mirror of
https://github.com/zylon-ai/private-gpt.git
synced 2025-12-22 20:12:55 +01:00
64c5ae214a
* Configure simple builtin logging Changed the 2 existing `print` in the `private_gpt` code base into actual python logging, stop using loguru (dependency will be dropped in a later commit). Try to use the `key=value` logging convention in logs (to indicate what dynamic values represents, and what is dynamic vs not). Using `%s` log style, so that the string formatting is pushed inside the logger, giving the ability to the logger to determine if the string need to be formatted or not (i.e. strings from debug logs might not be formatted if the log level is not debug) The (basic) builtin log configuration have been placed in `private_gpt/__init__.py` in order to initialize the logging system even before we start to launch any python code in `private_gpt` package (ensuring we get any initialization log formatted as we want to) Disabled `uvicorn` custom logging format, resulting in having uvicorn logs being outputted in our formatted. Some more concise format could be used if we want to, especially: ``` COMPACT_LOG_FORMAT = '%(asctime)s.%(msecs)03d [%(levelname)s] %(name)s - %(message)s' ``` Python documentation and cookbook on logging for reference: * https://docs.python.org/3/library/logging.html * https://docs.python.org/3/howto/logging.html * Removing loguru from the dependencies Result of `poetry remove loguru` * PR feedback: using `logger` variable name instead of `log` --------- Co-authored-by: Louis Melchior <louis@jaris.io>
108 lines
3.7 KiB
Python
108 lines
3.7 KiB
Python
"""FastAPI app creation, logger configuration and main API routes."""
|
|
from typing import Any
|
|
|
|
import llama_index
|
|
from fastapi import FastAPI
|
|
from fastapi.openapi.utils import get_openapi
|
|
|
|
from private_gpt.paths import docs_path
|
|
from private_gpt.server.chat.chat_router import chat_router
|
|
from private_gpt.server.chunks.chunks_router import chunks_router
|
|
from private_gpt.server.completions.completions_router import completions_router
|
|
from private_gpt.server.embeddings.embeddings_router import embeddings_router
|
|
from private_gpt.server.health.health_router import health_router
|
|
from private_gpt.server.ingest.ingest_router import ingest_router
|
|
from private_gpt.settings.settings import settings
|
|
|
|
# Add LlamaIndex simple observability
|
|
llama_index.set_global_handler("simple")
|
|
|
|
# Start the API
|
|
with open(docs_path / "description.md") as description_file:
|
|
description = description_file.read()
|
|
|
|
tags_metadata = [
|
|
{
|
|
"name": "Ingestion",
|
|
"description": "High-level APIs covering document ingestion -internally "
|
|
"managing document parsing, splitting,"
|
|
"metadata extraction, embedding generation and storage- and ingested "
|
|
"documents CRUD."
|
|
"Each ingested document is identified by an ID that can be used to filter the "
|
|
"context"
|
|
"used in *Contextual Completions* and *Context Chunks* APIs.",
|
|
},
|
|
{
|
|
"name": "Contextual Completions",
|
|
"description": "High-level APIs covering contextual Chat and Completions. They "
|
|
"follow OpenAI's format, extending it to "
|
|
"allow using the context coming from ingested documents to create the "
|
|
"response. Internally"
|
|
"manage context retrieval, prompt engineering and the response generation.",
|
|
},
|
|
{
|
|
"name": "Context Chunks",
|
|
"description": "Low-level API that given a query return relevant chunks of "
|
|
"text coming from the ingested"
|
|
"documents.",
|
|
},
|
|
{
|
|
"name": "Embeddings",
|
|
"description": "Low-level API to obtain the vector representation of a given "
|
|
"text, using an Embeddings model."
|
|
"Follows OpenAI's embeddings API format.",
|
|
},
|
|
{
|
|
"name": "Health",
|
|
"description": "Simple health API to make sure the server is up and running.",
|
|
},
|
|
]
|
|
|
|
app = FastAPI()
|
|
|
|
|
|
def custom_openapi() -> dict[str, Any]:
|
|
if app.openapi_schema:
|
|
return app.openapi_schema
|
|
openapi_schema = get_openapi(
|
|
title="PrivateGPT",
|
|
description=description,
|
|
version="0.1.0",
|
|
summary="PrivateGPT is a production-ready AI project that allows you to "
|
|
"ask questions to your documents using the power of Large Language "
|
|
"Models (LLMs), even in scenarios without Internet connection. "
|
|
"100% private, no data leaves your execution environment at any point.",
|
|
contact={
|
|
"url": "https://github.com/imartinez/privateGPT",
|
|
},
|
|
license_info={
|
|
"name": "Apache 2.0",
|
|
"url": "https://www.apache.org/licenses/LICENSE-2.0.html",
|
|
},
|
|
routes=app.routes,
|
|
tags=tags_metadata,
|
|
)
|
|
openapi_schema["info"]["x-logo"] = {
|
|
"url": "https://lh3.googleusercontent.com/drive-viewer"
|
|
"/AK7aPaD_iNlMoTquOBsw4boh4tIYxyEuhz6EtEs8nzq3yNkNAK00xGj"
|
|
"E1KUCmPJSk3TYOjcs6tReG6w_cLu1S7L_gPgT9z52iw=s2560"
|
|
}
|
|
|
|
app.openapi_schema = openapi_schema
|
|
return app.openapi_schema
|
|
|
|
|
|
app.openapi = custom_openapi # type: ignore[method-assign]
|
|
|
|
app.include_router(completions_router)
|
|
app.include_router(chat_router)
|
|
app.include_router(chunks_router)
|
|
app.include_router(ingest_router)
|
|
app.include_router(embeddings_router)
|
|
app.include_router(health_router)
|
|
|
|
|
|
if settings.ui.enabled:
|
|
from private_gpt.ui.ui import mount_in_app
|
|
|
|
mount_in_app(app)
|