servers.main

servers.main

This module provides functionality for creating a start a restAPI service which allows a user to call the search methods of different VectorStore objects, from an api-endpoint.

These functions interact with the ClassifAI PackageIndexer modules VectorStore objects, such that their embed and search methods are exposed on restAPI endpoints, in a FastAPI restAPI service started with these functions.

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.
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]	A list of endpoint names corresponding to the vector stores.	required

Returns

Name	Type	Description
	APIRouter	Router with intialized search endpoints

Raises

Name	Type	Description
	DataValidationError	Raised if the input parameters are invalid.
	ConfigurationError	Raised if one or more of the 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]	A list of endpoint names corresponding to the VectorStores to be exposed.	required

Returns

Name	Type	Description
	FastAPI	Server with intialized search endpoints

make_endpoints

servers.main.make_endpoints(router, vector_stores_dict)

Create and register the different endpoints to your app.

Parameters

Name	Type	Description	Default
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)

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]	A list of endpoint names corresponding to the VectorStores to be exposed.	required
port	int	[optional] The port on which the API server will run. Defaults to 8000.	8000

Raises

Name	Type	Description
	DataValidationError	Raised if the input parameters are invalid, e.g. port value is out of bounds.