Spaces:
Runtime error
Runtime error
File size: 4,310 Bytes
4bdb245 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 |
from typing import Literal
from fastapi import APIRouter, Depends, HTTPException, Request, UploadFile
from pydantic import BaseModel, Field
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
ingest_router = APIRouter(prefix="/v1", dependencies=[Depends(authenticated)])
class IngestTextBody(BaseModel):
file_name: str = Field(examples=["Avatar: The Last Airbender"])
text: str = Field(
examples=[
"Avatar is set in an Asian and Arctic-inspired world in which some "
"people can telekinetically manipulate one of the four elements—water, "
"earth, fire or air—through practices known as 'bending', inspired by "
"Chinese martial arts."
]
)
class IngestResponse(BaseModel):
object: Literal["list"]
model: Literal["private-gpt"]
data: list[IngestedDoc]
@ingest_router.post("/ingest", tags=["Ingestion"], deprecated=True)
def ingest(request: Request, file: UploadFile) -> IngestResponse:
"""Ingests and processes a file.
Deprecated. Use ingest/file instead.
"""
return ingest_file(request, file)
@ingest_router.post("/ingest/file", tags=["Ingestion"])
def ingest_file(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.post("/ingest/text", tags=["Ingestion"])
def ingest_text(request: Request, body: IngestTextBody) -> IngestResponse:
"""Ingests and processes a text, storing its chunks to be used as context.
The context obtained from files is later used in
`/chat/completions`, `/completions`, and `/chunks` APIs.
A Document will be generated with the given text. The Document
ID is returned in the response, together with the
extracted Metadata (which is later used to improve context retrieval). That ID
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 len(body.file_name) == 0:
raise HTTPException(400, "No file name provided")
ingested_documents = service.ingest_text(body.file_name, body.text)
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/{doc_id}", tags=["Ingestion"])
def delete_ingested(request: Request, doc_id: str) -> None:
"""Delete the specified ingested Document.
The `doc_id` can be obtained from the `GET /ingest/list` endpoint.
The document will be effectively deleted from your storage context.
"""
service = request.state.injector.get(IngestService)
service.delete(doc_id)
|