KMS/ragflow
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

DOCS: add OpenAI-compatible http and python api reference (#5374)

Browse Source 
### What problem does this PR solve?

Add OpenAI-compatible http and python api reference

### Type of change

- [x] Documentation Update

---------

Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
Co-authored-by: writinwaters <93570324+writinwaters@users.noreply.github.com>
This commit is contained in:
Yongteng Lei 2025-02-26 15:52:26 +08:00 committed by GitHub
parent a9e4695b74
commit b3b341173f
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 223 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

37
api/apps/sdk/session.py
View File

@ -217,7 +217,7 @@ def chat_completion_openai_like(tenant_id, chat_id):
model=model,
messages=[
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Who you are?"},
{"role": "user", "content": "Who are you?"},
{"role": "assistant", "content": "I am an AI assistant named..."},
{"role": "user", "content": "Can you tell me how to install neovim"},
],
@ -236,14 +236,20 @@ def chat_completion_openai_like(tenant_id, chat_id):
messages = req.get("messages", [])
# To prevent empty [] input
if len(messages) < 1:
return get_error_data_result("You have to provide messages")
return get_error_data_result("You have to provide messages.")
if messages[-1]["role"] != "user":
return get_error_data_result("The last content of this conversation is not from user.")
prompt = messages[-1]["content"]
# Treat context tokens as reasoning tokens
context_token_used = sum(len(message["content"]) for message in messages)
dia = DialogService.query(tenant_id=tenant_id, id=chat_id, status=StatusEnum.VALID.value)
if not dia:
return get_error_data_result(f"You don't own the chat {chat_id}")
dia = dia[0]
# Filter system and assistant messages
# Filter system and non-sense assistant messages
msg = None
msg = [m for m in messages if m["role"] != "system" and (m["role"] != "assistant" or msg)]
@ -251,7 +257,7 @@ def chat_completion_openai_like(tenant_id, chat_id):
# The value for the usage field on all chunks except for the last one will be null.
# The usage field on the last chunk contains token usage statistics for the entire request.
# The choices field on the last chunk will always be an empty array [].
def streamed_respose_generator(chat_id, dia, msg):
def streamed_response_generator(chat_id, dia, msg):
token_used = 0
response = {
"id": f"chatcmpl-{chat_id}",
@ -286,17 +292,17 @@ def chat_completion_openai_like(tenant_id, chat_id):
response["choices"][0]["delta"]["content"] = "**ERROR**: " + str(e)
yield f"data:{json.dumps(response, ensure_ascii=False)}\n\n".encode("utf-8")
# The last chunck
# The last chunk
response["choices"][0]["delta"]["content"] = None
response["choices"][0]["finish_reason"] = "stop"
response["usage"] = {
"prompt_tokens": len(msg),
"prompt_tokens": len(prompt),
"completion_tokens": token_used,
"total_tokens": len(msg) + token_used
"total_tokens": len(prompt) + token_used
}
yield f"data:{json.dumps(response, ensure_ascii=False)}\n\n".encode("utf-8")
resp = Response(streamed_respose_generator(chat_id, dia, msg), mimetype="text/event-stream")
resp = Response(streamed_response_generator(chat_id, dia, msg), mimetype="text/event-stream")
resp.headers.add_header("Cache-control", "no-cache")
resp.headers.add_header("Connection", "keep-alive")
resp.headers.add_header("X-Accel-Buffering", "no")
@ -308,6 +314,7 @@ def chat_completion_openai_like(tenant_id, chat_id):
# focus answer content only
answer = ans
break
content = answer["answer"]
response = {
"id": f"chatcmpl-{chat_id}",
@ -315,20 +322,20 @@ def chat_completion_openai_like(tenant_id, chat_id):
"created": int(time.time()),
"model": req.get("model", ""),
"usage": {
"prompt_tokens": len(messages),
"completion_tokens": len(answer),
"total_tokens": len(messages) + len(answer),
"prompt_tokens": len(prompt),
"completion_tokens": len(content),
"total_tokens": len(prompt) + len(content),
"completion_tokens_details": {
"reasoning_tokens": len(answer),
"accepted_prediction_tokens": len(answer),
"rejected_prediction_tokens": len(answer)
"reasoning_tokens": context_token_used,
"accepted_prediction_tokens": len(content),
"rejected_prediction_tokens": 0 # 0 for simplicity
}
},
"choices": [
{
"message": {
"role": "assistant",
"content": answer["answer"]
"content": content
},
"logprobs": None,
"finish_reason": "stop",

148
docs/references/http_api_reference.md
View File

@ -9,6 +9,154 @@ A complete reference for RAGFlow's RESTful API. Before proceeding, please ensure
---
## OpenAI-Compatible API
---
### Create chat completion
**POST** `/api/v1/chats_openai/{chat_id}/chat/completions`
Creates a model response for a given chat conversation.
This API follows the same request and response format as OpenAI's API. It allows you to interact with the model in a manner similar to how you would with [OpenAI's API](https://platform.openai.com/docs/api-reference/chat/create).
#### Request
- Method: POST
- URL: `/api/v1/chats_openai/{chat_id}/chat/completions`
- Headers:
- `'content-Type: application/json'`
- `'Authorization: Bearer <YOUR_API_KEY>'`
- Body:
- `"model"`: `string`
- `"messages"`: `object list`
- `"stream"`: `boolean`
##### Request example
```bash
curl --request POST \
--url http://{address}/api/v1/chats_openai/{chat_id}/chat/completions \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer <YOUR_API_KEY>' \
--data '{
"model": "model",
"messages": [{"role": "user", "content": "Say this is a test!"}],
"stream": true
}'
```
##### Request Parameters
- `model` (*Body parameter*) `string`, *Required*
The model used to generate the response. The server will parse this automatically, so you can set it to any value for now.
- `messages` (*Body parameter*) `list[object]`, *Required*
A list of historical chat messages used to generate the response. This must contain at least one message with the `user` role.
- `stream` (*Body parameter*) `boolean`
Whether to receive the response as a stream. Set this to `false` explicitly if you prefer to receive the entire response in one go instead of as a stream.
#### Response
Stream:
```json
{
"id": "chatcmpl-3a9c3572f29311efa69751e139332ced",
"choices": [
{
"delta": {
"content": "This is a test. If you have any specific questions or need information, feel",
"role": "assistant",
"function_call": null,
"tool_calls": null
},
"finish_reason": null,
"index": 0,
"logprobs": null
}
],
"created": 1740543996,
"model": "model",
"object": "chat.completion.chunk",
"system_fingerprint": "",
"usage": null
}
// omit duplicated information
{"choices":[{"delta":{"content":" free to ask, and I will do my best to provide an answer based on","role":"assistant"}}]}
{"choices":[{"delta":{"content":" the knowledge I have. If your question is unrelated to the provided knowledge base,","role":"assistant"}}]}
{"choices":[{"delta":{"content":" I will let you know.","role":"assistant"}}]}
// the last chunk
{
"id": "chatcmpl-3a9c3572f29311efa69751e139332ced",
"choices": [
{
"delta": {
"content": null,
"role": "assistant",
"function_call": null,
"tool_calls": null
},
"finish_reason": "stop",
"index": 0,
"logprobs": null
}
],
"created": 1740543996,
"model": "model",
"object": "chat.completion.chunk",
"system_fingerprint": "",
"usage": {
"prompt_tokens": 18,
"completion_tokens": 225,
"total_tokens": 243
}
}
```
Non-stream:
```json
{
"choices":[
{
"finish_reason":"stop",
"index":0,
"logprobs":null,
"message":{
"content":"This is a test. If you have any specific questions or need information, feel free to ask, and I will do my best to provide an answer based on the knowledge I have. If your question is unrelated to the provided knowledge base, I will let you know.",
"role":"assistant"
}
}
],
"created":1740543499,
"id":"chatcmpl-3a9c3572f29311efa69751e139332ced",
"model":"model",
"object":"chat.completion",
"usage":{
"completion_tokens":246,
"completion_tokens_details":{
"accepted_prediction_tokens":246,
"reasoning_tokens":18,
"rejected_prediction_tokens":0
},
"prompt_tokens":18,
"total_tokens":264
}
}
```
Failure:
```json
{
"code": 102,
"message": "The last content of this conversation is not from user."
}
```
## DATASET MANAGEMENT
---

53
docs/references/python_api_reference.md
View File

@ -13,10 +13,63 @@ Run the following command to download the Python SDK:
```bash
pip install ragflow-sdk
```
:::
---
## OpenAI-Compatible API
---
### Create chat completion
Creates a model response for the given historical chat conversation via OpenAI's API.
#### Parameters
##### model: `str`, *Required*
The model used to generate the response. The server will parse this automatically, so you can set it to any value for now.
##### messages: `list[object]`, *Required*
A list of historical chat messages used to generate the response. This must contain at least one message with the `user` role.
##### stream: `boolean`
Whether to receive the response as a stream. Set this to `false` explicitly if you prefer to receive the entire response in one go instead of as a stream.
#### Returns
- Success: Respose [message](https://platform.openai.com/docs/api-reference/chat/create) like OpenAI
- Failure: `Exception`
#### Examples
```python
from openai import OpenAI
model = "model"
client = OpenAI(api_key="ragflow-api-key", base_url=f"http://ragflow_address/api/v1/chats_openai/<chat_id>")
completion = client.chat.completions.create(
model=model,
messages=[
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Who are you?"},
],
stream=True
)
stream = True
if stream:
for chunk in completion:
print(chunk)
else:
print(completion.choices[0].message.content)
```
## DATASET MANAGEMENT
---