servers.main

servers.main

Utilities for building and running the ClassifAI REST API.

This module provides functions for creating FastAPI applications and routers that expose VectorStore embedding and search functionality as REST API endpoints.

It also contains helpers for validating configuration and starting the API server.

Classes

Name	Description
LogLevel	Valid levels of logs.

LogLevel

servers.main.LogLevel()

Valid levels of logs.

Functions

Name	Description
get_router	Create and return a FastAPI APIRouter with search endpoints.
get_server	Create and return a FastAPI server with search endpoints.
is_valid_log_level	Check if str is valid log level.
make_endpoints	Create and register the different endpoints to your app.
run_server	Create and run a FastAPI server with search endpoints.

get_router

servers.main.get_router(vector_stores, endpoint_names)

Create and return a FastAPI APIRouter with search endpoints.

Parameters

Name	Type	Description	Default
vector_stores	list[VectorStore]	A list of VectorStore objects, each responsible for handling embedding and search operations for a specific endpoint.	required
endpoint_names	list[str]	Endpoint names corresponding to the vector stores.	required

Returns

Name	Type	Description
	APIRouter	fastapi.APIRouter: Router with initialized search endpoints.

Raises

Name	Type	Description
	DataValidationError	If the input parameters are invalid.
	ConfigurationError	If one or more vector stores are invalid.

get_server

servers.main.get_server(vector_stores, endpoint_names)

Create and return a FastAPI server with search endpoints.

Parameters

Name	Type	Description	Default
vector_stores	list[VectorStore]	A list of VectorStore objects, each responsible for handling embedding and search operations for a specific endpoint.	required
endpoint_names	list[str]	Endpoint names corresponding to the VectorStore instances to expose.	required

Returns

Name	Type	Description
	FastAPI	fastapi.FastAPI: A FastAPI server with initialized search endpoints.

is_valid_log_level

servers.main.is_valid_log_level(value)

Check if str is valid log level.

make_endpoints

servers.main.make_endpoints(main_router, vector_stores_dict)

Create and register the different endpoints to your app.

Parameters

Name	Type	Description	Default
main_router	APIRouter | FastAPI	The FastAPI application instance.	required
vector_stores_dict	dict[str, VectorStore]	The name of the endpoint to be created.	required

run_server

servers.main.run_server(
    vector_stores,
    endpoint_names,
    port=8000,
    host_ip='127.0.0.1',
    log_level='warning',
    demo_mode=False,
)

Create and run a FastAPI server with search endpoints.

Parameters

Name	Type	Description	Default
vector_stores	list[VectorStore]	A list of VectorStore objects, each responsible for handling embedding and search operations for a specific endpoint.	required
endpoint_names	list[str]	Endpoint names corresponding to the VectorStore instances to expose.	required
port	int	The port on which the API server runs. Defaults to 8000.	8000
host_ip	str	The IP address on which the API server listens. Defaults to “127.0.0.1”. Note that “127.0.0.1” only accepts connections from the local machine. Use “0.0.0.0” to allow external connections.	'127.0.0.1'
log_level	str	The logging level for the Uvicorn server. Supported values are “critical”, “error”, “warning”, “info”, and “debug”.	'warning'
demo_mode	bool	Whether to display demo server information in the OpenAPI documentation.	False

Raises

Name	Type	Description
	DataValidationError	If the input parameters are invalid, for example if the port value is out of bounds.