Callbacks

Question

Does AzureAISearchVectorStore support a callback manager? I only get the message **********
Trace: index_construction
**********and no other EventsMy code is as follows:vector_store = AzureAISearchVectorStore( search_or_index_client=search_client, filterable_metadata_field_keys=metadata_fields, index_management=IndexManagement.VALIDATE_INDEX, 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",
) storage_context = StorageContext.from_defaults(vector_store=vector_store)
index = VectorStoreIndex.from_documents( [], storage_context=storage_context, callback_manager=callback_manager
)

Logan M · Answer

I don't think any vector store supports callbacks. They all happen around/outside of it

Simon 📐🛠 · Answer

But as per your docs you add a callback manager when creating an index right?

Logan M · Answer

Yea. And in your code, there won't be anything to trace, because there's no nodes (that last line of code is essentially a no-op)

Simon 📐🛠 · Answer

Ah okay so I should be using method “from nodes” not “from documents”?

Simon 📐🛠 · Answer

Or as per your first comment it can’t be done in llama index unless I have access to azure ai search sub-processes

Logan M · Answer

You can use from_documents or the constructor itself for nodes i.e. VectorStoreIndex(nodes=nodes, ...), but the point is since you are passing in an empty list, there is nothing to trace 👀

Logan M · Answer

there are no documents or nodes to process

Simon 📐🛠 · Answer

Yeah I was confused about that also, I grabbed it from the notebook tutorial.I assumed the storage context had the docs already (stored already on Azure) hence the empty array?

Logan M · Answer

Maybe? Depends which docs page lol

Simon 📐🛠 · Answer

This one:https://docs.llamaindex.ai/en/stable/examples/vector_stores/AzureAISearchIndexDemo/

Simon 📐🛠 · Answer

So adding a callback manager like:callback_manager = CallbackManager([LlamaDebugHandler()])to# Load documents
documents = SimpleDirectoryReader("../data/paul_graham/").load_data()
storage_context = StorageContext.from_defaults(vector_store=vector_store) Settings.llm = llm
Settings.embed_model = embed_model
index = VectorStoreIndex.from_documents( documents, storage_context=storage_context,
callback_manager=callback_manager
)doesnt work with no Events emitted besides Trace: index_constructionDoes Azure emit events to llama index I am unaware of? If it doesnt at all then just let me know.. lol

Logan M · Answer

that should work, but since you manually setup the llm and embedding model, you'll need to attach it there as well

Simon 📐🛠 · Answer

How do I do that? Any hints pls 🙏

Logan M · Answer

For example llm = OpenAI(..., callback_manager=callback_manager)embed_model = OpenAIEmbedding(..., callback_manager=callback_manager)

Find answers from the community

Callbacks