans: OpenChat 7B
+  en_US: OpenChat 7B
 model_type: llm
 features:
  - agent-thought
@@ -35,7 +35,7 @@ parameter_rules:
    max: 2
    default: 0
 pricing:
-  input: '0.0058'
-  output: '0.0078'
+  input: '0.0006'
+  output: '0.0006'
  unit: '0.0001'
  currency: USD
--- a/api/core/model_runtime/model_providers/novita/llm/openhermes-2.5-mistral-7b.yaml
+++ b/api/core/model_runtime/model_providers/novita/llm/openhermes-2.5-mistral-7b.yaml
@@ -1,7 +1,7 @@
 model: teknium/openhermes-2.5-mistral-7b
 label:
-  zh_Hans: teknium/openhermes-2.5-mistral-7b
-  en_US: teknium/openhermes-2.5-mistral-7b
+  zh_Hans: Openhermes2.5 Mistral 7B
+  en_US: Openhermes2.5 Mistral 7B
 model_type: llm
 features:
  - agent-thought
--- a/api/core/model_runtime/model_providers/novita/llm/llama-3.1-405b-instruct.yaml
+++ b/api/core/model_runtime/model_providers/novita/llm/llama-3.1-405b-instruct.yaml
@@ -1,7 +1,7 @@
-model: meta-llama/llama-3.1-405b-instruct
+model: qwen/qwen-2-72b-instruct
 label:
-  zh_Hans: meta-llama/llama-3.1-405b-instruct
-  en_US: meta-llama/llama-3.1-405b-instruct
+  zh_Hans: Qwen2 72B Instruct
+  en_US: Qwen2 72B Instruct
 model_type: llm
 features:
  - agent-thought
@@ -35,7 +35,7 @@ parameter_rules:
    max: 2
    default: 0
 pricing:
-  input: '0.03'
-  output: '0.05'
+  input: '0.0034'
+  output: '0.0039'
  unit: '0.0001'
  currency: USD
--- a/api/core/model_runtime/model_providers/novita/llm/qwen-2-7b-instruct.yaml
+++ b/api/core/model_runtime/model_providers/novita/llm/qwen-2-7b-instruct.yaml
@@ -0,0 +1,41 @@
+model: qwen/qwen-2-7b-instruct
+label:
+  zh_Hans: Qwen 2 7B Instruct
+  en_US: Qwen 2 7B Instruct
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 32768
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    min: 0
+    max: 2
+    default: 1
+  - name: top_p
+    use_template: top_p
+    min: 0
+    max: 1
+    default: 1
+  - name: max_tokens
+    use_template: max_tokens
+    min: 1
+    max: 2048
+    default: 512
+  - name: frequency_penalty
+    use_template: frequency_penalty
+    min: -2
+    max: 2
+    default: 0
+  - name: presence_penalty
+    use_template: presence_penalty
+    min: -2
+    max: 2
+    default: 0
+pricing:
+  input: '0.00054'
+  output: '0.00054'
+  unit: '0.0001'
+  currency: USD
--- a/api/core/model_runtime/model_providers/novita/llm/qwen-2-vl-72b-instruct.yaml
+++ b/api/core/model_runtime/model_providers/novita/llm/qwen-2-vl-72b-instruct.yaml
@@ -0,0 +1,41 @@
+model: qwen/qwen-2-vl-72b-instruct
+label:
+  zh_Hans: Qwen 2 VL 72B Instruct
+  en_US: Qwen 2 VL 72B Instruct
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 32768
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    min: 0
+    max: 2
+    default: 1
+  - name: top_p
+    use_template: top_p
+    min: 0
+    max: 1
+    default: 1
+  - name: max_tokens
+    use_template: max_tokens
+    min: 1
+    max: 2048
+    default: 512
+  - name: frequency_penalty
+    use_template: frequency_penalty
+    min: -2
+    max: 2
+    default: 0
+  - name: presence_penalty
+    use_template: presence_penalty
+    min: -2
+    max: 2
+    default: 0
+pricing:
+  input: '0.0045'
+  output: '0.0045'
+  unit: '0.0001'
+  currency: USD
--- a/api/core/model_runtime/model_providers/novita/llm/qwen-2.5-72b-instruct.yaml
+++ b/api/core/model_runtime/model_providers/novita/llm/qwen-2.5-72b-instruct.yaml
@@ -0,0 +1,41 @@
+model: qwen/qwen-2.5-72b-instruct
+label:
+  zh_Hans: Qwen 2.5 72B Instruct
+  en_US: Qwen 2.5 72B Instruct
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 32000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    min: 0
+    max: 2
+    default: 1
+  - name: top_p
+    use_template: top_p
+    min: 0
+    max: 1
+    default: 1
+  - name: max_tokens
+    use_template: max_tokens
+    min: 1
+    max: 2048
+    default: 512
+  - name: frequency_penalty
+    use_template: frequency_penalty
+    min: -2
+    max: 2
+    default: 0
+  - name: presence_penalty
+    use_template: presence_penalty
+    min: -2
+    max: 2
+    default: 0
+pricing:
+  input: '0.0038'
+  output: '0.004'
+  unit: '0.0001'
+  currency: USD
--- a/api/core/model_runtime/model_providers/novita/llm/wizardlm-2-8x22b.yaml
+++ b/api/core/model_runtime/model_providers/novita/llm/wizardlm-2-8x22b.yaml
@@ -1,7 +1,7 @@
 model: microsoft/wizardlm-2-8x22b
 label:
-  zh_Hans: microsoft/wizardlm-2-8x22b
-  en_US: microsoft/wizardlm-2-8x22b
+  zh_Hans: Wizardlm 2 8x22B
+  en_US: Wizardlm 2 8x22B
 model_type: llm
 features:
  - agent-thought
@@ -35,7 +35,7 @@ parameter_rules:
    max: 2
    default: 0
 pricing:
-  input: '0.0064'
-  output: '0.0064'
+  input: '0.0062'
+  output: '0.0062'
  unit: '0.0001'
  currency: USD
--- a/api/core/model_runtime/model_providers/novita/novita.yaml
+++ b/api/core/model_runtime/model_providers/novita/novita.yaml
@@ -1,6 +1,6 @@
 provider: novita
 label:
-  en_US: novita.ai
+  en_US: Novita AI
 description:
  en_US: An LLM API that matches various application scenarios with high cost-effectiveness.
  zh_Hans: 适配多种海外应用场景的高性价比 LLM API
@@ -8,13 +8,13 @@ icon_small:
  en_US: icon_s_en.svg
 icon_large:
  en_US: icon_l_en.svg
-background: "#eadeff"
+background: "#c7fce2"
 help:
  title:
-    en_US: Get your API key from novita.ai
-    zh_Hans: 从 novita.ai 获取 API Key
+    en_US: Get your API key from Novita AI
+    zh_Hans: 从 Novita AI 获取 API Key
  url:
-    en_US: https://novita.ai/settings#key-management?utm_source=dify&utm_medium=ch&utm_campaign=api
+    en_US: https://novita.ai/settings/key-management?utm_source=dify&utm_medium=ch&utm_campaign=api
 supported_model_types:
  - llm
 configurate_methods:
--- a/api/core/model_runtime/model_providers/nvidia/llm/_position.yaml
+++ b/api/core/model_runtime/model_providers/nvidia/llm/_position.yaml
@@ -1,3 +1,4 @@
+- deepseek-ai/deepseek-r1
 - google/gemma-7b
 - google/codegemma-7b
 - google/recurrentgemma-2b
--- a/api/core/model_runtime/model_providers/nvidia/llm/deepseek-r1.yaml
+++ b/api/core/model_runtime/model_providers/nvidia/llm/deepseek-r1.yaml
@@ -0,0 +1,35 @@
+model: deepseek-ai/deepseek-r1
+label:
+  en_US: deepseek-ai/deepseek-r1
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 128000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    min: 0
+    max: 1
+    default: 0.5
+  - name: top_p
+    use_template: top_p
+    min: 0
+    max: 1
+    default: 1
+  - name: max_tokens
+    use_template: max_tokens
+    min: 1
+    max: 1024
+    default: 1024
+  - name: frequency_penalty
+    use_template: frequency_penalty
+    min: -2
+    max: 2
+    default: 0
+  - name: presence_penalty
+    use_template: presence_penalty
+    min: -2
+    max: 2
+    default: 0
--- a/api/core/model_runtime/model_providers/nvidia/llm/llm.py
+++ b/api/core/model_runtime/model_providers/nvidia/llm/llm.py
@@ -83,7 +83,7 @@ class NVIDIALargeLanguageModel(OAIAPICompatLargeLanguageModel):
    def _add_custom_parameters(self, credentials: dict, model: str) -> None:
        credentials["mode"] = "chat"

-        if self.MODEL_SUFFIX_MAP[model]:
+        if self.MODEL_SUFFIX_MAP.get(model):
            credentials["server_url"] = f"https://ai.api.nvidia.com/v1/{self.MODEL_SUFFIX_MAP[model]}"
            credentials.pop("endpoint_url")
        else:
--- a/api/core/model_runtime/model_providers/oci/llm/cohere.command-r-08-2024.yaml
+++ b/api/core/model_runtime/model_providers/oci/llm/cohere.command-r-08-2024.yaml
@@ -0,0 +1,52 @@
+model: cohere.command-r-08-2024
+label:
+  en_US: cohere.command-r-08-2024 v1.7
+model_type: llm
+features:
+  - multi-tool-call
+  - agent-thought
+  - stream-tool-call
+model_properties:
+  mode: chat
+  context_size: 128000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    default: 1
+    max: 1.0
+  - name: topP
+    use_template: top_p
+    default: 0.75
+    min: 0
+    max: 1
+  - name: topK
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
+    default: 0
+    min: 0
+    max: 500
+  - name: presencePenalty
+    use_template: presence_penalty
+    min: 0
+    max: 1
+    default: 0
+  - name: frequencyPenalty
+    use_template: frequency_penalty
+    min: 0
+    max: 1
+    default: 0
+  - name: maxTokens
+    use_template: max_tokens
+    default: 600
+    max: 4000
+pricing:
+  input: '0.0009'
+  output: '0.0009'
+  unit: '0.0001'
+  currency: USD
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
jyong	295bbc4a8b	upgrade Unstructured version	2025-02-13 15:08:34 +08:00
Yingchun Lai	a3d3e30e3a	fix: fix tongyi models blocking mode with incremental_output=stream (#13620 )	2025-02-13 10:24:05 +08:00
AugNSo	2b86465d4c	fix document extractor node incorrectly processing doc and ppt files (#12902 )	2025-02-12 18:04:28 +08:00
kimjion	6529240da6	fix: no longer using old app detail cover when switch pathname (#13585 )	2025-02-12 15:02:11 +08:00
Bowen Liang	0751ad1eeb	feat(vdb): add HNSW vector index for TiDB vector store with TiFlash (#12043 )	2025-02-12 13:53:51 +08:00
Riddhimaan-Senapati	786550bdc9	fix: changed topics/keywords to topic/keywords (#13544 )	2025-02-12 09:15:15 +08:00
jiangbo721	bde756a1ab	chore:Remove useless brackets and format code (#13479 ) Co-authored-by: 刘江波 <jiangbo721@163.com>	2025-02-11 22:05:29 +08:00
Wu Jiayang	423fb2d7bc	Ensure the 'inputs' field in /chat-messages takes effect every time (#7955 ) Co-authored-by: Your Name <you@example.com> Co-authored-by: -LAN- <laipz8200@outlook.com>	2025-02-11 18:44:56 +08:00
Novice	f96b4f287a	fix: iteration node log time error (#13511 )	2025-02-11 16:35:21 +08:00
Novice	c00e7d3f65	fix: retry log running error (#13472 ) Co-authored-by: Novice Lee <novicelee@NoviPro.local>	2025-02-11 15:48:55 +08:00
yihong	1f38d4846b	fix: issue #13483 and #13434 (#13518 ) Signed-off-by: yihong0618 <zouzou0208@gmail.com>	2025-02-11 12:45:49 +08:00
liuzhenghua	47a64610ca	Fix the issue of repeated escaping of quotes in hit test (#13477 )	2025-02-11 09:58:31 +08:00
Riddhimaan-Senapati	f0a845f0f9	fix: removed LLM output from the main README (#13504 )	2025-02-11 09:09:07 +08:00
Abdullah AlOsaimi	abec23118d	feat: add support for X-Forwarded-Port in ProxyFix middleware (#13102 )	2025-02-10 22:28:29 +08:00
Xin Zhang	0957119550	fix: update UTC time format for consistency (#13471 )	2025-02-10 19:37:50 +08:00
github-actions[bot]	f48fa3e4e8	chore: translate i18n files (#13452 ) Co-authored-by: douxc <7553076+douxc@users.noreply.github.com>	2025-02-10 14:14:15 +08:00
非法操作	5ffc58d6ca	feat: improve think content display (#13431 )	2025-02-10 14:08:17 +08:00
NFish	7d958635f0	Fix/add trial expire tip time (#13464 )	2025-02-10 12:53:59 +08:00
Wu Tianwei	33990426c1	fix: add ids in FetchDatasetsParams (#13459 )	2025-02-10 12:28:36 +08:00
yihong	9f3fc7ebf8	ci: make ci safe using zizmor (#13397 ) Signed-off-by: yihong0618 <zouzou0208@gmail.com>	2025-02-10 12:26:08 +08:00
ybalbert001	c8357da13b	[Fix] Sagemaker LLM Provider can't adjust context size, it'a always 2… (#13462 ) Co-authored-by: Yuanbo Li <ybalbert@amazon.com>	2025-02-10 12:25:04 +08:00
NFish	2290f14fb1	feat: add tooltip if user's anthropic trial quota still available (#13418 )	2025-02-10 10:44:20 +08:00
Fei He	7796984444	Fix: Removed model params except max_token for deepseek r1 in volcengine (#13446 )	2025-02-10 10:26:26 +08:00
Fei He	75113c26c6	Feat : add deepseek support for tongyi (#13445 )	2025-02-10 10:26:03 +08:00
xhe	939a9ecd21	chore: use the wrap thinking api for volcengine (#13432 ) Signed-off-by: xhe <xw897002528@gmail.com>	2025-02-10 10:25:07 +08:00
Summer-Gu	f307c7cd88	feat: Docker adds SSRF-related timeout settings (#13395 )	2025-02-10 10:21:31 +08:00
Riddhimaan-Senapati	33ecceb90c	Feat: add comparison table to main readme (#13435 )	2025-02-10 10:13:46 +08:00
NFish	e0d1cab079	fix: add missed background color to iteration node (#13448 )	2025-02-10 10:04:56 +08:00
Riddhimaan-Senapati	811d72a727	feat: added a _position.yaml for vertex ai provider (#13367 )	2025-02-09 10:29:07 +08:00
Yi Xiao	c3c575c2e1	Fix: model selector UI hover issue (#13396 )	2025-02-09 10:24:57 +08:00
海狸大師	c189629eca	Fix(i18n): Refine zh-Hant workflow translations (#13421 )	2025-02-09 10:24:45 +08:00
Naoki Takashima	37117c22d4	feat(model): support Gemini 2.0 Flash Lite Preview model (02-05) in Google's model provider (#13399 )	2025-02-09 10:22:33 +08:00
Riddhimaan-Senapati	b05e9d2ab4	feat: update backend documentation (#13374 )	2025-02-08 20:36:33 +08:00
aplio	0451333990	fix(settings): add notClearable prop to language selection (#13406 )	2025-02-08 20:36:23 +08:00
MuYu	ab2e6c19a4	Fixes #13415 reset model-provider-page form value use schema.default (#13416 )	2025-02-08 20:34:52 +08:00
aplio	f7959bc887	fix(chatbot): update button class to include text color for better visibility (#13411 )	2025-02-08 20:34:37 +08:00
aplio	45874c699d	Nitpick/fix typos in document (#13413 )	2025-02-08 20:33:45 +08:00
Junjie.M	286cdc41ab	reasoning model unified think tag is <think></think> (#13392 ) Co-authored-by: crazywoola <427733928@qq.com>	2025-02-08 16:19:41 +08:00
Hash Brown	78708eb5d5	fix: merge conflict between #11301 and #11885 (#13391 )	2025-02-08 14:38:10 +08:00
胡春东	cf36745770	fix(workflow_tool): enable File parameter support after workflow is published as a tool (#13175 )	2025-02-08 12:30:00 +08:00
depy	6622c7f98d	fix: Fix HTTP request node non 443 port SSL site inaccessible (#13376 )	2025-02-08 12:00:45 +08:00
Hash Brown	3112b74527	fix: build failed due to `getPrevChatList` no longer exists (#13383 )	2025-02-08 11:59:02 +08:00
Katy Tao	b3ae6b634f	feat: add pan and zoom support for MiniMap (#13382 )	2025-02-08 11:57:41 +08:00
Xin Zhang	982bca5d40	fix: add rate limiting to prevent brute force on password reset (#13292 )	2025-02-08 10:28:31 +08:00
Kalo Chin	c8dcde6cd0	fix: Gemini 2.0 Flash 001 model yaml file naming (#13372 )	2025-02-08 09:12:42 +08:00
Riddhimaan-Senapati	8f9db61688	feat: added new silicon flow models (#13369 )	2025-02-08 09:12:22 +08:00
github-actions[bot]	ebdbaf34e6	chore: translate i18n files (#13349 ) Co-authored-by: JzoNgKVO <27049666+JzoNgKVO@users.noreply.github.com>	2025-02-07 22:41:25 +08:00
zhu-an	a081b1e79e	fix: add compatibility config for third-party S3-compatible providers (#13354 ) Co-authored-by: zhaoqingyu.1075 <zhaoqingyu.1075@bytedance.com>	2025-02-07 22:35:24 +08:00
Steven sun	38c31e64db	add enable_search parameter to qwen_max, plus, turbo (#13335 ) Co-authored-by: steven <sunzwj@digitalchina.com>	2025-02-07 22:16:26 +08:00
Yi Xiao	ae6f67420c	Chore: update app detail panel (#13337 )	2025-02-07 18:56:43 +08:00
-LAN-	ca19bd31d4	chore(*): Bump version to 0.15.3 (#13308 ) Signed-off-by: -LAN- <laipz8200@outlook.com>	2025-02-07 15:20:05 +08:00
-LAN-	413dfd5628	feat: add completion mode and context size options for LLM configuration (#13325 ) Signed-off-by: -LAN- <laipz8200@outlook.com>	2025-02-07 15:08:53 +08:00
-LAN-	f9515901cc	fix: Azure AI Foundry model cannot be used in the workflow (#13323 ) Signed-off-by: -LAN- <laipz8200@outlook.com>	2025-02-07 14:52:57 +08:00
呆萌闷油瓶	3f42fabff8	chore:improve thinking display for llm from xinference and ollama pro… (#13318 )	2025-02-07 14:29:29 +08:00
-LAN-	1caa578771	chore(*): Update style of thinking (#13319 ) Signed-off-by: -LAN- <laipz8200@outlook.com>	2025-02-07 14:06:35 +08:00
Lazy_Frog	b7c11c1818	Fix the problem of Workflow terminates after parallel tasks execution, merge node not triggered (#12498 ) Co-authored-by: Novice Lee <novicelee@NoviPro.local>	2025-02-07 13:56:08 +08:00
非法操作	3eb3db0663	chore: refactor the OpenAICompatible and improve thinking display (#13299 )	2025-02-07 13:28:46 +08:00
-LAN-	be46f32056	fix(credits): require model name equals (#13314 ) Signed-off-by: -LAN- <laipz8200@outlook.com>	2025-02-07 13:28:17 +08:00
sino	6e5c915f96	feat(model): add deepseek-r1 for openrouter (#13312 )	2025-02-07 12:39:13 +08:00
-LAN-	04d13a8116	feat(credits): Allow to configure model-credit mapping (#13274 ) Signed-off-by: -LAN- <laipz8200@outlook.com>	2025-02-07 11:01:31 +08:00
Kemal	e638ede3f2	Update README_TR.md (#13294 )	2025-02-07 09:11:39 +08:00
Riddhimaan-Senapati	2348abe4bf	feat: added a couple of models not defined in vertex ai, that were already … (#13296 )	2025-02-07 09:11:25 +08:00
呆萌闷油瓶	f7e7a399d9	feat:add think tag display for xinference deepseek r1 (#13291 )	2025-02-06 22:04:58 +08:00
le0zh	ba91f34636	fix: incorrect transferMethod assignment for remote file (#13286 )	2025-02-06 19:32:21 +08:00
zhu-an	16865d43a8	feat: add deepseek models for volcengine provider (#13283 ) Co-authored-by: zhaoqingyu.1075 <zhaoqingyu.1075@bytedance.com>	2025-02-06 18:20:03 +08:00
呆萌闷油瓶	0d13aee15c	feat:add deepseek r1 think display for ollama provider (#13272 )	2025-02-06 15:32:10 +08:00
Wu Tianwei	49b4144ffd	fix: add dataset edit permissions (#13223 )	2025-02-06 14:26:16 +08:00
dependabot[bot]	186e2d972e	chore(deps): bump katex from 0.16.10 to 0.16.21 in /web (#13270 ) Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	2025-02-06 13:27:07 +08:00
engchina	40dd63ecef	Upgrade oracle models (#13174 ) Co-authored-by: engchina <atjapan2015@gmail.com>	2025-02-06 13:24:27 +08:00
-LAN-	6d66d6da15	feat(model_providers): Support deepseek-r1 for Nvidia Catalog (#13269 ) Signed-off-by: -LAN- <laipz8200@outlook.com>	2025-02-06 13:03:19 +08:00
weiwenyan-dev	03ec3513f3	Fix bug large data no render (#12683 ) Co-authored-by: ex_wenyan.wei <ex_wenyan.wei@tcl.com>	2025-02-06 13:00:04 +08:00
-LAN-	87763fc234	feat(model_providers): Support deepseek for Azure AI Foundry (#13267 ) Signed-off-by: -LAN- <laipz8200@outlook.com>	2025-02-06 12:45:48 +08:00
JasonVV	f6c44cae2e	feat(model): add gemini-2.0 model (#13266 )	2025-02-06 12:28:59 +08:00
xhe	da2ee04fce	fix: correct linewrap think display in generic openai api (#13260 ) Signed-off-by: xhe <xw897002528@gmail.com>	2025-02-06 10:53:08 +08:00
JasonVV	7673c36af3	feat(model): add gemini-2.0-flash-thinking-exp-01-21 (#13230 )	2025-02-06 10:01:00 +08:00
Riddhimaan-Senapati	9457b2af2f	feat: added models :gemini 2.0 flash 001 and gemini 2.0 pro exp 02-05 (#13247 )	2025-02-06 09:58:39 +08:00
k-zaku	7203991032	feat: add parameter "reasoning_effort" and Openai o3-mini (#13243 )	2025-02-06 09:29:48 +08:00
xhe	5a685f7156	feat: add think display for volcengine and generic openapi (#13234 ) Signed-off-by: xhe <xw897002528@gmail.com>	2025-02-06 09:24:40 +08:00
Riddhimaan-Senapati	a6a25030ad	fix: updated _position.yaml to include the latest model already integ… (#13245 )	2025-02-06 09:21:51 +08:00
Riddhimaan-Senapati	00458a31d5	feat: added deepseek r1 and v3 to siliconflow (#13238 )	2025-02-05 21:59:18 +08:00
-LAN-	c6ddf6d6cc	feat(model_providers): Add Groq DeepSeek-R1-Distill-Llama-70b (#13229 ) Signed-off-by: -LAN- <laipz8200@outlook.com>	2025-02-05 19:15:29 +08:00
Joshbly	34b21b3065	feat: Add o3-mini and o3-mini-2025-01-31 model variants (#13129 ) Co-authored-by: crazywoola <427733928@qq.com>	2025-02-05 17:04:45 +08:00
Bowen Liang	8fbb355cd2	chore: squash system dependencies installation steps (#13206 )	2025-02-05 16:42:53 +08:00
HQidea	e8b3b7e578	Fix new variables in the conversation opener would override prompt_variables (#13191 )	2025-02-05 16:16:00 +08:00
-LAN-	59ca44f493	chore(model_runtime): Move deepseek ahead in the providers list. (#13197 ) Signed-off-by: -LAN- <laipz8200@outlook.com>	2025-02-05 16:08:28 +08:00
Bowen Liang	9e1457c2c3	fix: mypy checks violation in AzureBlobStorage (#13215 )	2025-02-05 15:56:23 +08:00
te-chan	fac83e14bc	Use DefaultAzureCredential for managed identity in azure blob extention (#11559 )	2025-02-05 13:43:43 +08:00
Nam Vu	a97cec57e4	fix: SSRF proxy file descriptor leak in concurrent requests (#13108 )	2025-02-05 13:10:27 +08:00
Riddhimaan-Senapati	38c10b47d3	Feat: add linkedin to readme (#13203 )	2025-02-05 12:27:58 +08:00
MaFee921	1a2523fd15	feat: bedrock_endpoint_url (#12838 )	2025-02-05 12:24:24 +08:00
Warren Chen	03243cb422	Modify params for bedrock retrieve generate (#13182 )	2025-02-05 12:17:42 +08:00
Bowen Liang	2ad7ee0344	chore: add tests for build docker image when dockerfile changed (#10732 )	2025-02-05 11:40:22 +08:00
Riddhimaan-Senapati	55ce3618ce	fix: Dollar Sign Handling in Markdown (#13178 ) Co-authored-by: crazywoola <427733928@qq.com>	2025-02-05 11:00:56 +08:00
TechnoHouse	e9e34c1ab2	Install apt dependencies using bookworm source, consistent with base image. Remove unnecessary, error-prone pins (#13176 )	2025-02-05 10:07:22 +08:00
-LAN-	d4c916b496	chore(pyproject): Add type stubs into `pyproject.toml` (#13145 ) Signed-off-by: -LAN- <laipz8200@outlook.com>	2025-02-04 12:01:28 +08:00
Obada Khalili	8fbc9c9342	Solve circular dependency issue between `workflow/constants.ts` file and `default.ts` file (#13165 )	2025-02-04 09:26:01 +08:00
aplio	1b6fd9dfe8	fix: set indexing technique from dataset during update-by-text (#13155 )	2025-02-03 11:06:03 +08:00
非法操作	304467e3f5	fix: not install libmagic raise error (#13146 )	2025-02-03 11:05:20 +08:00
Kei YAMAZAKI	7452032d81	add azure openai api version 2024-12-01-preview (#13135 )	2025-02-03 11:04:20 +08:00
aplio	87e2048f1b	nitpick: fix small typos in template.en.mdx (#13156 )	2025-02-03 11:03:11 +08:00
Nam Vu	d876084392	chore: upgrade libldap2 (#13158 )	2025-02-03 11:02:14 +08:00
非法操作	840729afa5	feat: the think tag display of siliconflow's deepseek r1 (#13153 )	2025-02-02 21:55:13 +08:00
Obada Khalili	941ad03f3c	pass model and cost so that langfuse can show cost (#13117 )	2025-02-02 15:27:27 +08:00
aplio	d73d191f99	feature. add feat to modify metadata via dataset api (#13116 )	2025-02-02 15:27:12 +08:00
Masashi Tomooka	c2664e0283	chore: fix wrong VectorType match case (#13123 )	2025-02-02 15:26:59 +08:00
-LAN-	ee61cede4e	test(huggingface_hub): Skip the failed test temporarily. (#13142 ) Signed-off-by: -LAN- <laipz8200@outlook.com>	2025-02-02 14:47:26 +08:00
-LAN-	b47669b80b	fix: deduct LLM quota after processing invoke result (#13075 ) Signed-off-by: -LAN- <laipz8200@outlook.com>	2025-02-02 12:05:11 +08:00
Hash Brown	c0d0c63592	feat: switch to chat messages before regenerated (#11301 ) Co-authored-by: zuodongxu <192560071+zuodongxu@users.noreply.github.com>	2025-01-31 13:05:10 +08:00
Yingchun Lai	b09c39c8dc	refactor: avoid to use extra space when finding model by name (#13043 )	2025-01-30 15:08:29 +08:00
heyszt	b4b09ddc3c	add tongyi qwen2.5-14b/7b-instruct-1m model (#13089 )	2025-01-29 11:58:01 +08:00
Ademílson Tonato	d0a21086bd	refactor: Update Firecrawl API parameters and default settings (#13082 )	2025-01-29 11:21:05 +08:00
Yingchun Lai	d44882c1b5	refactor: reduce duplciate code by inheritance (#13073 )	2025-01-28 10:52:01 +08:00
Yingchun Lai	23c68efa2d	fix: fix the formatter is not applied on log file (#12704 )	2025-01-28 10:49:58 +08:00
Jason	560c5de1b7	Fixed Novita AI color and added DeepSeek R1 model (#13074 )	2025-01-28 10:38:54 +08:00
Abdullah AlOsaimi	5d91dbd000	Set default LOG_LEVEL to INFO for celery workers and beat (#13066 ) Co-authored-by: Abdullah AlOsaimi <189027247+osaimi@users.noreply.github.com>	2025-01-27 17:09:41 +08:00
heyszt	6c31ee36cd	fix qwen-vl blocking mode (#13052 )	2025-01-27 11:35:23 +08:00
jiandanfeng	edc29780ed	fix: "Model schema not found" error only in agents (#12655 ) (#12760 )	2025-01-27 11:33:13 +08:00
yjc980121	aad7e4dd1c	fix:Improve MIME type detection for remote URL uploads using python-magic (#12693 )	2025-01-27 11:33:03 +08:00
Xin Zhang	a6a727e8a4	feat: add inner API to create workspace without requiring email (#13021 )	2025-01-26 15:36:56 +08:00
NFish	d1fc65fabc	fix: adjust iteration node dark style (#13051 )	2025-01-26 11:19:41 +08:00
Jason	d4be5ef9de	Update Novita AI predefined models (#13045 )	2025-01-26 09:25:29 +08:00
Shun Miyazawa	1374be5a31	fix: Unexpected tag creation when pressing enter during tag conversion (#13041 )	2025-01-25 19:30:26 +08:00
Warren Chen	b2bbc28580	support bedrock kb: retrieve and generate (#13027 )	2025-01-25 17:28:06 +08:00
非法操作	59b3e672aa	feat: add agent thinking content display of deepseek R1 (#12949 )	2025-01-24 20:13:42 +08:00
IWAI, Masaharu	a2f8bce8f5	chore: add Japanese translation: model_providers/bedrock (#13016 )	2025-01-24 18:43:33 +08:00
Yueh-Po Peng (Yabi)	a2b9adb3a2	Change typo in translation (#13004 )	2025-01-24 13:48:21 +08:00
IWAI, Masaharu	28067640b5	fix: wrong zh_Hans translation: Ohio (#13006 )	2025-01-24 13:41:20 +08:00
lowell	da67916843	feat: add glm-4-air-0111 (#12997 ) Co-authored-by: lowell <lowell.hu@zkteco.in>	2025-01-24 10:04:46 +08:00
zxhlyh	e54ce479ad	Feat/prompt editor dark theme (#12976 )	2025-01-23 16:20:00 +08:00
Ademílson Tonato	6024d8a42d	refactor: Update Firecrawl to use v1 API (#12574 ) Co-authored-by: Ademílson Tonato <ademilson.tonato@refurbed.com>	2025-01-23 11:14:48 +08:00
Joel	f565f08aa0	fix: get property of string type variable caused page crash (#12969 )	2025-01-23 11:02:29 +08:00
Jhvcc	fd4afe09f8	fix: tools translate search (#12950 ) Co-authored-by: lowell <lowell.hu@zkteco.in>	2025-01-22 19:27:02 +08:00
jiandanfeng	dd0904f95c	feat: add giteeAI risk control identification. (#12946 )	2025-01-22 19:26:25 +08:00
huangzhuo1949	4c3076f2a4	feat: add pg vector index (#12338 ) Co-authored-by: huangzhuo <huangzhuo1@xiaomi.com>	2025-01-22 17:07:18 +08:00