mirror of
https://github.com/zylon-ai/private-gpt.git
synced 2025-12-22 17:05:41 +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
56 lines
2.1 KiB
Python
56 lines
2.1 KiB
Python
from typing import Literal
|
|
|
|
from fastapi import APIRouter, Depends
|
|
from pydantic import BaseModel, Field
|
|
|
|
from private_gpt.di import root_injector
|
|
from private_gpt.open_ai.extensions.context_filter import ContextFilter
|
|
from private_gpt.server.chunks.chunks_service import Chunk, ChunksService
|
|
from private_gpt.server.utils.auth import authenticated
|
|
|
|
chunks_router = APIRouter(prefix="/v1", dependencies=[Depends(authenticated)])
|
|
|
|
|
|
class ChunksBody(BaseModel):
|
|
text: str = Field(examples=["Q3 2023 sales"])
|
|
context_filter: ContextFilter | None = None
|
|
limit: int = 10
|
|
prev_next_chunks: int = Field(default=0, examples=[2])
|
|
|
|
|
|
class ChunksResponse(BaseModel):
|
|
object: Literal["list"]
|
|
model: Literal["private-gpt"]
|
|
data: list[Chunk]
|
|
|
|
|
|
@chunks_router.post("/chunks", tags=["Context Chunks"])
|
|
def chunks_retrieval(body: ChunksBody) -> ChunksResponse:
|
|
"""Given a `text`, returns the most relevant chunks from the ingested documents.
|
|
|
|
The returned information can be used to generate prompts that can be
|
|
passed to `/completions` or `/chat/completions` APIs. Note: it is usually a very
|
|
fast API, because only the Embeddings model is involved, not the LLM. The
|
|
returned information contains the relevant chunk `text` together with the source
|
|
`document` it is coming from. It also contains a score that can be used to
|
|
compare different results.
|
|
|
|
The max number of chunks to be returned is set using the `limit` param.
|
|
|
|
Previous and next chunks (pieces of text that appear right before or after in the
|
|
document) can be fetched by using the `prev_next_chunks` field.
|
|
|
|
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.
|
|
"""
|
|
service = root_injector.get(ChunksService)
|
|
results = service.retrieve_relevant(
|
|
body.text, body.context_filter, body.limit, body.prev_next_chunks
|
|
)
|
|
return ChunksResponse(
|
|
object="list",
|
|
model="private-gpt",
|
|
data=results,
|
|
)
|