feat: support speech2text and tts for gpustack

fix: gpustack llm and text_embedding model url path wrong after edited
2026-01-10 00:04:14 +00:00 · 2025-01-07 09:19:39 +08:00 · 2025-01-07 09:19:39 +08:00
551 changed files with 10957 additions and 18958 deletions
--- a/.github/actions/setup-poetry/action.yml
+++ b/.github/actions/setup-poetry/action.yml
@@ -8,7 +8,7 @@ inputs:
  poetry-version:
    description: Poetry version to set up
    required: true
-    default: '2.0.1'
+    default: '1.8.4'
  poetry-lockfile:
    description: Path to the Poetry lockfile to restore cache from
    required: true
--- a/.github/workflows/api-tests.yml
+++ b/.github/workflows/api-tests.yml
@@ -42,23 +42,25 @@ jobs:
        run: poetry install -C api --with dev

      - name: Check dependencies in pyproject.toml
-        run: poetry run -P api bash dev/pytest/pytest_artifacts.sh
+        run: poetry run -C api bash dev/pytest/pytest_artifacts.sh

      - name: Run Unit tests
-        run: poetry run -P api bash dev/pytest/pytest_unit_tests.sh
+        run: poetry run -C api bash dev/pytest/pytest_unit_tests.sh

      - name: Run ModelRuntime
-        run: poetry run -P api bash dev/pytest/pytest_model_runtime.sh
+        run: poetry run -C api bash dev/pytest/pytest_model_runtime.sh

      - name: Run dify config tests
-        run: poetry run -P api python dev/pytest/pytest_config_tests.py
+        run: poetry run -C api python dev/pytest/pytest_config_tests.py

      - name: Run Tool
-        run: poetry run -P api bash dev/pytest/pytest_tools.sh
+        run: poetry run -C api bash dev/pytest/pytest_tools.sh

      - name: Run mypy
        run: |
-          poetry run -C api python -m mypy --install-types --non-interactive .
+          pushd api
+          poetry run python -m mypy --install-types --non-interactive .
+          popd

      - name: Set up dotenvs
        run: |
@@ -78,4 +80,4 @@ jobs:
            ssrf_proxy

      - name: Run Workflow
-        run: poetry run -P api bash dev/pytest/pytest_workflow.sh
+        run: poetry run -C api bash dev/pytest/pytest_workflow.sh
--- a/.github/workflows/build-push.yml
+++ b/.github/workflows/build-push.yml
@@ -5,8 +5,8 @@ on:
    branches:
      - "main"
      - "deploy/dev"
-    tags:
-      - "*"
+  release:
+    types: [published]

 concurrency:
  group: build-push-${{ github.head_ref || github.run_id }}
--- a/.github/workflows/docker-build.yml
+++ b/.github/workflows/docker-build.yml
@@ -1,47 +0,0 @@
-name: Build docker image
-
-on:
-  pull_request:
-    branches:
-      - "main"
-    paths:
-      - api/Dockerfile
-      - web/Dockerfile
-
-concurrency:
-  group: docker-build-${{ 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/style.yml
+++ b/.github/workflows/style.yml
@@ -38,12 +38,12 @@ jobs:
        if: steps.changed-files.outputs.any_changed == 'true'
        run: |
          poetry run -C api ruff --version
-          poetry run -C api ruff check ./
-          poetry run -C api ruff format --check ./
+          poetry run -C api ruff check ./api
+          poetry run -C api ruff format --check ./api

      - name: Dotenv check
        if: steps.changed-files.outputs.any_changed == 'true'
-        run: poetry run -P api dotenv-linter ./api/.env.example ./web/.env.example
+        run: poetry run -C api dotenv-linter ./api/.env.example ./web/.env.example

      - name: Lint hints
        if: failure()
@@ -82,33 +82,6 @@ jobs:
        if: steps.changed-files.outputs.any_changed == 'true'
        run: yarn run lint

-  docker-compose-template:
-    name: Docker Compose Template
-    runs-on: ubuntu-latest
-
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v4
-
-      - name: Check changed files
-        id: changed-files
-        uses: tj-actions/changed-files@v45
-        with:
-          files: |
-            docker/generate_docker_compose
-            docker/.env.example
-            docker/docker-compose-template.yaml
-            docker/docker-compose.yaml
-
-      - name: Generate Docker Compose
-        if: steps.changed-files.outputs.any_changed == 'true'
-        run: |
-          cd docker
-          ./generate_docker_compose
-
-      - name: Check for changes
-        if: steps.changed-files.outputs.any_changed == 'true'
-        run: git diff --exit-code

  superlinter:
    name: SuperLinter
--- a/.github/workflows/vdb-tests.yml
+++ b/.github/workflows/vdb-tests.yml
@@ -70,4 +70,4 @@ jobs:
            tidb

      - name: Test Vector Stores
-        run: poetry run -P api bash dev/pytest/pytest_vdb.sh
+        run: poetry run -C api bash dev/pytest/pytest_vdb.sh
--- a/.markdownlint.json
+++ b/.markdownlint.json
@@ -1,4 +0,0 @@
-{
-    "MD024": false,
-    "MD013": false
-}
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,45 +0,0 @@
-# Changelog
-
-All notable changes to Dify will be documented in this file.
-
-The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
-and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
-
-## [0.15.8] - 2025-05-30
-
-### Added
-
- Added gunicorn keepalive setting (#19537)
-
-### Fixed
-
- Fixed database configuration to allow DB_EXTRAS to set search_path via options (#16a4f77)
- Fixed frontend third-party package security issues (#19655)
- Updated dependencies: huggingface-hub (~0.16.4 to ~0.31.0), transformers (~4.35.0 to ~4.39.0), and resend (~0.7.0 to ~2.9.0) (#19563)
- Downgrade boto3 from 1.36 to 1.35 (#19736)
-
-## [0.15.7] - 2025-04-27
-
-### Added
-
- Added support for GPT-4.1 in model providers (#18912)
- Added support for Amazon Bedrock DeepSeek-R1 model (#18908)
- Added support for Amazon Bedrock Claude Sonnet 3.7 model (#18788)
- Refined version compatibility logic in app DSL service
-
-### Fixed
-
- Fixed issue with creating apps from template categories (#18807, #18868)
- Fixed DSL version check when creating apps from explore templates (#18872, #18878)
-
-## [0.15.6] - 2025-04-22
-
-### Security
-
- Fixed clickjacking vulnerability (#18552)
- Fixed reset password security issue (#18366)
- Updated reset password token when email code verification succeeds (#18362)
-
-### Fixed
-
- Fixed Vertex AI Gemini 2.0 Flash 001 schema (#18405)
--- a/README.md
+++ b/README.md
@@ -25,9 +25,6 @@
    <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_AR.md
+++ b/README_AR.md
@@ -21,9 +21,6 @@
    <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
@@ -21,9 +21,6 @@
    <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
@@ -21,9 +21,6 @@
    <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
@@ -21,9 +21,6 @@
    <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
@@ -21,9 +21,6 @@
    <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
@@ -21,9 +21,6 @@
    <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_KR.md
+++ b/README_KR.md
@@ -21,9 +21,6 @@
    <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
@@ -25,9 +25,6 @@
    <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
@@ -22,9 +22,6 @@
    <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_TR.md
+++ b/README_TR.md
@@ -21,9 +21,6 @@
    <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">
@@ -65,6 +62,8 @@ 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.

@@ -151,6 +150,8 @@ 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>**
@@ -176,6 +177,8 @@ 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
@@ -21,9 +21,6 @@
    <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/.env.example
+++ b/api/.env.example
@@ -430,7 +430,4 @@ CREATE_TIDB_SERVICE_JOB_ENABLED=false
 # Maximum number of submitted thread count in a ThreadPool for parallel node execution
 MAX_SUBMIT_COUNT=100
 # Lockout duration in seconds
-LOGIN_LOCKOUT_DURATION=86400
-
-# Prevent Clickjacking
-ALLOW_EMBED=false
+LOGIN_LOCKOUT_DURATION=86400
--- a/api/.ruff.toml
+++ b/api/.ruff.toml
@@ -53,12 +53,10 @@ ignore = [
    "FURB152", # math-constant
    "UP007", # non-pep604-annotation
    "UP032", # f-string
-    "UP045", # non-pep604-annotation-optional
    "B005", # strip-with-multi-characters
    "B006", # mutable-argument-default
    "B007", # unused-loop-control-variable
    "B026", # star-arg-unpacking-after-keyword-arg
-    "B903", # class-as-data-structure
    "B904", # raise-without-from-inside-except
    "B905", # zip-without-explicit-strict
    "N806", # non-lowercase-variable-in-function
--- a/api/Dockerfile
+++ b/api/Dockerfile
@@ -4,7 +4,7 @@ FROM python:3.12-slim-bookworm AS base
 WORKDIR /app/api

 # Install Poetry
-ENV POETRY_VERSION=2.0.1
+ENV POETRY_VERSION=1.8.4

 # if you located in China, you can use aliyun mirror to speed up
 # RUN pip install --no-cache-dir poetry==${POETRY_VERSION} -i https://mirrors.aliyun.com/pypi/simple/
@@ -48,18 +48,16 @@ ENV TZ=UTC

 WORKDIR /app/api

-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 \
+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 \
    && apt-get autoremove -y \
    && rm -rf /var/lib/apt/lists/*

@@ -78,6 +76,7 @@ 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
@@ -79,5 +79,5 @@
 2. Run the tests locally with mocked system environment variables in `tool.pytest_env` section in `pyproject.toml`

   ```bash
-   poetry run -P api bash dev/pytest/pytest_all_tests.sh
+   poetry run -C api bash dev/pytest/pytest_all_tests.sh
   ```
--- a/api/configs/feature/init.py
+++ b/api/configs/feature/init.py
@@ -146,7 +146,7 @@ class EndpointConfig(BaseSettings):
    )

    CONSOLE_WEB_URL: str = Field(
-        description="Base URL for the console web interface,used for frontend references and CORS configuration",
+        description="Base URL for the console web interface," "used for frontend references and CORS configuration",
        default="",
    )

--- a/api/configs/feature/hosted_service/init.py
+++ b/api/configs/feature/hosted_service/init.py
@@ -1,40 +1,9 @@
 from typing import Optional

-from pydantic import Field, NonNegativeInt, computed_field
+from pydantic import Field, NonNegativeInt
 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
@@ -212,7 +181,7 @@ class HostedFetchAppTemplateConfig(BaseSettings):
    """

    HOSTED_FETCH_APP_TEMPLATES_MODE: str = Field(
-        description="Mode for fetching app templates: remote, db, or builtin default to remote,",
+        description="Mode for fetching app templates: remote, db, or builtin" " default to remote,",
        default="remote",
    )

@@ -233,7 +202,5 @@ class HostedServiceConfig(
    HostedZhipuAIConfig,
    # moderation
    HostedModerationConfig,
-    # credit config
-    HostedCreditConfig,
 ):
    pass
--- a/api/configs/middleware/init.py
+++ b/api/configs/middleware/init.py
@@ -1,5 +1,5 @@
 from typing import Any, Literal, Optional
-from urllib.parse import parse_qsl, quote_plus
+from urllib.parse import quote_plus

 from pydantic import Field, NonNegativeInt, PositiveFloat, PositiveInt, computed_field
 from pydantic_settings import BaseSettings
@@ -166,28 +166,14 @@ class DatabaseConfig(BaseSettings):
        default=False,
    )

-    @computed_field  # type: ignore[misc]
-    @property
+    @computed_field
    def SQLALCHEMY_ENGINE_OPTIONS(self) -> dict[str, Any]:
-        # Parse DB_EXTRAS for 'options'
-        db_extras_dict = dict(parse_qsl(self.DB_EXTRAS))
-        options = db_extras_dict.get("options", "")
-        # Always include timezone
-        timezone_opt = "-c timezone=UTC"
-        if options:
-            # Merge user options and timezone
-            merged_options = f"{options} {timezone_opt}"
-        else:
-            merged_options = timezone_opt
-
-        connect_args = {"options": merged_options}
-
        return {
            "pool_size": self.SQLALCHEMY_POOL_SIZE,
            "max_overflow": self.SQLALCHEMY_MAX_OVERFLOW,
            "pool_recycle": self.SQLALCHEMY_POOL_RECYCLE,
            "pool_pre_ping": self.SQLALCHEMY_POOL_PRE_PING,
-            "connect_args": connect_args,
+            "connect_args": {"options": "-c timezone=UTC"},
        }


--- a/api/configs/middleware/vdb/milvus_config.py
+++ b/api/configs/middleware/vdb/milvus_config.py
@@ -33,9 +33,3 @@ class MilvusConfig(BaseSettings):
        description="Name of the Milvus database to connect to (default is 'default')",
        default="default",
    )
-
-    MILVUS_ENABLE_HYBRID_SEARCH: bool = Field(
-        description="Enable hybrid search features (requires Milvus >= 2.5.0). Set to false for compatibility with "
-        "older versions",
-        default=True,
-    )
--- 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="0.15.8",
+        default="0.14.2",
    )

    COMMIT_SHA: str = Field(
--- a/api/controllers/common/helpers.py
+++ b/api/controllers/common/helpers.py
@@ -1,32 +1,12 @@
 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
@@ -67,13 +47,6 @@ 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/admin.py
+++ b/api/controllers/console/admin.py
@@ -56,7 +56,7 @@ class InsertExploreAppListApi(Resource):

        app = App.query.filter(App.id == args["app_id"]).first()
        if not app:
-            raise NotFound(f"App '{args['app_id']}' is not found")
+            raise NotFound(f'App \'{args["app_id"]}\' is not found')

        site = app.site
        if not site:
--- a/api/controllers/console/app/audio.py
+++ b/api/controllers/console/app/audio.py
@@ -22,7 +22,7 @@ from controllers.console.wraps import account_initialization_required, setup_req
 from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError
 from core.model_runtime.errors.invoke import InvokeError
 from libs.login import login_required
-from models import App, AppMode
+from models.model import AppMode
 from services.audio_service import AudioService
 from services.errors.audio import (
    AudioTooLargeServiceError,
@@ -79,7 +79,7 @@ class ChatMessageTextApi(Resource):
    @login_required
    @account_initialization_required
    @get_app_model
-    def post(self, app_model: App):
+    def post(self, app_model):
        from werkzeug.exceptions import InternalServerError

        try:
@@ -98,13 +98,9 @@ class ChatMessageTextApi(Resource):
                and app_model.workflow.features_dict
            ):
                text_to_speech = app_model.workflow.features_dict.get("text_to_speech")
-                if text_to_speech is None:
-                    raise ValueError("TTS is not enabled")
                voice = args.get("voice") or text_to_speech.get("voice")
            else:
                try:
-                    if app_model.app_model_config is None:
-                        raise ValueError("AppModelConfig not found")
                    voice = args.get("voice") or app_model.app_model_config.text_to_speech_dict.get("voice")
                except Exception:
                    voice = None
--- a/api/controllers/console/auth/forgot_password.py
+++ b/api/controllers/console/auth/forgot_password.py
@@ -8,7 +8,7 @@ from constants.languages import languages
 from controllers.console import api
 from controllers.console.auth.error import EmailCodeError, InvalidEmailError, InvalidTokenError, PasswordMismatchError
 from controllers.console.error import AccountInFreezeError, AccountNotFound, EmailSendIpLimitError
-from controllers.console.wraps import email_password_login_enabled, setup_required
+from controllers.console.wraps import setup_required
 from events.tenant_event import tenant_was_created
 from extensions.ext_database import db
 from libs.helper import email, extract_remote_ip
@@ -22,7 +22,6 @@ from services.feature_service import FeatureService

 class ForgotPasswordSendEmailApi(Resource):
    @setup_required
-    @email_password_login_enabled
    def post(self):
        parser = reqparse.RequestParser()
        parser.add_argument("email", type=email, required=True, location="json")
@@ -54,7 +53,6 @@ class ForgotPasswordSendEmailApi(Resource):

 class ForgotPasswordCheckApi(Resource):
    @setup_required
-    @email_password_login_enabled
    def post(self):
        parser = reqparse.RequestParser()
        parser.add_argument("email", type=str, required=True, location="json")
@@ -74,20 +72,11 @@ class ForgotPasswordCheckApi(Resource):
        if args["code"] != token_data.get("code"):
            raise EmailCodeError()

-        # Verified, revoke the first token
-        AccountService.revoke_reset_password_token(args["token"])
-
-        # Refresh token data by generating a new token
-        _, new_token = AccountService.generate_reset_password_token(
-            user_email, code=args["code"], additional_data={"phase": "reset"}
-        )
-
-        return {"is_valid": True, "email": token_data.get("email"), "token": new_token}
+        return {"is_valid": True, "email": token_data.get("email")}


 class ForgotPasswordResetApi(Resource):
    @setup_required
-    @email_password_login_enabled
    def post(self):
        parser = reqparse.RequestParser()
        parser.add_argument("token", type=str, required=True, nullable=False, location="json")
@@ -106,9 +95,6 @@ class ForgotPasswordResetApi(Resource):

        if reset_data is None:
            raise InvalidTokenError()
-        # Must use token in reset phase
-        if reset_data.get("phase", "") != "reset":
-            raise InvalidTokenError()

        AccountService.revoke_reset_password_token(token)

--- a/api/controllers/console/auth/login.py
+++ b/api/controllers/console/auth/login.py
@@ -22,7 +22,7 @@ from controllers.console.error import (
    EmailSendIpLimitError,
    NotAllowedCreateWorkspace,
 )
-from controllers.console.wraps import email_password_login_enabled, setup_required
+from controllers.console.wraps import setup_required
 from events.tenant_event import tenant_was_created
 from libs.helper import email, extract_remote_ip
 from libs.password import valid_password
@@ -38,7 +38,6 @@ class LoginApi(Resource):
    """Resource for user login."""

    @setup_required
-    @email_password_login_enabled
    def post(self):
        """Authenticate user and login."""
        parser = reqparse.RequestParser()
@@ -111,7 +110,6 @@ class LogoutApi(Resource):

 class ResetPasswordSendEmailApi(Resource):
    @setup_required
-    @email_password_login_enabled
    def post(self):
        parser = reqparse.RequestParser()
        parser.add_argument("email", type=email, required=True, location="json")
--- a/api/controllers/console/datasets/datasets.py
+++ b/api/controllers/console/datasets/datasets.py
@@ -52,12 +52,12 @@ class DatasetListApi(Resource):
        # provider = request.args.get("provider", default="vendor")
        search = request.args.get("keyword", default=None, type=str)
        tag_ids = request.args.getlist("tag_ids")
-        include_all = request.args.get("include_all", default="false").lower() == "true"
+
        if ids:
            datasets, total = DatasetService.get_datasets_by_ids(ids, current_user.current_tenant_id)
        else:
            datasets, total = DatasetService.get_datasets(
-                page, limit, current_user.current_tenant_id, current_user, search, tag_ids, include_all
+                page, limit, current_user.current_tenant_id, current_user, search, tag_ids
            )

        # check embedding setting
@@ -457,7 +457,7 @@ class DatasetIndexingEstimateApi(Resource):
            )
        except LLMBadRequestError:
            raise ProviderNotInitializeError(
-                "No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
+                "No Embedding Model available. Please configure a valid provider " "in the Settings -> Model Provider."
            )
        except ProviderTokenNotInitError as ex:
            raise ProviderNotInitializeError(ex.description)
@@ -619,7 +619,9 @@ class DatasetRetrievalSettingApi(Resource):
        vector_type = dify_config.VECTOR_STORE
        match vector_type:
            case (
-                VectorType.RELYT
+                VectorType.MILVUS
+                | VectorType.RELYT
+                | VectorType.PGVECTOR
                | VectorType.TIDB_VECTOR
                | VectorType.CHROMA
                | VectorType.TENCENT
@@ -638,12 +640,10 @@ class DatasetRetrievalSettingApi(Resource):
                | VectorType.MYSCALE
                | VectorType.ORACLE
                | VectorType.ELASTICSEARCH
-                | VectorType.ELASTICSEARCH_JA
                | VectorType.PGVECTOR
                | VectorType.TIDB_ON_QDRANT
                | VectorType.LINDORM
                | VectorType.COUCHBASE
-                | VectorType.MILVUS
            ):
                return {
                    "retrieval_method": [
@@ -683,7 +683,6 @@ class DatasetRetrievalSettingMockApi(Resource):
                | VectorType.MYSCALE
                | VectorType.ORACLE
                | VectorType.ELASTICSEARCH
-                | VectorType.ELASTICSEARCH_JA
                | VectorType.COUCHBASE
                | VectorType.PGVECTOR
                | VectorType.LINDORM
--- a/api/controllers/console/datasets/datasets_document.py
+++ b/api/controllers/console/datasets/datasets_document.py
@@ -257,8 +257,7 @@ class DatasetDocumentListApi(Resource):
        parser.add_argument("original_document_id", type=str, required=False, location="json")
        parser.add_argument("doc_form", type=str, default="text_model", required=False, nullable=False, location="json")
        parser.add_argument("retrieval_model", type=dict, required=False, nullable=False, location="json")
-        parser.add_argument("embedding_model", type=str, required=False, nullable=True, location="json")
-        parser.add_argument("embedding_model_provider", type=str, required=False, nullable=True, location="json")
+
        parser.add_argument(
            "doc_language", type=str, default="English", required=False, nullable=False, location="json"
        )
@@ -350,7 +349,8 @@ class DatasetInitApi(Resource):
                )
            except InvokeAuthorizationError:
                raise ProviderNotInitializeError(
-                    "No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
+                    "No Embedding Model available. Please configure a valid provider "
+                    "in the Settings -> Model Provider."
                )
            except ProviderTokenNotInitError as ex:
                raise ProviderNotInitializeError(ex.description)
@@ -525,7 +525,8 @@ class DocumentBatchIndexingEstimateApi(DocumentResource):
                return response.model_dump(), 200
            except LLMBadRequestError:
                raise ProviderNotInitializeError(
-                    "No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
+                    "No Embedding Model available. Please configure a valid provider "
+                    "in the Settings -> Model Provider."
                )
            except ProviderTokenNotInitError as ex:
                raise ProviderNotInitializeError(ex.description)
--- a/api/controllers/console/datasets/datasets_segments.py
+++ b/api/controllers/console/datasets/datasets_segments.py
@@ -168,7 +168,8 @@ class DatasetDocumentSegmentApi(Resource):
                )
            except LLMBadRequestError:
                raise ProviderNotInitializeError(
-                    "No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
+                    "No Embedding Model available. Please configure a valid provider "
+                    "in the Settings -> Model Provider."
                )
            except ProviderTokenNotInitError as ex:
                raise ProviderNotInitializeError(ex.description)
@@ -216,7 +217,8 @@ class DatasetDocumentSegmentAddApi(Resource):
                )
            except LLMBadRequestError:
                raise ProviderNotInitializeError(
-                    "No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
+                    "No Embedding Model available. Please configure a valid provider "
+                    "in the Settings -> Model Provider."
                )
            except ProviderTokenNotInitError as ex:
                raise ProviderNotInitializeError(ex.description)
@@ -265,7 +267,8 @@ class DatasetDocumentSegmentUpdateApi(Resource):
                )
            except LLMBadRequestError:
                raise ProviderNotInitializeError(
-                    "No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
+                    "No Embedding Model available. Please configure a valid provider "
+                    "in the Settings -> Model Provider."
                )
            except ProviderTokenNotInitError as ex:
                raise ProviderNotInitializeError(ex.description)
@@ -365,9 +368,9 @@ class DatasetDocumentSegmentBatchImportApi(Resource):
            result = []
            for index, row in df.iterrows():
                if document.doc_form == "qa_model":
-                    data = {"content": row.iloc[0], "answer": row.iloc[1]}
+                    data = {"content": row[0], "answer": row[1]}
                else:
-                    data = {"content": row.iloc[0]}
+                    data = {"content": row[0]}
                result.append(data)
            if len(result) == 0:
                raise ValueError("The CSV file is empty.")
@@ -434,7 +437,8 @@ class ChildChunkAddApi(Resource):
                )
            except LLMBadRequestError:
                raise ProviderNotInitializeError(
-                    "No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
+                    "No Embedding Model available. Please configure a valid provider "
+                    "in the Settings -> Model Provider."
                )
            except ProviderTokenNotInitError as ex:
                raise ProviderNotInitializeError(ex.description)
--- a/api/controllers/console/explore/conversation.py
+++ b/api/controllers/console/explore/conversation.py
@@ -32,7 +32,7 @@ class ConversationListApi(InstalledAppResource):

        pinned = None
        if "pinned" in args and args["pinned"] is not None:
-            pinned = args["pinned"] == "true"
+            pinned = True if args["pinned"] == "true" else False

        try:
            with Session(db.engine) as session:
--- 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"]
+                app_model, current_user, args["conversation_id"], args["first_id"], args["limit"], "desc"
            )
        except services.errors.conversation.ConversationNotExistsError:
            raise NotFound("Conversation Not Exists.")
--- a/api/controllers/console/wraps.py
+++ b/api/controllers/console/wraps.py
@@ -154,16 +154,3 @@ def enterprise_license_required(view):
        return view(*args, **kwargs)

    return decorated
-
-
-def email_password_login_enabled(view):
-    @wraps(view)
-    def decorated(*args, **kwargs):
-        features = FeatureService.get_system_features()
-        if features.enable_email_password_login:
-            return view(*args, **kwargs)
-
-        # otherwise, return 403
-        abort(403)
-
-    return decorated
--- a/api/controllers/inner_api/workspace/workspace.py
+++ b/api/controllers/inner_api/workspace/workspace.py
@@ -1,5 +1,3 @@
-import json
-
 from flask_restful import Resource, reqparse  # type: ignore

 from controllers.console.wraps import setup_required
@@ -31,34 +29,4 @@ 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() if tenant.created_at else None,
-            "updated_at": tenant.updated_at.isoformat() 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/init.py
+++ b/api/controllers/service_api/init.py
@@ -7,4 +7,4 @@ api = ExternalApi(bp)

 from . import index
 from .app import app, audio, completion, conversation, file, message, workflow
-from .dataset import dataset, document, hit_testing, segment, upload_file
+from .dataset import dataset, document, hit_testing, segment
--- a/api/controllers/service_api/dataset/dataset.py
+++ b/api/controllers/service_api/dataset/dataset.py
@@ -31,11 +31,8 @@ class DatasetListApi(DatasetApiResource):
        # provider = request.args.get("provider", default="vendor")
        search = request.args.get("keyword", default=None, type=str)
        tag_ids = request.args.getlist("tag_ids")
-        include_all = request.args.get("include_all", default="false").lower() == "true"

-        datasets, total = DatasetService.get_datasets(
-            page, limit, tenant_id, current_user, search, tag_ids, include_all
-        )
+        datasets, total = DatasetService.get_datasets(page, limit, tenant_id, current_user, search, tag_ids)
        # check embedding setting
        provider_manager = ProviderManager()
        configurations = provider_manager.get_configurations(tenant_id=current_user.current_tenant_id)
--- a/api/controllers/service_api/dataset/document.py
+++ b/api/controllers/service_api/dataset/document.py
@@ -18,7 +18,6 @@ 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
@@ -51,9 +50,6 @@ 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)
@@ -65,28 +61,6 @@ 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:
@@ -133,8 +107,6 @@ 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)
@@ -143,32 +115,6 @@ 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")
@@ -215,30 +161,6 @@ 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)
@@ -306,29 +228,6 @@ 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/service_api/dataset/segment.py
+++ b/api/controllers/service_api/dataset/segment.py
@@ -53,7 +53,8 @@ class SegmentApi(DatasetApiResource):
                )
            except LLMBadRequestError:
                raise ProviderNotInitializeError(
-                    "No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
+                    "No Embedding Model available. Please configure a valid provider "
+                    "in the Settings -> Model Provider."
                )
            except ProviderTokenNotInitError as ex:
                raise ProviderNotInitializeError(ex.description)
@@ -94,7 +95,8 @@ class SegmentApi(DatasetApiResource):
                )
            except LLMBadRequestError:
                raise ProviderNotInitializeError(
-                    "No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
+                    "No Embedding Model available. Please configure a valid provider "
+                    "in the Settings -> Model Provider."
                )
            except ProviderTokenNotInitError as ex:
                raise ProviderNotInitializeError(ex.description)
@@ -173,7 +175,8 @@ class DatasetSegmentApi(DatasetApiResource):
                )
            except LLMBadRequestError:
                raise ProviderNotInitializeError(
-                    "No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
+                    "No Embedding Model available. Please configure a valid provider "
+                    "in the Settings -> Model Provider."
                )
            except ProviderTokenNotInitError as ex:
                raise ProviderNotInitializeError(ex.description)
--- a/api/controllers/service_api/dataset/upload_file.py
+++ b/api/controllers/service_api/dataset/upload_file.py
@@ -1,54 +0,0 @@
-from werkzeug.exceptions import NotFound
-
-from controllers.service_api import api
-from controllers.service_api.wraps import (
-    DatasetApiResource,
-)
-from core.file import helpers as file_helpers
-from extensions.ext_database import db
-from models.dataset import Dataset
-from models.model import UploadFile
-from services.dataset_service import DocumentService
-
-
-class UploadFileApi(DatasetApiResource):
-    def get(self, tenant_id, dataset_id, document_id):
-        """Get upload file."""
-        # check dataset
-        dataset_id = str(dataset_id)
-        tenant_id = str(tenant_id)
-        dataset = db.session.query(Dataset).filter(Dataset.tenant_id == tenant_id, Dataset.id == dataset_id).first()
-        if not dataset:
-            raise NotFound("Dataset not found.")
-        # check document
-        document_id = str(document_id)
-        document = DocumentService.get_document(dataset.id, document_id)
-        if not document:
-            raise NotFound("Document not found.")
-        # check upload file
-        if document.data_source_type != "upload_file":
-            raise ValueError(f"Document data source type ({document.data_source_type}) is not upload_file.")
-        data_source_info = document.data_source_info_dict
-        if data_source_info and "upload_file_id" in data_source_info:
-            file_id = data_source_info["upload_file_id"]
-            upload_file = db.session.query(UploadFile).filter(UploadFile.id == file_id).first()
-            if not upload_file:
-                raise NotFound("UploadFile not found.")
-        else:
-            raise ValueError("Upload file id not found in document data source info.")
-
-        url = file_helpers.get_signed_file_url(upload_file_id=upload_file.id)
-        return {
-            "id": upload_file.id,
-            "name": upload_file.name,
-            "size": upload_file.size,
-            "extension": upload_file.extension,
-            "url": url,
-            "download_url": f"{url}&as_attachment=true",
-            "mime_type": upload_file.mime_type,
-            "created_by": upload_file.created_by,
-            "created_at": upload_file.created_at.timestamp(),
-        }, 200
-
-
-api.add_resource(UploadFileApi, "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/upload-file")
--- a/api/controllers/service_api/wraps.py
+++ b/api/controllers/service_api/wraps.py
@@ -1,5 +1,5 @@
 from collections.abc import Callable
-from datetime import UTC, datetime, timedelta
+from datetime import UTC, datetime
 from enum import Enum
 from functools import wraps
 from typing import Optional
@@ -8,8 +8,6 @@ from flask import current_app, request
 from flask_login import user_logged_in  # type: ignore
 from flask_restful import Resource  # type: ignore
 from pydantic import BaseModel
-from sqlalchemy import select, update
-from sqlalchemy.orm import Session
 from werkzeug.exceptions import Forbidden, Unauthorized

 from extensions.ext_database import db
@@ -176,7 +174,7 @@ def validate_dataset_token(view=None):
    return decorator


-def validate_and_get_api_token(scope: str | None = None):
+def validate_and_get_api_token(scope=None):
    """
    Validate and get API token.
    """
@@ -190,29 +188,20 @@ def validate_and_get_api_token(scope: str | None = None):
    if auth_scheme != "bearer":
        raise Unauthorized("Authorization scheme must be 'Bearer'")

-    current_time = datetime.now(UTC).replace(tzinfo=None)
-    cutoff_time = current_time - timedelta(minutes=1)
-    with Session(db.engine, expire_on_commit=False) as session:
-        update_stmt = (
-            update(ApiToken)
-            .where(
-                ApiToken.token == auth_token,
-                (ApiToken.last_used_at.is_(None) | (ApiToken.last_used_at < cutoff_time)),
-                ApiToken.type == scope,
-            )
-            .values(last_used_at=current_time)
-            .returning(ApiToken)
+    api_token = (
+        db.session.query(ApiToken)
+        .filter(
+            ApiToken.token == auth_token,
+            ApiToken.type == scope,
        )
-        result = session.execute(update_stmt)
-        api_token = result.scalar_one_or_none()
+        .first()
+    )

-        if not api_token:
-            stmt = select(ApiToken).where(ApiToken.token == auth_token, ApiToken.type == scope)
-            api_token = session.scalar(stmt)
-            if not api_token:
-                raise Unauthorized("Access token is invalid")
-        else:
-            session.commit()
+    if not api_token:
+        raise Unauthorized("Access token is invalid")
+
+    api_token.last_used_at = datetime.now(UTC).replace(tzinfo=None)
+    db.session.commit()

    return api_token

@@ -240,7 +229,7 @@ def create_or_update_end_user_for_user_id(app_model: App, user_id: Optional[str]
            tenant_id=app_model.tenant_id,
            app_id=app_model.id,
            type="service_api",
-            is_anonymous=user_id == "DEFAULT-USER",
+            is_anonymous=True if user_id == "DEFAULT-USER" else False,
            session_id=user_id,
        )
        db.session.add(end_user)
--- a/api/controllers/web/conversation.py
+++ b/api/controllers/web/conversation.py
@@ -39,7 +39,7 @@ class ConversationListApi(WebApiResource):

        pinned = None
        if "pinned" in args and args["pinned"] is not None:
-            pinned = args["pinned"] == "true"
+            pinned = True if args["pinned"] == "true" else False

        try:
            with Session(db.engine) as session:
--- 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"]
+                app_model, end_user, args["conversation_id"], args["first_id"], args["limit"], "desc"
            )
        except services.errors.conversation.ConversationNotExistsError:
            raise NotFound("Conversation Not Exists.")
--- a/api/core/agent/cot_agent_runner.py
+++ b/api/core/agent/cot_agent_runner.py
@@ -104,6 +104,7 @@ class CotAgentRunner(BaseAgentRunner, ABC):

            # recalc llm max tokens
            prompt_messages = self._organize_prompt_messages()
+            self.recalc_llm_max_tokens(self.model_config, prompt_messages)
            # invoke model
            chunks = model_instance.invoke_llm(
                prompt_messages=prompt_messages,
@@ -171,7 +172,7 @@ class CotAgentRunner(BaseAgentRunner, ABC):

            self.save_agent_thought(
                agent_thought=agent_thought,
-                tool_name=(scratchpad.action.action_name if scratchpad.action and not scratchpad.is_final() else ""),
+                tool_name=scratchpad.action.action_name if scratchpad.action else "",
                tool_input={scratchpad.action.action_name: scratchpad.action.action_input} if scratchpad.action else {},
                tool_invoke_meta={},
                thought=scratchpad.thought or "",
--- a/api/core/agent/fc_agent_runner.py
+++ b/api/core/agent/fc_agent_runner.py
@@ -84,6 +84,7 @@ class FunctionCallAgentRunner(BaseAgentRunner):

            # recalc llm max tokens
            prompt_messages = self._organize_prompt_messages()
+            self.recalc_llm_max_tokens(self.model_config, prompt_messages)
            # invoke model
            chunks: Union[Generator[LLMResultChunk, None, None], LLMResult] = model_instance.invoke_llm(
                prompt_messages=prompt_messages,
--- a/api/core/app/apps/agent_chat/app_runner.py
+++ b/api/core/app/apps/agent_chat/app_runner.py
@@ -55,6 +55,20 @@ class AgentChatAppRunner(AppRunner):
        query = application_generate_entity.query
        files = application_generate_entity.files

+        # Pre-calculate the number of tokens of the prompt messages,
+        # and return the rest number of tokens by model context token size limit and max token size limit.
+        # If the rest number of tokens is not enough, raise exception.
+        # Include: prompt template, inputs, query(optional), files(optional)
+        # Not Include: memory, external data, dataset context
+        self.get_pre_calculate_rest_tokens(
+            app_record=app_record,
+            model_config=application_generate_entity.model_conf,
+            prompt_template_entity=app_config.prompt_template,
+            inputs=inputs,
+            files=files,
+            query=query,
+        )
+
        memory = None
        if application_generate_entity.conversation_id:
            # get memory of conversation (read-only)
@@ -188,7 +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:
+        if not model_schema or not model_schema.features:
            raise ValueError("Model schema not found")

        if {ModelFeature.MULTI_TOOL_CALL, ModelFeature.TOOL_CALL}.intersection(model_schema.features or []):
--- a/api/core/app/apps/base_app_queue_manager.py
+++ b/api/core/app/apps/base_app_queue_manager.py
@@ -167,7 +167,8 @@ class AppQueueManager:
        else:
            if isinstance(data, DeclarativeMeta) or hasattr(data, "_sa_instance_state"):
                raise TypeError(
-                    "Critical Error: Passing SQLAlchemy Model instances that cause thread safety issues is not allowed."
+                    "Critical Error: Passing SQLAlchemy Model instances "
+                    "that cause thread safety issues is not allowed."
                )


--- a/api/core/app/apps/base_app_runner.py
+++ b/api/core/app/apps/base_app_runner.py
@@ -15,8 +15,10 @@ from core.app.features.annotation_reply.annotation_reply import AnnotationReplyF
 from core.app.features.hosting_moderation.hosting_moderation import HostingModerationFeature
 from core.external_data_tool.external_data_fetch import ExternalDataFetch
 from core.memory.token_buffer_memory import TokenBufferMemory
+from core.model_manager import ModelInstance
 from core.model_runtime.entities.llm_entities import LLMResult, LLMResultChunk, LLMResultChunkDelta, LLMUsage
 from core.model_runtime.entities.message_entities import AssistantPromptMessage, PromptMessage
+from core.model_runtime.entities.model_entities import ModelPropertyKey
 from core.model_runtime.errors.invoke import InvokeBadRequestError
 from core.moderation.input_moderation import InputModeration
 from core.prompt.advanced_prompt_transform import AdvancedPromptTransform
@@ -29,6 +31,106 @@ if TYPE_CHECKING:


 class AppRunner:
+    def get_pre_calculate_rest_tokens(
+        self,
+        app_record: App,
+        model_config: ModelConfigWithCredentialsEntity,
+        prompt_template_entity: PromptTemplateEntity,
+        inputs: Mapping[str, str],
+        files: Sequence["File"],
+        query: Optional[str] = None,
+    ) -> int:
+        """
+        Get pre calculate rest tokens
+        :param app_record: app record
+        :param model_config: model config entity
+        :param prompt_template_entity: prompt template entity
+        :param inputs: inputs
+        :param files: files
+        :param query: query
+        :return:
+        """
+        # Invoke model
+        model_instance = ModelInstance(
+            provider_model_bundle=model_config.provider_model_bundle, model=model_config.model
+        )
+
+        model_context_tokens = model_config.model_schema.model_properties.get(ModelPropertyKey.CONTEXT_SIZE)
+
+        max_tokens = 0
+        for parameter_rule in model_config.model_schema.parameter_rules:
+            if parameter_rule.name == "max_tokens" or (
+                parameter_rule.use_template and parameter_rule.use_template == "max_tokens"
+            ):
+                max_tokens = (
+                    model_config.parameters.get(parameter_rule.name)
+                    or model_config.parameters.get(parameter_rule.use_template or "")
+                ) or 0
+
+        if model_context_tokens is None:
+            return -1
+
+        if max_tokens is None:
+            max_tokens = 0
+
+        # get prompt messages without memory and context
+        prompt_messages, stop = self.organize_prompt_messages(
+            app_record=app_record,
+            model_config=model_config,
+            prompt_template_entity=prompt_template_entity,
+            inputs=inputs,
+            files=files,
+            query=query,
+        )
+
+        prompt_tokens = model_instance.get_llm_num_tokens(prompt_messages)
+
+        rest_tokens: int = model_context_tokens - max_tokens - prompt_tokens
+        if rest_tokens < 0:
+            raise InvokeBadRequestError(
+                "Query or prefix prompt is too long, you can reduce the prefix prompt, "
+                "or shrink the max token, or switch to a llm with a larger token limit size."
+            )
+
+        return rest_tokens
+
+    def recalc_llm_max_tokens(
+        self, model_config: ModelConfigWithCredentialsEntity, prompt_messages: list[PromptMessage]
+    ):
+        # recalc max_tokens if sum(prompt_token +  max_tokens) over model token limit
+        model_instance = ModelInstance(
+            provider_model_bundle=model_config.provider_model_bundle, model=model_config.model
+        )
+
+        model_context_tokens = model_config.model_schema.model_properties.get(ModelPropertyKey.CONTEXT_SIZE)
+
+        max_tokens = 0
+        for parameter_rule in model_config.model_schema.parameter_rules:
+            if parameter_rule.name == "max_tokens" or (
+                parameter_rule.use_template and parameter_rule.use_template == "max_tokens"
+            ):
+                max_tokens = (
+                    model_config.parameters.get(parameter_rule.name)
+                    or model_config.parameters.get(parameter_rule.use_template or "")
+                ) or 0
+
+        if model_context_tokens is None:
+            return -1
+
+        if max_tokens is None:
+            max_tokens = 0
+
+        prompt_tokens = model_instance.get_llm_num_tokens(prompt_messages)
+
+        if prompt_tokens + max_tokens > model_context_tokens:
+            max_tokens = max(model_context_tokens - prompt_tokens, 16)
+
+            for parameter_rule in model_config.model_schema.parameter_rules:
+                if parameter_rule.name == "max_tokens" or (
+                    parameter_rule.use_template and parameter_rule.use_template == "max_tokens"
+                ):
+                    model_config.parameters[parameter_rule.name] = max_tokens
+
    def organize_prompt_messages(
        self,
        app_record: App,
--- a/api/core/app/apps/chat/app_runner.py
+++ b/api/core/app/apps/chat/app_runner.py
@@ -50,6 +50,20 @@ class ChatAppRunner(AppRunner):
        query = application_generate_entity.query
        files = application_generate_entity.files

+        # Pre-calculate the number of tokens of the prompt messages,
+        # and return the rest number of tokens by model context token size limit and max token size limit.
+        # If the rest number of tokens is not enough, raise exception.
+        # Include: prompt template, inputs, query(optional), files(optional)
+        # Not Include: memory, external data, dataset context
+        self.get_pre_calculate_rest_tokens(
+            app_record=app_record,
+            model_config=application_generate_entity.model_conf,
+            prompt_template_entity=app_config.prompt_template,
+            inputs=inputs,
+            files=files,
+            query=query,
+        )
+
        memory = None
        if application_generate_entity.conversation_id:
            # get memory of conversation (read-only)
@@ -180,6 +194,9 @@ class ChatAppRunner(AppRunner):
        if hosting_moderation_result:
            return

+        # Re-calculate the max tokens if sum(prompt_token +  max_tokens) over model token limit
+        self.recalc_llm_max_tokens(model_config=application_generate_entity.model_conf, prompt_messages=prompt_messages)
+
        # Invoke model
        model_instance = ModelInstance(
            provider_model_bundle=application_generate_entity.model_conf.provider_model_bundle,
--- a/api/core/app/apps/completion/app_runner.py
+++ b/api/core/app/apps/completion/app_runner.py
@@ -43,6 +43,20 @@ class CompletionAppRunner(AppRunner):
        query = application_generate_entity.query
        files = application_generate_entity.files

+        # Pre-calculate the number of tokens of the prompt messages,
+        # and return the rest number of tokens by model context token size limit and max token size limit.
+        # If the rest number of tokens is not enough, raise exception.
+        # Include: prompt template, inputs, query(optional), files(optional)
+        # Not Include: memory, external data, dataset context
+        self.get_pre_calculate_rest_tokens(
+            app_record=app_record,
+            model_config=application_generate_entity.model_conf,
+            prompt_template_entity=app_config.prompt_template,
+            inputs=inputs,
+            files=files,
+            query=query,
+        )
+
        # organize all inputs and template to prompt messages
        # Include: prompt template, inputs, query(optional), files(optional)
        prompt_messages, stop = self.organize_prompt_messages(
@@ -138,6 +152,9 @@ class CompletionAppRunner(AppRunner):
        if hosting_moderation_result:
            return

+        # Re-calculate the max tokens if sum(prompt_token +  max_tokens) over model token limit
+        self.recalc_llm_max_tokens(model_config=application_generate_entity.model_conf, prompt_messages=prompt_messages)
+
        # Invoke model
        model_instance = ModelInstance(
            provider_model_bundle=application_generate_entity.model_conf.provider_model_bundle,
--- a/api/core/app/apps/message_based_app_generator.py
+++ b/api/core/app/apps/message_based_app_generator.py
@@ -89,7 +89,6 @@ class MessageBasedAppGenerator(BaseAppGenerator):
            Conversation.id == conversation_id,
            Conversation.app_id == app_model.id,
            Conversation.status == "normal",
-            Conversation.is_deleted.is_(False),
        ]

        if isinstance(user, Account):
--- a/api/core/app/task_pipeline/message_cycle_manage.py
+++ b/api/core/app/task_pipeline/message_cycle_manage.py
@@ -145,7 +145,7 @@ class MessageCycleManage:

            # get extension
            if "." in message_file.url:
-                extension = f".{message_file.url.split('.')[-1]}"
+                extension = f'.{message_file.url.split(".")[-1]}'
                if len(extension) > 10:
                    extension = ".bin"
            else:
--- a/api/core/external_data_tool/api/api.py
+++ b/api/core/external_data_tool/api/api.py
@@ -62,9 +62,8 @@ class ApiExternalDataTool(ExternalDataTool):

        if not api_based_extension:
            raise ValueError(
-                "[External data tool] API query failed, variable: {}, error: api_based_extension_id is invalid".format(
-                    self.variable
-                )
+                "[External data tool] API query failed, variable: {}, "
+                "error: api_based_extension_id is invalid".format(self.variable)
            )

        # decrypt api_key
--- a/api/core/file/models.py
+++ b/api/core/file/models.py
@@ -90,7 +90,7 @@ class File(BaseModel):
    def markdown(self) -> str:
        url = self.generate_url()
        if self.type == FileType.IMAGE:
-            text = f"![{self.filename or ''}]({url})"
+            text = f'![{self.filename or ""}]({url})'
        else:
            text = f"[{self.filename or url}]({url})"

--- a/api/core/helper/ssrf_proxy.py
+++ b/api/core/helper/ssrf_proxy.py
@@ -11,6 +11,15 @@ 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]

@@ -42,11 +51,7 @@ 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 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),
-                }
+            elif proxy_mounts:
                with httpx.Client(mounts=proxy_mounts) as client:
                    response = client.request(method=method, url=url, **kwargs)
            else:
--- a/api/core/indexing_runner.py
+++ b/api/core/indexing_runner.py
@@ -530,6 +530,7 @@ class IndexingRunner:
        # chunk nodes by chunk size
        indexing_start_at = time.perf_counter()
        tokens = 0
+        chunk_size = 10
        if dataset_document.doc_form != IndexType.PARENT_CHILD_INDEX:
            # create keyword index
            create_keyword_thread = threading.Thread(
@@ -538,22 +539,11 @@ class IndexingRunner:
            )
            create_keyword_thread.start()

-        max_workers = 10
        if dataset.indexing_technique == "high_quality":
-            with concurrent.futures.ThreadPoolExecutor(max_workers=max_workers) as executor:
+            with concurrent.futures.ThreadPoolExecutor(max_workers=10) as executor:
                futures = []
-
-                # Distribute documents into multiple groups based on the hash values of page_content
-                # This is done to prevent multiple threads from processing the same document,
-                # Thereby avoiding potential database insertion deadlocks
-                document_groups: list[list[Document]] = [[] for _ in range(max_workers)]
-                for document in documents:
-                    hash = helper.generate_text_hash(document.page_content)
-                    group_index = int(hash, 16) % max_workers
-                    document_groups[group_index].append(document)
-                for chunk_documents in document_groups:
-                    if len(chunk_documents) == 0:
-                        continue
+                for i in range(0, len(documents), chunk_size):
+                    chunk_documents = documents[i : i + chunk_size]
                    futures.append(
                        executor.submit(
                            self._process_chunk,
--- a/api/core/llm_generator/prompts.py
+++ b/api/core/llm_generator/prompts.py
@@ -131,7 +131,7 @@ JAVASCRIPT_CODE_GENERATOR_PROMPT_TEMPLATE = (
 SUGGESTED_QUESTIONS_AFTER_ANSWER_INSTRUCTION_PROMPT = (
    "Please help me predict the three most likely questions that human would ask, "
    "and keeping each question under 20 characters.\n"
-    "MAKE SURE your output is the SAME language as the Assistant's latest response. "
+    "MAKE SURE your output is the SAME language as the Assistant's latest response"
    "The output must be an array in JSON format following the specified schema:\n"
    '["question1","question2","question3"]\n'
 )
--- a/api/core/memory/token_buffer_memory.py
+++ b/api/core/memory/token_buffer_memory.py
@@ -26,7 +26,7 @@ class TokenBufferMemory:
        self.model_instance = model_instance

    def get_history_prompt_messages(
-        self, max_token_limit: int = 100000, message_limit: Optional[int] = None
+        self, max_token_limit: int = 2000, message_limit: Optional[int] = None
    ) -> Sequence[PromptMessage]:
        """
        Get history prompt messages.
--- a/api/core/model_runtime/entities/init.py
+++ b/api/core/model_runtime/entities/init.py
@@ -1,4 +1,4 @@
-from .llm_entities import LLMMode, LLMResult, LLMResultChunk, LLMResultChunkDelta, LLMUsage
+from .llm_entities import LLMResult, LLMResultChunk, LLMResultChunkDelta, LLMUsage
 from .message_entities import (
    AssistantPromptMessage,
    AudioPromptMessageContent,
@@ -23,7 +23,6 @@ __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 StrEnum
+from enum import Enum
 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(StrEnum):
+class LLMMode(Enum):
    """
    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
@@ -221,12 +221,13 @@ class AIModel(ABC):
        :param credentials: model credentials
        :return: model schema
        """
-        # Try to get model schema from predefined models
-        for predefined_model in self.predefined_models():
-            if model == predefined_model.model:
-                return predefined_model
+        # 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 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
@@ -30,11 +30,6 @@ from core.model_runtime.model_providers.__base.ai_model import AIModel

 logger = logging.getLogger(__name__)

-HTML_THINKING_TAG = (
-    '<details style="color:gray;background-color: #f8f8f8;padding: 8px;border-radius: 4px;" open> '
-    "<summary> Thinking... </summary>"
-)
-

 class LargeLanguageModel(AIModel):
    """
@@ -405,40 +400,6 @@ 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 details 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 = HTML_THINKING_TAG + reasoning_content
-                is_reasoning = True
-            else:
-                content = reasoning_content
-        elif is_reasoning:
-            content = "</details>" + content
-            is_reasoning = False
-        return content, is_reasoning
-
-    def _wrap_thinking_by_tag(self, content: str) -> str:
-        """
-        if the reasoning response is a <think>...</think> block from delta.get("content"),
-        we replace <think> to <detail>.
-
-        :param content: delta.get("content")
-        :return: processed_content
-        """
-        return content.replace("<think>", HTML_THINKING_TAG).replace("</think>", "</details>")
-
    def _invoke_result_generator(
        self,
        model: str,
--- a/api/core/model_runtime/model_providers/__base/tokenizers/gpt2_tokenzier.py
+++ b/api/core/model_runtime/model_providers/__base/tokenizers/gpt2_tokenzier.py
@@ -1,11 +1,13 @@
-import logging
+from concurrent.futures import ProcessPoolExecutor
+from os.path import abspath, dirname, join
 from threading import Lock
-from typing import Any
+from typing import Any, cast

-logger = logging.getLogger(__name__)
+from transformers import GPT2Tokenizer as TransformerGPT2Tokenizer  # type: ignore

 _tokenizer: Any = None
 _lock = Lock()
+_executor = ProcessPoolExecutor(max_workers=1)


 class GPT2Tokenizer:
@@ -15,37 +17,22 @@ class GPT2Tokenizer:
        use gpt2 tokenizer to get num tokens
        """
        _tokenizer = GPT2Tokenizer.get_encoder()
-        tokens = _tokenizer.encode(text)
+        tokens = _tokenizer.encode(text, verbose=False)
        return len(tokens)

    @staticmethod
    def get_num_tokens(text: str) -> int:
-        # Because this process needs more cpu resource, we turn this back before we find a better way to handle it.
-        #
-        # future = _executor.submit(GPT2Tokenizer._get_num_tokens_by_gpt2, text)
-        # result = future.result()
-        # return cast(int, result)
-        return GPT2Tokenizer._get_num_tokens_by_gpt2(text)
+        future = _executor.submit(GPT2Tokenizer._get_num_tokens_by_gpt2, text)
+        result = future.result()
+        return cast(int, result)

    @staticmethod
    def get_encoder() -> Any:
        global _tokenizer, _lock
        with _lock:
            if _tokenizer is None:
-                # Try to use tiktoken to get the tokenizer because it is faster
-                #
-                try:
-                    import tiktoken
-
-                    _tokenizer = tiktoken.get_encoding("gpt2")
-                except Exception:
-                    from os.path import abspath, dirname, join
-
-                    from transformers import GPT2Tokenizer as TransformerGPT2Tokenizer  # type: ignore
-
-                    base_path = abspath(__file__)
-                    gpt2_tokenizer_path = join(dirname(base_path), "gpt2")
-                    _tokenizer = TransformerGPT2Tokenizer.from_pretrained(gpt2_tokenizer_path)
-                    logger.info("Fallback to Transformers' GPT-2 tokenizer from tiktoken")
+                base_path = abspath(__file__)
+                gpt2_tokenizer_path = join(dirname(base_path), "gpt2")
+                _tokenizer = TransformerGPT2Tokenizer.from_pretrained(gpt2_tokenizer_path)

            return _tokenizer
--- a/api/core/model_runtime/model_providers/_position.yaml
+++ b/api/core/model_runtime/model_providers/_position.yaml
@@ -1,5 +1,4 @@
 - openai
- deepseek
 - anthropic
 - azure_openai
 - google
@@ -33,6 +32,7 @@
 - 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
@@ -51,40 +51,6 @@ 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, Sequence
+from collections.abc import Generator
 from typing import Any, Optional, Union

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

        if not self.client:
-            endpoint = str(credentials.get("endpoint"))
-            api_key = str(credentials.get("api_key"))
+            endpoint = credentials.get("endpoint")
+            api_key = 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]
@@ -95,7 +94,6 @@ class AzureAIStudioLargeLanguageModel(LargeLanguageModel):
            "temperature": model_parameters.get("temperature", 0),
            "top_p": model_parameters.get("top_p", 1),
            "stream": stream,
-            "model": model,
        }

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

@@ -335,10 +327,7 @@ class AzureAIStudioLargeLanguageModel(LargeLanguageModel):
            fetch_from=FetchFrom.CUSTOMIZABLE_MODEL,
            model_type=ModelType.LLM,
            features=[],
-            model_properties={
-                ModelPropertyKey.CONTEXT_SIZE: int(credentials.get("context_size", "4096")),
-                ModelPropertyKey.MODE: credentials.get("mode", LLMMode.CHAT),
-            },
+            model_properties={},
            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
@@ -53,9 +53,6 @@ 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
@@ -138,18 +135,6 @@ 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/azure_openai/llm/llm.py
+++ b/api/core/model_runtime/model_providers/azure_openai/llm/llm.py
@@ -108,7 +108,7 @@ class AzureOpenAILargeLanguageModel(_CommonAzureOpenAI, LargeLanguageModel):
        ai_model_entity = self._get_ai_model_entity(base_model_name=base_model_name, model=model)

        if not ai_model_entity:
-            raise CredentialsValidateFailedError(f"Base Model Name {credentials['base_model_name']} is invalid")
+            raise CredentialsValidateFailedError(f'Base Model Name {credentials["base_model_name"]} is invalid')

        try:
            client = AzureOpenAI(**self._to_credential_kwargs(credentials))
--- a/api/core/model_runtime/model_providers/azure_openai/text_embedding/text_embedding.py
+++ b/api/core/model_runtime/model_providers/azure_openai/text_embedding/text_embedding.py
@@ -130,7 +130,7 @@ class AzureOpenAITextEmbeddingModel(_CommonAzureOpenAI, TextEmbeddingModel):
            raise CredentialsValidateFailedError("Base Model Name is required")

        if not self._get_ai_model_entity(credentials["base_model_name"], model):
-            raise CredentialsValidateFailedError(f"Base Model Name {credentials['base_model_name']} is invalid")
+            raise CredentialsValidateFailedError(f'Base Model Name {credentials["base_model_name"]} is invalid')

        try:
            credentials_kwargs = self._to_credential_kwargs(credentials)
--- a/api/core/model_runtime/model_providers/bedrock/bedrock.yaml
+++ b/api/core/model_runtime/model_providers/bedrock/bedrock.yaml
@@ -44,7 +44,6 @@ 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:
@@ -52,86 +51,62 @@ 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 (俄亥俄)
-            ja_JP: 米国 (オハイオ)
+            zh_Hans: 美国东部 (弗吉尼亚北部)
        - 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
@@ -13,7 +13,6 @@ 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
@@ -22,7 +21,6 @@ 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/bedrock/llm/eu.anthropic.claude-3.7-sonnet-v1.yaml
+++ b/api/core/model_runtime/model_providers/bedrock/llm/eu.anthropic.claude-3.7-sonnet-v1.yaml
@@ -1,115 +0,0 @@
-model: us.anthropic.claude-3-7-sonnet-20250219-v1:0
-label:
-  en_US: Claude 3.7 Sonnet(US.Cross Region Inference)
-icon: icon_s_en.svg
-model_type: llm
-features:
-  - agent-thought
-  - vision
-  - tool-call
-  - stream-tool-call
-model_properties:
-  mode: chat
-  context_size: 200000
-# docs: https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-anthropic-claude-messages.html
-parameter_rules:
-  - name: enable_cache
-    label:
-      zh_Hans: 启用提示缓存
-      en_US: Enable Prompt Cache
-    type: boolean
-    required: false
-    default: true
-    help:
-      zh_Hans: 启用提示缓存可以提高性能并降低成本。Claude 3.7 Sonnet支持在system、messages和tools字段中使用缓存检查点。
-      en_US: Enable prompt caching to improve performance and reduce costs. Claude 3.7 Sonnet supports cache checkpoints in system, messages, and tools fields.
-  - name: reasoning_type
-    label:
-      zh_Hans: 推理配置
-      en_US: Reasoning Type
-    type: boolean
-    required: false
-    default: false
-    placeholder:
-      zh_Hans: 设置推理配置
-      en_US: Set reasoning configuration
-    help:
-      zh_Hans: 控制模型的推理能力。启用时，temperature将固定为1且top_p将被禁用。
-      en_US: Controls the model's reasoning capability. When enabled, temperature will be fixed to 1 and top_p will be disabled.
-  - name: reasoning_budget
-    show_on:
-      - variable: reasoning_type
-        value: true
-    label:
-      zh_Hans: 推理预算
-      en_US: Reasoning Budget
-    type: int
-    default: 1024
-    min: 0
-    max: 128000
-    help:
-      zh_Hans: 推理的预算限制（最小1024），必须小于max_tokens。仅在推理类型为enabled时可用。
-      en_US: Budget limit for reasoning (minimum 1024), must be less than max_tokens. Only available when reasoning type is enabled.
-
-  - name: max_tokens
-    use_template: max_tokens
-    required: true
-    label:
-      zh_Hans: 最大token数
-      en_US: Max Tokens
-    type: int
-    default: 8192
-    min: 1
-    max: 128000
-    help:
-      zh_Hans: 停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。
-      en_US: The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.
-  - name: temperature
-    use_template: temperature
-    required: false
-    label:
-      zh_Hans: 模型温度
-      en_US: Model Temperature
-    type: float
-    default: 1
-    min: 0.0
-    max: 1.0
-    help:
-      zh_Hans: 生成内容的随机性。当推理功能启用时，该值将被固定为1。
-      en_US: The amount of randomness injected into the response. When reasoning is enabled, this value will be fixed to 1.
-  - name: top_p
-    show_on:
-      - variable: reasoning_type
-        value: disabled
-    use_template: top_p
-    label:
-      zh_Hans: Top P
-      en_US: Top P
-    required: false
-    type: float
-    default: 0.999
-    min: 0.000
-    max: 1.000
-    help:
-      zh_Hans: 在核采样中的概率阈值。当推理功能启用时，该参数将被禁用。
-      en_US: The probability threshold in nucleus sampling. When reasoning is enabled, this parameter will be disabled.
-  - name: top_k
-    label:
-      zh_Hans: 取样数量
-      en_US: Top k
-    required: false
-    type: int
-    default: 0
-    min: 0
-    # tip docs from aws has error, max value is 500
-    max: 500
-    help:
-      zh_Hans: 对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。
-      en_US: Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.
-  - name: response_format
-    use_template: response_format
-pricing:
-  input: '0.003'
-  output: '0.015'
-  unit: '0.001'
-  currency: USD
--- a/api/core/model_runtime/model_providers/bedrock/llm/llm.py
+++ b/api/core/model_runtime/model_providers/bedrock/llm/llm.py
@@ -58,7 +58,6 @@ class BedrockLargeLanguageModel(LargeLanguageModel):
    # TODO There is invoke issue: context limit on Cohere Model, will add them after fixed.
    CONVERSE_API_ENABLED_MODEL_INFO = [
        {"prefix": "anthropic.claude-v2", "support_system_prompts": True, "support_tool_use": False},
-        {"prefix": "us.deepseek", "support_system_prompts": True, "support_tool_use": False},
        {"prefix": "anthropic.claude-v1", "support_system_prompts": True, "support_tool_use": False},
        {"prefix": "us.anthropic.claude-3", "support_system_prompts": True, "support_tool_use": True},
        {"prefix": "eu.anthropic.claude-3", "support_system_prompts": True, "support_tool_use": True},
--- a/api/core/model_runtime/model_providers/bedrock/llm/us.deepseek-r1.yaml
+++ b/api/core/model_runtime/model_providers/bedrock/llm/us.deepseek-r1.yaml
@@ -1,63 +0,0 @@
-model: us.deepseek.r1-v1:0
-label:
-  en_US: DeepSeek-R1(US.Cross Region Inference)
-icon: icon_s_en.svg
-model_type: llm
-features:
-  - agent-thought
-  - vision
-  - tool-call
-  - stream-tool-call
-model_properties:
-  mode: chat
-  context_size: 32768
-parameter_rules:
-  - name: max_tokens
-    use_template: max_tokens
-    required: true
-    label:
-      zh_Hans: 最大token数
-      en_US: Max Tokens
-    type: int
-    default: 8192
-    min: 1
-    max: 128000
-    help:
-      zh_Hans: 停止前生成的最大令牌数。
-      en_US: The maximum number of tokens to generate before stopping.
-  - name: temperature
-    use_template: temperature
-    required: false
-    label:
-      zh_Hans: 模型温度
-      en_US: Model Temperature
-    type: float
-    default: 1
-    min: 0.0
-    max: 1.0
-    help:
-      zh_Hans: 生成内容的随机性。当推理功能启用时，该值将被固定为1。
-      en_US: The amount of randomness injected into the response. When reasoning is enabled, this value will be fixed to 1.
-  - name: top_p
-    show_on:
-      - variable: reasoning_type
-        value: disabled
-    use_template: top_p
-    label:
-      zh_Hans: Top P
-      en_US: Top P
-    required: false
-    type: float
-    default: 0.999
-    min: 0.000
-    max: 1.000
-    help:
-      zh_Hans: 在核采样中的概率阈值。当推理功能启用时，该参数将被禁用。
-      en_US: The probability threshold in nucleus sampling. When reasoning is enabled, this parameter will be disabled.
-  - name: response_format
-    use_template: response_format
-pricing:
-  input: '0.001'
-  output: '0.005'
-  unit: '0.001'
-  currency: USD
--- a/api/core/model_runtime/model_providers/bedrock/rerank/rerank.py
+++ b/api/core/model_runtime/model_providers/bedrock/rerank/rerank.py
@@ -70,7 +70,7 @@ class BedrockRerankModel(RerankModel):
        rerankingConfiguration = {
            "type": "BEDROCK_RERANKING_MODEL",
            "bedrockRerankingConfiguration": {
-                "numberOfResults": min(top_n, len(text_sources)),
+                "numberOfResults": top_n,
                "modelConfiguration": {
                    "modelArn": model_package_arn,
                },
--- a/api/core/model_runtime/model_providers/cohere/llm/llm.py
+++ b/api/core/model_runtime/model_providers/cohere/llm/llm.py
@@ -677,17 +677,16 @@ class CohereLargeLanguageModel(LargeLanguageModel):

        :return: model schema
        """
-        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
+        # get model schema
+        models = self.predefined_models()
+        model_map = {model.model: model for model in models}

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

        base_model_schema = cast(AIModelEntity, base_model_schema)

--- a/api/core/model_runtime/model_providers/deepseek/llm/_position.yaml
+++ b/api/core/model_runtime/model_providers/deepseek/llm/_position.yaml
@@ -1,3 +1,2 @@
 - deepseek-chat
 - deepseek-coder
- deepseek-reasoner
--- a/api/core/model_runtime/model_providers/deepseek/llm/deepseek-chat.yaml
+++ b/api/core/model_runtime/model_providers/deepseek/llm/deepseek-chat.yaml
@@ -10,7 +10,7 @@ features:
  - stream-tool-call
 model_properties:
  mode: chat
-  context_size: 64000
+  context_size: 128000
 parameter_rules:
  - name: temperature
    use_template: temperature
--- a/api/core/model_runtime/model_providers/deepseek/llm/deepseek-coder.yaml
+++ b/api/core/model_runtime/model_providers/deepseek/llm/deepseek-coder.yaml
@@ -10,7 +10,7 @@ features:
  - stream-tool-call
 model_properties:
  mode: chat
-  context_size: 64000
+  context_size: 128000
 parameter_rules:
  - name: temperature
    use_template: temperature
--- a/api/core/model_runtime/model_providers/deepseek/llm/deepseek-reasoner.yaml
+++ b/api/core/model_runtime/model_providers/deepseek/llm/deepseek-reasoner.yaml
@@ -1,21 +0,0 @@
-model: deepseek-reasoner
-label:
-  zh_Hans: deepseek-reasoner
-  en_US: deepseek-reasoner
-model_type: llm
-features:
-  - agent-thought
-model_properties:
-  mode: chat
-  context_size: 64000
-parameter_rules:
-  - name: max_tokens
-    use_template: max_tokens
-    min: 1
-    max: 8192
-    default: 4096
-pricing:
-  input: "4"
-  output: "16"
-  unit: "0.000001"
-  currency: RMB
--- a/api/core/model_runtime/model_providers/deepseek/llm/llm.py
+++ b/api/core/model_runtime/model_providers/deepseek/llm/llm.py
@@ -24,6 +24,9 @@ class DeepseekLargeLanguageModel(OAIAPICompatLargeLanguageModel):
        user: Optional[str] = None,
    ) -> Union[LLMResult, Generator]:
        self._add_custom_parameters(credentials)
+        # {"response_format": "xx"} need convert to {"response_format": {"type": "xx"}}
+        if "response_format" in model_parameters:
+            model_parameters["response_format"] = {"type": model_parameters.get("response_format")}
        return super()._invoke(model, credentials, prompt_messages, model_parameters, tools, stop, stream)

    def validate_credentials(self, model: str, credentials: dict) -> None:
--- a/api/core/model_runtime/model_providers/google/google.py
+++ b/api/core/model_runtime/model_providers/google/google.py
@@ -19,8 +19,8 @@ class GoogleProvider(ModelProvider):
        try:
            model_instance = self.get_model_instance(ModelType.LLM)

-            # Use `gemini-2.0-flash` model for validate,
-            model_instance.validate_credentials(model="gemini-2.0-flash", credentials=credentials)
+            # Use `gemini-pro` model for validate,
+            model_instance.validate_credentials(model="gemini-pro", credentials=credentials)
        except CredentialsValidateFailedError as ex:
            raise ex
        except Exception as ex:
--- a/api/core/model_runtime/model_providers/google/llm/_position.yaml
+++ b/api/core/model_runtime/model_providers/google/llm/_position.yaml
@@ -1,8 +1,5 @@
- gemini-2.0-flash-001
 - gemini-2.0-flash-exp
- 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
 - gemini-1.5-pro-latest
 - gemini-1.5-pro-001
@@ -19,3 +16,5 @@
 - gemini-exp-1206
 - gemini-exp-1121
 - gemini-exp-1114
+- gemini-pro
+- gemini-pro-vision
--- a/api/core/model_runtime/model_providers/google/llm/gemini-2.0-flash-001.yml
+++ b/api/core/model_runtime/model_providers/google/llm/gemini-2.0-flash-001.yml
@@ -1,41 +0,0 @@
-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-thinking-exp-01-21.yaml
+++ b/api/core/model_runtime/model_providers/google/llm/gemini-2.0-flash-thinking-exp-01-21.yaml
@@ -1,39 +0,0 @@
-model: gemini-2.0-flash-thinking-exp-01-21
-label:
-  en_US: Gemini 2.0 Flash Thinking Exp 01-21
-model_type: llm
-features:
-  - agent-thought
-  - vision
-  - document
-  - video
-  - audio
-model_properties:
-  mode: chat
-  context_size: 32767
-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
@@ -1,41 +0,0 @@
-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/vertex_ai/llm/gemini-exp-1114.yaml
+++ b/api/core/model_runtime/model_providers/vertex_ai/llm/gemini-exp-1114.yaml
@@ -1,18 +1,12 @@
-model: gemini-exp-1114
+model: gemini-pro-vision
 label:
-  en_US: Gemini exp 1114
+  en_US: Gemini Pro Vision
 model_type: llm
 features:
-  - agent-thought
  - vision
-  - tool-call
-  - stream-tool-call
-  - document
-  - video
-  - audio
 model_properties:
  mode: chat
-  context_size: 32767
+  context_size: 12288
 parameter_rules:
  - name: temperature
    use_template: temperature
@@ -27,15 +21,15 @@ parameter_rules:
      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
+  - name: max_tokens_to_sample
    use_template: max_tokens
-    default: 8192
+    required: true
+    default: 4096
    min: 1
-    max: 8192
-  - name: json_schema
-    use_template: json_schema
+    max: 4096
 pricing:
  input: '0.00'
  output: '0.00'
  unit: '0.000001'
  currency: USD
+deprecated: true
--- a/api/core/model_runtime/model_providers/vertex_ai/llm/gemini-exp-1121.yaml
+++ b/api/core/model_runtime/model_providers/vertex_ai/llm/gemini-exp-1121.yaml
@@ -1,18 +1,14 @@
-model: gemini-exp-1121
+model: gemini-pro
 label:
-  en_US: Gemini exp 1121
+  en_US: Gemini Pro
 model_type: llm
 features:
  - agent-thought
-  - vision
  - tool-call
  - stream-tool-call
-  - document
-  - video
-  - audio
 model_properties:
  mode: chat
-  context_size: 32767
+  context_size: 30720
 parameter_rules:
  - name: temperature
    use_template: temperature
@@ -27,15 +23,17 @@ parameter_rules:
      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
+  - name: max_tokens_to_sample
    use_template: max_tokens
-    default: 8192
+    required: true
+    default: 2048
    min: 1
-    max: 8192
-  - name: json_schema
-    use_template: json_schema
+    max: 2048
+  - name: response_format
+    use_template: response_format
 pricing:
  input: '0.00'
  output: '0.00'
  unit: '0.000001'
  currency: USD
+deprecated: true
--- a/api/core/model_runtime/model_providers/groq/llm/_position.yaml
+++ b/api/core/model_runtime/model_providers/groq/llm/_position.yaml
@@ -1,4 +1,3 @@
- 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
@@ -1,36 +0,0 @@
-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/huggingface_hub/text_embedding/text_embedding.py
+++ b/api/core/model_runtime/model_providers/huggingface_hub/text_embedding/text_embedding.py
@@ -162,9 +162,9 @@ class HuggingfaceHubTextEmbeddingModel(_CommonHuggingfaceHub, TextEmbeddingModel
    @staticmethod
    def _check_endpoint_url_model_repository_name(credentials: dict, model_name: str):
        try:
-            url = f"{HUGGINGFACE_ENDPOINT_API}{credentials['huggingface_namespace']}"
+            url = f'{HUGGINGFACE_ENDPOINT_API}{credentials["huggingface_namespace"]}'
            headers = {
-                "Authorization": f"Bearer {credentials['huggingfacehub_api_token']}",
+                "Authorization": f'Bearer {credentials["huggingfacehub_api_token"]}',
                "Content-Type": "application/json",
            }

--- a/api/core/model_runtime/model_providers/minimax/llm/llm.py
+++ b/api/core/model_runtime/model_providers/minimax/llm/llm.py
@@ -34,7 +34,6 @@ from core.model_runtime.model_providers.minimax.llm.types import MinimaxMessage

 class MinimaxLargeLanguageModel(LargeLanguageModel):
    model_apis = {
-        "minimax-text-01": MinimaxChatCompletionPro,
        "abab7-chat-preview": MinimaxChatCompletionPro,
        "abab6.5t-chat": MinimaxChatCompletionPro,
        "abab6.5s-chat": MinimaxChatCompletionPro,
--- a/api/core/model_runtime/model_providers/minimax/llm/minimax-text-01.yaml
+++ b/api/core/model_runtime/model_providers/minimax/llm/minimax-text-01.yaml
@@ -1,46 +0,0 @@
-model: minimax-text-01
-label:
-  en_US: Minimax-Text-01
-model_type: llm
-features:
-  - agent-thought
-  - tool-call
-  - stream-tool-call
-model_properties:
-  mode: chat
-  context_size: 1000192
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-    min: 0.01
-    max: 1
-    default: 0.1
-  - name: top_p
-    use_template: top_p
-    min: 0.01
-    max: 1
-    default: 0.95
-  - name: max_tokens
-    use_template: max_tokens
-    required: true
-    default: 2048
-    min: 1
-    max: 1000192
-  - name: mask_sensitive_info
-    type: boolean
-    default: true
-    label:
-      zh_Hans: 隐私保护
-      en_US: Moderate
-    help:
-      zh_Hans: 对输出中易涉及隐私问题的文本信息进行打码，目前包括但不限于邮箱、域名、链接、证件号、家庭住址等，默认true，即开启打码
-      en_US: Mask the sensitive info of the generated content, such as email/domain/link/address/phone/id..
-  - name: presence_penalty
-    use_template: presence_penalty
-  - name: frequency_penalty
-    use_template: frequency_penalty
-pricing:
-  input: '0.001'
-  output: '0.008'
-  unit: '0.001'
-  currency: RMB
--- a/api/core/model_runtime/model_providers/moonshot/llm/llm.py
+++ b/api/core/model_runtime/model_providers/moonshot/llm/llm.py
@@ -44,6 +44,9 @@ class MoonshotLargeLanguageModel(OAIAPICompatLargeLanguageModel):
        self._add_custom_parameters(credentials)
        self._add_function_call(model, credentials)
        user = user[:32] if user else None
+        # {"response_format": "json_object"} need convert to {"response_format": {"type": "json_object"}}
+        if "response_format" in model_parameters:
+            model_parameters["response_format"] = {"type": model_parameters.get("response_format")}
        return super()._invoke(model, credentials, prompt_messages, model_parameters, tools, stop, stream, user)

    def validate_credentials(self, model: str, credentials: dict) -> None:
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
alexcodelf	df82bccfdf	feat: support speech2text and tts for gpustack	2025-01-07 09:19:39 +08:00
alexcodelf	5ba875f96b	fix: gpustack llm and text_embedding model url path wrong after edited	2025-01-07 09:19:39 +08:00