autollm

>>> from autollm import AutoQueryEngine

>>> query_engine = AutoQueryEngine.from_defaults(
...     documents=documents,
...     llm_model="gpt-3.5-turbo",
...     llm_max_tokens="256",
...     llm_temperature="0.1",
...     system_prompt='...',
...     query_wrapper_prompt='...',
...     enable_cost_calculator=True,
...     embed_model="huggingface/BAAI/bge-large-zh",
...     chunk_size=512,
...     chunk_overlap=64,
...     context_window=4096,
...     similarity_top_k=3,
...     response_mode="compact",
...     structured_answer_filtering=False,
...     vector_store_type="LanceDBVectorStore",
...     lancedb_uri="./lancedb",
...     lancedb_table_name="vectors",
...     exist_ok=True,
...     overwrite_existing=False,
... )

>>> response = query_engine.query("Who is SafeVideo AI?")

>>> print(response.response)
"A startup that provides self hosted AI API's for companies!"

>>> from autollm import AutoFastAPI

>>> app = AutoFastAPI.from_query_engine(
...      query_engine,
...      api_title='...',
...      api_description='...',
...      api_version='...',
...      api_term_of_service='...',
    )

>>> uvicorn.run(app, host="0.0.0.0", port=8000)
INFO:    Started server process [12345]
INFO:    Waiting for application startup.
INFO:    Application startup complete.
INFO:    Uvicorn running on http://http://0.0.0.0:8000/

• huggingface - ollama example:

  >>> from autollm import AutoQueryEngine
  
  >>> llm_model = "ollama/llama2"
  >>> llm_api_base = "http://localhost:11434"
  
  >>> AutoQueryEngine.from_defaults(
  ...     documents='...',
  ...     llm_model=llm_model,
  ...     llm_api_base=llm_api_base,
  ... )
  

• microsoft azure - openai example:

  >>> from autollm import AutoQueryEngine
  
  >>> os.environ["AZURE_API_KEY"] = ""
  >>> os.environ["AZURE_API_BASE"] = ""
  >>> os.environ["AZURE_API_VERSION"] = ""
  
  >>> llm_model = "azure/")
  
  >>> AutoQueryEngine.from_defaults(
  ...     documents='...',
  ...     llm_model=llm_model
  ... )
  

• google - vertexai example:

  >>> from autollm import AutoQueryEngine
  
  >>> os.environ["VERTEXAI_PROJECT"] = "hardy-device-38811"  # Your Project ID`
  >>> os.environ["VERTEXAI_LOCATION"] = "us-central1"  # Your Location
  
  >>> llm_model = "text-bison@001"
  
  >>> AutoQueryEngine.from_defaults(
  ...     documents='...',
  ...     llm_model=llm_model
  ... )
  

• aws bedrock - claude v2 example:

  >>> from autollm import AutoQueryEngine
  
  >>> os.environ["AWS_ACCESS_KEY_ID"] = ""
  >>> os.environ["AWS_SECRET_ACCESS_KEY"] = ""
  >>> os.environ["AWS_REGION_NAME"] = ""
  
  >>> llm_model = "anthropic.claude-v2"
  
  >>> AutoQueryEngine.from_defaults(
  ...     documents='...',
  ...     llm_model=llm_model
  ... )
  

• QdrantVectorStore example:

  >>> from autollm import AutoQueryEngine
  >>> import qdrant_client
  
  >>> vector_store_type = "QdrantVectorStore"
  >>> client = qdrant_client.QdrantClient(
  ...     url="http://:",
  ...     api_key=""
  ... )
  >>> collection_name = "quickstart"
  
  >>> AutoQueryEngine.from_defaults(
  ...     documents='...',
  ...     vector_store_type=vector_store_type,
  ...     client=client,
  ...     collection_name=collection_name,
  ... )
  

>>> from autollm import AutoFastAPI

>>> app = AutoFastAPI.from_config(config_path, env_path)

Here, config and env should be replaced by your configuration and environment file paths.

After creating your FastAPI app, run the following command in your terminal to get it up and running:

uvicorn main:app

>>> from llama_index import StorageContext, ServiceContext, VectorStoreIndex
>>> from llama_index.vectorstores import LanceDBVectorStore

>>> from autollm import AutoQueryEngine

>>> vector_store = LanceDBVectorStore(uri="./.lancedb")
>>> storage_context = StorageContext.from_defaults(vector_store=vector_store)
>>> service_context = ServiceContext.from_defaults()
>>> index = VectorStoreIndex.from_documents(
        documents=documents,
        storage_context=storage_contex,
        service_context=service_context,
    )

>>> query_engine = AutoQueryEngine.from_instances(index)