SystemSh0cker/private-gpt
1
0
Fork 0
mirror of https://github.com/zylon-ai/private-gpt.git synced 2025-12-22 13:55:41 +01:00
Code Issues Projects Releases Packages Activity

feat(API): Ingest plain text (#1417)

Browse source 
* Add ingest/text route to ingest plain text

* Add new ingest text test and adapt ingest/file ones

* Include new API in docs

* Remove duplicated logic
This commit is contained in:
Iván Martínez 2023-12-18 21:47:05 +01:00 • committed by GitHub
parent 059f35840a
commit 6eeb95ec7f
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
6 changed files with 198 additions and 17 deletions
Download patch file Download diff file Expand all files Collapse all files

45
private_gpt/server/ingest/ingest_router.py
View file

@ -1,7 +1,7 @@
from typing import Literal
from fastapi import APIRouter, Depends, HTTPException, Request, UploadFile
from pydantic import BaseModel
from pydantic import BaseModel, Field
from private_gpt.server.ingest.ingest_service import IngestService
from private_gpt.server.ingest.model import IngestedDoc
@ -10,14 +10,35 @@ 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"])
@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
@ -40,6 +61,26 @@ def ingest(request: Request, file: UploadFile) -> IngestResponse:
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.