jandres/GenAIExamples
1
0
Fork 0
Code Issues Pull Requests Actions 3 Packages Projects Releases Wiki Activity

Refine README for chat history, feedback management and prompt registry microservice (#727)

Browse Source 
* [chat_history]: Refine README documentation

Signed-off-by: Yeoh, Hoong Tee <hoong.tee.yeoh@intel.com>

* [feedback_management]: Refine README documentation

Signed-off-by: Yeoh, Hoong Tee <hoong.tee.yeoh@intel.com>

* [prompt_registry]: Refine README documentation

Signed-off-by: Yeoh, Hoong Tee <hoong.tee.yeoh@intel.com>

* Fix readme typo

Signed-off-by: Yeoh, Hoong Tee <hoong.tee.yeoh@intel.com>

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

---------

Signed-off-by: Yeoh, Hoong Tee <hoong.tee.yeoh@intel.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
This commit is contained in:
Hoong Tee, Yeoh
2024-09-24 21:49:32 +08:00
committed by GitHub
parent 1f57d070f0
commit 9d566be203
7 changed files with 317 additions and 244 deletions
Download Patch File Download Diff File Expand all files Collapse all files

26
comps/chathistory/README.md Normal file
View File

@@ -0,0 +1,26 @@
# 📝 Chat History Microservice
The Chat History Microservice is a scalable solution for storing, retrieving and managing chat conversations using various type of databases. This microservice is designed to seamlessly integrate with OPEA chat applications, enabling data persistence and efficient management of chat histories.
It can be integrated into application by making HTTP requests to the provided API endpoints as shown in the flow diagram below.
![Flow Chart](./assets/img/chathistory_flow.png)
---
## 🛠️ Features
- **Store Chat Conversations**: Save chat messages user information, and metadata associated with each conversation.
- **Retrieve Chat Histories**: Fetch chat histories for a specific user or retrieve a particular conversation by its unique identifier.
- **Update Chat Conversations**: Modify existing chat conversations by adding new messages or updating existing ones.
- **Delete Chat Conversations**: Remove chat conversations record from database.
---
## ⚙️ Implementation
The Chat History microservice able to support various database backends for storing the chat conversations.
### Chat History with MongoDB
For more detail, please refer to this [README](./mongo/README.md)

0
comps/chathistory/mongo/assets/img/chathistory_flow.png → comps/chathistory/assets/img/chathistory_flow.png
View File

Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 87 KiB

After

Width:  |  Height:  |  Size: 87 KiB

134
comps/chathistory/mongo/README.md
View File

@@ -1,10 +1,8 @@
# Chat History Microservice
# 📝 Chat History Microservice with MongoDB
The Chat History Microservice allows you to store, retrieve and manage chat conversations with a MongoDB database. This microservice can be used for data persistence in OPEA chat applications, enabling you to save and access chat histories.
This README provides setup guides and all the necessary information about the Chat History microservice with MongoDB database.
It can be integrated into any application by making HTTP requests to the provided API endpoints as shown in the flow diagram below.
![Flow Chart](./assets/img/chathistory_flow.png)
---
## Setup Environment Variables
@@ -17,6 +15,8 @@ export DB_NAME=${DB_NAME}
export COLLECTION_NAME=${COLLECTION_NAME}
```
---
## 🚀Start Microservice with Docker
### Build Docker Image
@@ -28,78 +28,82 @@ docker build -t opea/chathistory-mongo-server:latest --build-arg https_proxy=$ht
### Run Docker with CLI
- Run mongoDB image
- Run MongoDB image container
```bash
docker run -d -p 27017:27017 --name=mongo mongo:latest
```
```bash
docker run -d -p 27017:27017 --name=mongo mongo:latest
```
- Run the chathistory Service
- Run the Chat History microservice
```bash
docker run -d --name="chathistory-mongo-server" -p 6013:6013 -p 6012:6012 -p 6014:6014 -e http_proxy=$http_proxy -e https_proxy=$https_proxy -e no_proxy=$no_proxy -e MONGO_HOST=${MONGO_HOST} -e MONGO_PORT=${MONGO_PORT} -e DB_NAME=${DB_NAME} -e COLLECTION_NAME=${COLLECTION_NAME} opea/chathistory-mongo-server:latest
```
```bash
docker run -d --name="chathistory-mongo-server" -p 6013:6013 -p 6012:6012 -p 6014:6014 -e http_proxy=$http_proxy -e https_proxy=$https_proxy -e no_proxy=$no_proxy -e MONGO_HOST=${MONGO_HOST} -e MONGO_PORT=${MONGO_PORT} -e DB_NAME=${DB_NAME} -e COLLECTION_NAME=$ {COLLECTION_NAME} opea/chathistory-mongo-server:latest
```
## Invoke Microservice
---
Once chathistory service is up and running, users can update the database by using the below API endpoint. The API returns a unique UUID for the saved conversation.
## ✅ Invoke Microservice
```bash
curl -X 'POST' \
http://${host_ip}:6012/v1/chathistory/create \
-H 'accept: application/json' \
-H 'Content-Type: application/json' \
-d '{
"data": {
"messages": "test Messages", "user": "test"
}
}'
```
The Chat History microservice exposes the following API endpoints:
- Create new chat conversation
```bash
curl -X 'POST' \
http://${host_ip}:6012/v1/chathistory/create \
-H 'accept: application/json' \
-H 'Content-Type: application/json' \
-d '{
"data": {
"messages": "test Messages", "user": "test"
}
}'
```
- Get all the Conversations for a user
```bash
curl -X 'POST' \
http://${host_ip}:6012/v1/chathistory/get \
-H 'accept: application/json' \
-H 'Content-Type: application/json' \
-d '{
"user": "test"}'
```
```bash
curl -X 'POST' \
http://${host_ip}:6012/v1/chathistory/get \
-H 'accept: application/json' \
-H 'Content-Type: application/json' \
-d '{
"user": "test"}'
```
- Get specific conversation by specifying the id.
- Get a specific conversation by id.
```bash
curl -X 'POST' \
http://${host_ip}:6012/v1/chathistory/get \
-H 'accept: application/json' \
-H 'Content-Type: application/json' \
-d '{
"user": "test", "id":"668620173180b591e1e0cd74"}'
```
```bash
curl -X 'POST' \
http://${host_ip}:6012/v1/chathistory/get \
-H 'accept: application/json' \
-H 'Content-Type: application/json' \
-d '{
"user": "test", "id":"668620173180b591e1e0cd74"}'
```
- Update the conversation by specifying the id.
- Update the conversation by id.
```bash
curl -X 'POST' \
http://${host_ip}:6012/v1/chathistory/create \
-H 'accept: application/json' \
-H 'Content-Type: application/json' \
-d '{
"data": {
"messages": "test Messages Update", "user": "test"
},
"id":"668620173180b591e1e0cd74"
}'
```
```bash
curl -X 'POST' \
http://${host_ip}:6012/v1/chathistory/create \
-H 'accept: application/json' \
-H 'Content-Type: application/json' \
-d '{
"data": {
"messages": "test Messages Update", "user": "test"
},
"id":"668620173180b591e1e0cd74"
}'
```
- Delete a stored conversation by specifying the id.
- Delete a stored conversation.
```bash
curl -X 'POST' \
http://${host_ip}:6012/v1/chathistory/delete \
-H 'accept: application/json' \
-H 'Content-Type: application/json' \
-d '{
"user": "test", "id":"668620173180b591e1e0cd74"}'
```
```bash
curl -X 'POST' \
http://${host_ip}:6012/v1/chathistory/delete \
-H 'accept: application/json' \
-H 'Content-Type: application/json' \
-d '{
"user": "test", "id":"668620173180b591e1e0cd74"}'
```

22
comps/feedback_management/README.md Normal file
View File

@@ -0,0 +1,22 @@
# 🗨 Feedback Management Microservice
The Feedback Management microservice facilitates the storage and retrieval of users'feedback data by establishing a connection with the databases. This microservice is designed to seamlessly integrate with OPEA applications, enabling data persistence and efficient management of feedback data.
---
## 🛠️ Features
- **Store Feedback**: Save feedback data from user into database.
- **Retrieve Feedback**: Fetch feedback data from database based on user or id.
- **Update Feedback**: Update feedback data info in the database based on id.
- **Delete Feedback**: Remove feedback record from database.
---
## ⚙️ Implementation
The Feedback Management microservice able to support various database backends for storing the feedback data.
### Feedback Management with MongoDB
For more detail, please refer to this [README](./mongo/README.md)

230
comps/feedback_management/mongo/README.md
View File

@@ -1,6 +1,8 @@
# Feedback Management Microservice
# 🗨 Feedback Management Microservice with MongoDB
The Feedback Management microservice facilitates the storage and retrieval of users'feedback data by establishing a connection with the database.
This README provides setup guides and all the necessary information about the Feedback Management microservice with MongoDB database.
---
## Setup Environment Variables
@@ -13,13 +15,7 @@ export DB_NAME=${DB_NAME}
export COLLECTION_NAME=${COLLECTION_NAME}
```
## Start Feedback Management microservice for MongoDB with Python script
Start document preparation microservice for Milvus with below command.
```bash
python feedback.py
```
---
## 🚀Start Microservice with Docker
@@ -32,126 +28,130 @@ docker build -t opea/feedbackmanagement-mongo-server:latest --build-arg https_pr
### Run Docker with CLI
1. Run mongoDB image
- Run MongoDB image container
```bash
docker run -d -p 27017:27017 --name=mongo mongo:latest
```
```bash
docker run -d -p 27017:27017 --name=mongo mongo:latest
```
2. Run Feedback Management service
- Run Feedback Management microservice
```bash
docker run -d --name="feedbackmanagement-mongo-server" -p 6016:6016 -e http_proxy=$http_proxy -e https_proxy=$https_proxy -e no_proxy=$no_proxy -e MONGO_HOST=${MONGO_HOST} -e MONGO_PORT=${MONGO_PORT} -e DB_NAME=${DB_NAME} -e COLLECTION_NAME=${COLLECTION_NAME} opea/feedbackmanagement-mongo-server:latest
```
```bash
docker run -d --name="feedbackmanagement-mongo-server" -p 6016:6016 -e http_proxy=$http_proxy -e https_proxy=$https_proxy -e no_proxy=$no_proxy -e MONGO_HOST=${MONGO_HOST} -e MONGO_PORT=${MONGO_PORT} -e DB_NAME=${DB_NAME} -e COLLECTION_NAME=${COLLECTION_NAME} opea/feedbackmanagement-mongo-server:latest
```
### Invoke Microservice
---
Once feedback management service is up and running, user can access the database by using API endpoint below. Each API serves different purpose and return appropriate response.
### ✅ Invoke Microservice
- Save feedback data into database.
The Feedback Management microservice exposes the following API endpoints:
```bash
curl -X 'POST' \
http://{host_ip}:6016/v1/feedback/create \
-H 'accept: application/json' \
-H 'Content-Type: application/json' \
-d '{
"chat_id": "66445d4f71c7eff23d44f78d",
"chat_data": {
"user": "test",
"messages": [
{
"role": "system",
"content": "You are helpful assistant"
},
{
"role": "user",
"content": "hi",
"time": "1724915247"
},
{
"role": "assistant",
"content": "Hi, may I help you?",
"time": "1724915249"
}
]
},
"feedback_data": {
"comment": "Moderate",
"rating": 3,
"is_thumbs_up": true
}}'
- Save feedback data
```bash
curl -X 'POST' \
http://{host_ip}:6016/v1/feedback/create \
-H 'accept: application/json' \
-H 'Content-Type: application/json' \
-d '{
"chat_id": "66445d4f71c7eff23d44f78d",
"chat_data": {
"user": "test",
"messages": [
{
"role": "system",
"content": "You are helpful assistant"
},
{
"role": "user",
"content": "hi",
"time": "1724915247"
},
{
"role": "assistant",
"content": "Hi, may I help you?",
"time": "1724915249"
}
]
},
"feedback_data": {
"comment": "Moderate",
"rating": 3,
"is_thumbs_up": true
}}'
# Take note that chat_id here would be the id get from chathistory_mongo service
# If you do not wish to maintain chat history via chathistory_mongo service, you may generate some random uuid for it or just leave it empty.
```
# Take note that chat_id here would be the id get from chathistory_mongo service
# If you do not wish to maintain chat history via chathistory_mongo service, you may generate some random uuid for it or just leave it empty.
```
- Update the feedback data of specified feedback_id
- Update feedback data by feedback_id
```bash
curl -X 'POST' \
http://{host_ip}:6016/v1/feedback/create \
-H 'accept: application/json' \
-H 'Content-Type: application/json' \
-d '{
"chat_id": "66445d4f71c7eff23d44f78d",
"chat_data": {
"user": "test",
"messages": [
{
"role": "system",
"content": "You are helpful assistant"
},
{
"role": "user",
"content": "hi",
"time": "1724915247"
},
{
"role": "assistant",
"content": "Hi, may I help you?",
"time": "1724915249"
}
]
},
"feedback_data": {
"comment": "Fair and Moderate answer",
"rating": 2,
"is_thumbs_up": true
},
"feedback_id": "{feedback_id of the data that wanted to update}"}'
```bash
curl -X 'POST' \
http://{host_ip}:6016/v1/feedback/create \
-H 'accept: application/json' \
-H 'Content-Type: application/json' \
-d '{
"chat_id": "66445d4f71c7eff23d44f78d",
"chat_data": {
"user": "test",
"messages": [
{
"role": "system",
"content": "You are helpful assistant"
},
{
"role": "user",
"content": "hi",
"time": "1724915247"
},
{
"role": "assistant",
"content": "Hi, may I help you?",
"time": "1724915249"
}
]
},
"feedback_data": {
"comment": "Fair and Moderate answer",
"rating": 2,
"is_thumbs_up": true
},
"feedback_id": "{feedback_id of the data that wanted to update}"}'
# Just include any feedback_data field value that you wanted to update.
```
# Just include any feedback_data field value that you wanted to update.
```
- Retrieve feedback data from database based on user or feedback_id
- Retrieve feedback data by user
```bash
curl -X 'POST' \
http://{host_ip}:6016/v1/feedback/get \
-H 'accept: application/json' \
-H 'Content-Type: application/json' \
-d '{
"user": "test"}'
```
```bash
curl -X 'POST' \
http://{host_ip}:6016/v1/feedback/get \
-H 'accept: application/json' \
-H 'Content-Type: application/json' \
-d '{
"user": "test"}'
```
```bash
curl -X 'POST' \
http://{host_ip}:6016/v1/feedback/get \
-H 'accept: application/json' \
-H 'Content-Type: application/json' \
-d '{
"user": "test", "feedback_id":"{feedback_id returned from save feedback route above}"}'
```
- Retrieve feedback data by feedback_id
- Delete feedback data from database based on feedback_id provided
```bash
curl -X 'POST' \
http://{host_ip}:6016/v1/feedback/get \
-H 'accept: application/json' \
-H 'Content-Type: application/json' \
-d '{
"user": "test", "feedback_id":"{feedback_id returned from save feedback route above}"}'
```
```bash
curl -X 'POST' \
http://{host_ip}:6016/v1/feedback/delete \
-H 'accept: application/json' \
-H 'Content-Type: application/json' \
-d '{
"user": "test", "feedback_id":"{feedback_id to be deleted}"}'
```
- Delete feedback data by feedback_id
```bash
curl -X 'POST' \
http://{host_ip}:6016/v1/feedback/delete \
-H 'accept: application/json' \
-H 'Content-Type: application/json' \
-d '{
"user": "test", "feedback_id":"{feedback_id to be deleted}"}'
```

21
comps/prompt_registry/README.md Normal file
View File

@@ -0,0 +1,21 @@
# 🧾 Prompt Registry Microservice
The Prompt Registry microservice facilitates the storage and retrieval of users'preferred prompts by establishing a connection with the databases. This microservice is designed to seamlessly integrate with OPEA applications, enabling data persistence and efficient management of user's preferred prompts.
---
## 🛠️ Features
- **Store Prompt**: Save user's preferred prompt into database.
- **Retrieve Prompt**: Fetch prompt from database based on user, id or even a keyword search.
- **Delete Prompt**: Remove prompt from database.
---
## ⚙️ Implementation
The Prompt Registry microservice able to support various database backends for storing the prompts.
### Prompt Registry with MongoDB
For more detail, please refer to this [README](./mongo/README.md)

128
comps/prompt_registry/mongo/README.md
View File

@@ -1,6 +1,8 @@
# Prompt Registry Microservice
# 🧾 Prompt Registry Microservice with MongoDB
The Prompt Registry microservice facilitates the storage and retrieval of users'preferred prompts by establishing a connection with the database.
This README provides setup guides and all the necessary information about the Prompt Registry microservice with MongoDB database.
---
## Setup Environment Variables
@@ -13,13 +15,7 @@ export DB_NAME=${DB_NAME}
export COLLECTION_NAME=${COLLECTION_NAME}
```
## Start Prompt Registry microservice for MongoDB with Python script
Start document preparation microservice for Milvus with below command.
```bash
python prompt.py
```
---
## 🚀Start Microservice with Docker
@@ -32,72 +28,76 @@ docker build -t opea/promptregistry-mongo-server:latest --build-arg https_proxy=
### Run Docker with CLI
1. Run mongoDB image
- Run MongoDB image container
```bash
docker run -d -p 27017:27017 --name=mongo mongo:latest
```
```bash
docker run -d -p 27017:27017 --name=mongo mongo:latest
```
2. Run prompt_registry service
- Run Prompt Registry microservice
```bash
docker run -d --name="promptregistry-mongo-server" -p 6012:6012 -e http_proxy=$http_proxy -e https_proxy=$https_proxy -e no_proxy=$no_proxy -e MONGO_HOST=${MONGO_HOST} -e MONGO_PORT=${MONGO_PORT} -e DB_NAME=${DB_NAME} -e COLLECTION_NAME=${COLLECTION_NAME} opea/promptregistry-mongo-server:latest
```
```bash
docker run -d --name="promptregistry-mongo-server" -p 6012:6012 -e http_proxy=$http_proxy -e https_proxy=$https_proxy -e no_proxy=$no_proxy -e MONGO_HOST=${MONGO_HOST} -e MONGO_PORT=${MONGO_PORT} -e DB_NAME=${DB_NAME} -e COLLECTION_NAME=${COLLECTION_NAME} opea/promptregistry-mongo-server:latest
```
### Invoke Microservice
---
Once prompt_registry service is up and running, users can access the database by using API endpoint below. Each API serves different purpose and return appropriate response.
### ✅ Invoke Microservice
- Save prompt into database.
The Prompt Registry microservice exposes the following API endpoints:
```bash
curl -X 'POST' \
http://{host_ip}:6012/v1/prompt/create \
-H 'accept: application/json' \
-H 'Content-Type: application/json' \
-d '{
"prompt_text": "test prompt", "user": "test"
}'
```
- Save prompt
- Retrieve prompt from database based on user or prompt_id
```bash
curl -X 'POST' \
http://{host_ip}:6012/v1/prompt/create \
-H 'accept: application/json' \
-H 'Content-Type: application/json' \
-d '{
"prompt_text": "test prompt", "user": "test"
}'
```
```bash
curl -X 'POST' \
http://{host_ip}:6012/v1/prompt/get \
-H 'accept: application/json' \
-H 'Content-Type: application/json' \
-d '{
"user": "test"}'
```
- Retrieve prompt from database by user
```bash
curl -X 'POST' \
http://{host_ip}:6012/v1/prompt/get \
-H 'accept: application/json' \
-H 'Content-Type: application/json' \
-d '{
"user": "test", "prompt_id":"{prompt_id returned from save prompt route above}"}'
```
```bash
curl -X 'POST' \
http://{host_ip}:6012/v1/prompt/get \
-H 'accept: application/json' \
-H 'Content-Type: application/json' \
-d '{
"user": "test"}'
```
- Retrieve relevant prompt based on provided keyword
- Retrieve prompt from database by prompt_id
```bash
curl -X 'POST' \
http://{host_ip}:6012/v1/prompt/get \
-H 'accept: application/json' \
-H 'Content-Type: application/json' \
-d '{
"user": "test", "prompt_text": "{keyword to search}"}'
```
```bash
curl -X 'POST' \
http://{host_ip}:6012/v1/prompt/get \
-H 'accept: application/json' \
-H 'Content-Type: application/json' \
-d '{
"user": "test", "prompt_id":"{prompt_id returned from save prompt route above}"}'
```
- Delete prompt from database based on prompt_id provided
- Retrieve relevant prompt by keyword
```bash
curl -X 'POST' \
http://{host_ip}:6012/v1/prompt/delete \
-H 'accept: application/json' \
-H 'Content-Type: application/json' \
-d '{
"user": "test", "prompt_id":"{prompt_id to be deleted}"}'
```
```bash
curl -X 'POST' \
http://{host_ip}:6012/v1/prompt/get \
-H 'accept: application/json' \
-H 'Content-Type: application/json' \
-d '{
"user": "test", "prompt_text": "{keyword to search}"}'
```
- Delete prompt by prompt_id
```bash
curl -X 'POST' \
http://{host_ip}:6012/v1/prompt/delete \
-H 'accept: application/json' \
-H 'Content-Type: application/json' \
-d '{
"user": "test", "prompt_id":"{prompt_id to be deleted}"}'
```