How to use VectorIndexAutoRetriever with ChatEngine?

[neelmalgo]

For RAG based ChatBot, I want to use metadata filtering with Azure Ai Search. MetaData Filtering happens in the retrieval stage. The as_chat_engine method of VectorStoreIndex uses BaseRetriever. However i want to use VectorIndexAutoRetriever. Does anybody know how to implement this?

[dosubot[bot]]

To use VectorIndexAutoRetriever with ChatEngine for a RAG-based ChatBot that utilizes metadata filtering with Azure AI Search, follow these steps:

1. Create the Azure AI Search Vector Store:

   from azure.core.credentials import AzureKeyCredential
   from azure.search.documents import SearchClient
   from azure.search.documents.indexes import SearchIndexClient
   from llama_index.vector_stores.azureaisearch import AzureAISearchVectorStore
   from llama_index.vector_stores.azureaisearch import IndexManagement, MetadataIndexFieldType
   
   # Azure AI Search setup
   search_service_api_key = "YOUR-AZURE-SEARCH-SERVICE-ADMIN-KEY"
   search_service_endpoint = "YOUR-AZURE-SEARCH-SERVICE-ENDPOINT"
   search_service_api_version = "2023-11-01"
   credential = AzureKeyCredential(search_service_api_key)
   
   # Index name to use
   index_name = "llamaindex-vector-demo"
   
   # Use index client to demonstrate creating an index
   index_client = SearchIndexClient(
       endpoint=search_service_endpoint,
       credential=credential,
   )
   
   metadata_fields = {
       "author": "author",
       "theme": ("topic", MetadataIndexFieldType.STRING),
       "director": "director",
   }
   
   # Creating an Azure AI Search Vector Store
   vector_store = AzureAISearchVectorStore(
       search_or_index_client=index_client,
       filterable_metadata_field_keys=metadata_fields,
       index_name=index_name,
       index_management=IndexManagement.CREATE_IF_NOT_EXISTS,
       id_field_key="id",
       chunk_field_key="chunk",
       embedding_field_key="embedding",
       embedding_dimensionality=1536,
       metadata_string_field_key="metadata",
       doc_id_field_key="doc_id",
       language_analyzer="en.lucene",
       vector_algorithm_type="exhaustiveKnn",
   )

2. Create the VectorIndexAutoRetriever:

   from llama_index.legacy.indices.vector_store.retrievers.auto_retriever import VectorIndexAutoRetriever
   from llama_index.legacy.indices.vector_store.base import VectorStoreIndex
   from llama_index.legacy.vector_stores.types import VectorStoreInfo
   
   # Assuming you have a VectorStoreIndex instance
   vector_store_index = VectorStoreIndex(vector_store=vector_store)
   
   # Create VectorStoreInfo
   vector_store_info = VectorStoreInfo(
       description="Your vector store description",
       supported_metadata_filters=["author", "theme", "director"]
   )
   
   retriever = VectorIndexAutoRetriever(
       index=vector_store_index,
       vector_store_info=vector_store_info
   )

3. Create the ChatEngine with the VectorIndexAutoRetriever:

   from llama_index.chat_engine import ChatEngine
   
   chat_engine = ChatEngine(retriever=retriever)

By following these steps, you can set up a RAG-based ChatBot that utilizes metadata filtering with Azure AI Search and integrates it with ChatEngine using VectorIndexAutoRetriever.

Details

Sources

• llama-index-integrations/vector_stores/llama-index-vector-stores-azureaisearch/llama_index/vector_stores/azureaisearch/base.py
• llama-index-core/llama_index/core/indices/vector_store/retrievers/auto_retriever/auto_retriever.py
• llama-index-legacy/llama_index/legacy/indices/vector_store/retrievers/auto_retriever/auto_retriever.py
• llama-index-legacy/llama_index/legacy/vector_stores/azureaisearch.py

About Dosu
This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.

Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

To continue the conversation, mention @dosu.

[ZumelzuR]

@dosu
This is not accurate, some functions are wrong.

Also azure not support currently filter "all". How could fix this in order to restrict some filters?