mirror of
https://github.com/zylon-ai/private-gpt.git
synced 2025-12-22 07:40:12 +01:00
aa70d3d9f0
* Add simple Basic auth To enable the basic authentication, one must set `server.auth.enabled` to true. The static string defined in `server.auth.secret` must be set in the header `Authorization`. The health check endpoint will always be accessible, no matter the API auth configuration. * Fix linting and type check * Fighting with mypy being too restrictive Had to disable mypy in the `auth` as we are not using the same signature for the authenticated method. mypy was complaining that the signatures of `authenticated` must be identical, no matter in which logical branch we are. Given that fastapi is accomodating itself of method signatures (it will inject the dependencies in the method call), this warning of mypy is actually preventing us to do something legit. mypy doc: https://mypy.readthedocs.io/en/stable/common_issues.html * Write tests to verify that the simple auth is working
73 lines
2.6 KiB
Python
73 lines
2.6 KiB
Python
from fastapi import APIRouter, Depends
|
|
from pydantic import BaseModel
|
|
from starlette.responses import StreamingResponse
|
|
|
|
from private_gpt.open_ai.extensions.context_filter import ContextFilter
|
|
from private_gpt.open_ai.openai_models import (
|
|
OpenAICompletion,
|
|
OpenAIMessage,
|
|
)
|
|
from private_gpt.server.chat.chat_router import ChatBody, chat_completion
|
|
from private_gpt.server.utils.auth import authenticated
|
|
|
|
completions_router = APIRouter(prefix="/v1", dependencies=[Depends(authenticated)])
|
|
|
|
|
|
class CompletionsBody(BaseModel):
|
|
prompt: str
|
|
use_context: bool = False
|
|
context_filter: ContextFilter | None = None
|
|
include_sources: bool = True
|
|
stream: bool = False
|
|
|
|
model_config = {
|
|
"json_schema_extra": {
|
|
"examples": [
|
|
{
|
|
"prompt": "How do you fry an egg?",
|
|
"stream": False,
|
|
"use_context": False,
|
|
"include_sources": False,
|
|
}
|
|
]
|
|
}
|
|
}
|
|
|
|
|
|
@completions_router.post(
|
|
"/completions",
|
|
response_model=None,
|
|
summary="Completion",
|
|
responses={200: {"model": OpenAICompletion}},
|
|
tags=["Contextual Completions"],
|
|
)
|
|
def prompt_completion(body: CompletionsBody) -> OpenAICompletion | StreamingResponse:
|
|
"""We recommend most users use our Chat completions API.
|
|
|
|
Given a prompt, the model will return one predicted completion. If `use_context`
|
|
is set to `true`, the model will use context coming from the ingested documents
|
|
to create the response. The documents being used can be filtered using the
|
|
`context_filter` and passing the document IDs to be used. Ingested documents IDs
|
|
can be found using `/ingest/list` endpoint. If you want all ingested documents to
|
|
be used, remove `context_filter` altogether.
|
|
|
|
When using `'include_sources': true`, the API will return the source Chunks used
|
|
to create the response, which come from the context provided.
|
|
|
|
When using `'stream': true`, the API will return data chunks following [OpenAI's
|
|
streaming model](https://platform.openai.com/docs/api-reference/chat/streaming):
|
|
```
|
|
{"id":"12345","object":"completion.chunk","created":1694268190,
|
|
"model":"private-gpt","choices":[{"index":0,"delta":{"content":"Hello"},
|
|
"finish_reason":null}]}
|
|
```
|
|
"""
|
|
message = OpenAIMessage(content=body.prompt, role="user")
|
|
chat_body = ChatBody(
|
|
messages=[message],
|
|
use_context=body.use_context,
|
|
stream=body.stream,
|
|
include_sources=body.include_sources,
|
|
context_filter=body.context_filter,
|
|
)
|
|
return chat_completion(chat_body)
|