private_gpt/server/ingest/ingest_router.py

from typing import Literal, List

from fastapi import APIRouter, Depends, HTTPException, Request, UploadFile
from pydantic import BaseModel

from private_gpt.server.ingest.ingest_service import IngestService
from private_gpt.server.ingest.model import IngestedDoc
#from private_gpt.server.utils.auth import authenticated
from private_gpt.server.utils.authentication import get_current_user
ingest_router = APIRouter(prefix="/v1", dependencies=[Depends(get_current_user)])


class IngestResponse(BaseModel):
    object: Literal["list"]
    model: Literal["private-gpt"]
    data: list[IngestedDoc]


@ingest_router.post("/ingest", tags=["Ingestion"])
def ingest(request: Request, file: UploadFile) -> IngestResponse:
    """Ingests and processes a file, storing its chunks to be used as context.

    The context obtained from files is later used in
    `/chat/completions`, `/completions`, and `/chunks` APIs.

    Most common document
    formats are supported, but you may be prompted to install an extra dependency to
    manage a specific file type.

    A file can generate different Documents (for example a PDF generates one Document
    per page). All Documents IDs are returned in the response, together with the
    extracted Metadata (which is later used to improve context retrieval). Those IDs
    can be used to filter the context used to create responses in
    `/chat/completions`, `/completions`, and `/chunks` APIs.
    """
    service = request.state.injector.get(IngestService)
    if file.filename is None:
        raise HTTPException(400, "No file name provided")
    ingested_documents = service.ingest_bin_data(file.filename, file.file)
    return IngestResponse(object="list", model="private-gpt", data=ingested_documents)


@ingest_router.get("/ingest/list", tags=["Ingestion"])
def list_ingested(request: Request) -> IngestResponse:
    """Lists already ingested Documents including their Document ID and metadata.

    Those IDs can be used to filter the context used to create responses
    in `/chat/completions`, `/completions`, and `/chunks` APIs.
    """
    service = request.state.injector.get(IngestService)
    ingested_documents = service.list_ingested()
    return IngestResponse(object="list", model="private-gpt", data=ingested_documents)


@ingest_router.delete("/ingest/{file_name}", tags=["Ingestion"])
def delete_ingested(request: Request, file_name: str) -> None:
    """Delete all ingested Documents with the specified file name.

    The `file_name` can be obtained from the `GET /ingest/list` endpoint.
    All documents with the specified file name will be effectively deleted from your storage context.
    """
    service = request.state.injector.get(IngestService)

    # Find all doc_ids with the specified file_name
    ingested_documents = service.list_ingested()
    documents_to_delete = [doc.doc_id for doc in ingested_documents if doc.doc_metadata.get("file_name") == file_name]

    # Delete all documents with the specified file_name
    for doc_id_to_delete in documents_to_delete:
        service.delete(doc_id_to_delete)


@ingest_router.get("/ingest/list_filenames", tags=["Ingestion"], response_model=List[str])
def list_ingested(request: Request) -> List[str]:
    """Lists already ingested Documents including their Document ID and metadata.

    Those IDs can be used to filter the context used to create responses
    in `/chat/completions`, `/completions`, and `/chunks` APIs.
    """
    service = request.state.injector.get(IngestService)
    ingested_documents: List[IngestedDoc] = service.list_ingested()

    # Extract unique filenames
    unique_filenames = set(doc.doc_metadata.get("file_name", "") for doc in ingested_documents)
    unique_filenames_list = list(unique_filenames)

    return unique_filenames_list