feat: Client support chatdata

[Aries-ckt]

Description

Close #1328

1. Add datasource api v2
2. Client Support chatdata
3. Add examples and docs

How Has This Been Tested?

1.python dbgpt/app/dbgpt_server.py
2. add datasource called dbgpt

Curl

DBGPT_API_KEY=dbgpt

curl -X POST "http://localhost:5000/api/v2/chat/completions" \
    -H "Authorization: Bearer $DBGPT_API_KEY" \
    -H "accept: application/json" \
    -H "Content-Type: application/json" \
    -d "{\"messages\":\"show spaces data limit 5\",\"model\":\"chatgpt_proxyllm\",\"chat_mode\":\"chat_data\",\"chat_param\":\"dbgpt\",\"stream\":false}"

{
    "id": "2bb80fdd-e47e-4083-8bc9-7ca66ee0931b",
    "object": "chat.completion",
    "created": 1711509733,
    "model": "chatgpt_proxyllm",
    "choices": [
        {
            "index": 0,
            "message": {
                "role": "assistant",
                "content": "The user wants to display information about knowledge spaces with a limit of 5 results.\\n<chart-view content=\"{\"type\": \"response_table\", \"sql\": \"SELECT * FROM knowledge_space LIMIT 5\", \"data\": [{\"id\": 5, \"name\": \"frfrw\", \"vector_type\": \"Chroma\", \"desc\": \"eee\", \"owner\": \"eee\", \"context\": null, \"gmt_created\": \"2024-01-02T13:29:52\", \"gmt_modified\": \"2024-01-02T13:29:52\", \"description\": null}, {\"id\": 7, \"name\": \"acc\", \"vector_type\": \"Chroma\", \"desc\": \"dede\", \"owner\": \"dede\", \"context\": null, \"gmt_created\": \"2024-01-02T13:47:01\", \"gmt_modified\": \"2024-01-02T13:47:01\", \"description\": null}, {\"id\": 8, \"name\": \"bcc\", \"vector_type\": \"Chroma\", \"desc\": \"dede\", \"owner\": \"dede\", \"context\": null, \"gmt_created\": \"2024-01-02T14:22:02\", \"gmt_modified\": \"2024-01-02T14:22:02\", \"description\": null}, {\"id\": 9, \"name\": \"dede\", \"vector_type\": \"Chroma\", \"desc\": \"dede\", \"owner\": \"dede\", \"context\": null, \"gmt_created\": \"2024-01-02T14:36:18\", \"gmt_modified\": \"2024-01-02T14:36:18\", \"description\": null}, {\"id\": 10, \"name\": \"qqq\", \"vector_type\": \"Chroma\", \"desc\": \"dede\", \"owner\": \"dede\", \"context\": null, \"gmt_created\": \"2024-01-02T14:40:56\", \"gmt_modified\": \"2024-01-02T14:40:56\", \"description\": null}]}\" />"
            },
            "finish_reason": null
        }
    ],
    "usage": {
        "prompt_tokens": 0,
        "total_tokens": 0,
        "completion_tokens": 0
    }
}

Python

from dbgpt.client import Client

DBGPT_API_KEY = "dbgpt"
DB_NAME="dbgpt"

client = Client(api_key=DBGPT_API_KEY)
res = client.chat(
    messages="show space datas limit 5", 
    model="chatgpt_proxyllm", 
    chat_mode="chat_data", 
    chat_param=DB_NAME
)

Snapshots:

Include snapshots for easier review.

Checklist:

• My code follows the style guidelines of this project
• I have already rebased the commits and make the commit message conform to the project standard.
• I have performed a self-review of my own code
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation
• Any dependent changes have been merged and published in downstream modules

[csunny]

r+

(dbgpt_env) magic@B-4TMH9N3X-2120 DB-GPT % curl -X POST "http://localhost:5000/api/v2/chat/completions" \
    -H "Authorization: Bearer $DBGPT_API_KEY" \
    -H "accept: application/json" \
    -H "Content-Type: application/json" \
    -d "{\"messages\":\"query  user counts\",\"model\":\"proxyllm\",\"chat_mode\":\"chat_data\",\"chat_param\":\"dbgpt_test\",\"stream\":false}"

results

{"id":"13358aad-e2cc-43fc-8eb0-4a97f05f490c","object":"chat.completion","created":1711543056,"model":"proxyllm","choices":[{"index":0,"message":{"role":"assistant","content":"用户问题是查询用户数量，可以使用COUNT函数来统计用户表中的记录数。\\n<chart-view content=\"{\"type\": \"response_table\", \"sql\": \"SELECT COUNT(*) AS user_counts FROM user\", \"data\": [{\"user_counts\": 25}]}\" />"},"finish_reason":null}],"usage":{"prompt_tokens":0,"total_tokens":0,"completion_tokens":0}}%

[fangyinc]

LGTM.