Want to use embeddings generated by lmstudio for llamaindex's vectorstoreindex for creating a query engine

[GildeshAbhay]

I have this basic code for RAG using Auto-Merge technique wthin llamaindex

    node_parser = HierarchicalNodeParser.from_defaults(chunk_sizes=chunk_size)
    nodes = node_parser.get_nodes_from_documents([doc])
    storage_context = StorageContext.from_defaults()
    storage_context.docstore.add_documents(nodes)
    index = VectorStoreIndex(nodes, storage_context=storage_context , embed_model=embed_model)
    postproc = None
    reranker = SentenceTransformerRerank(model="cross-encoder/ms-marco-MiniLM-L-2-v2", top_n=3)
    retriever = index.as_retriever(similarity_top_k=retrieval_metadata_similarity)
    retriever = AutoMergingRetriever(retriever,index.storage_context,verbose=True)
    response_synthesizer = get_response_synthesizer(response_mode=response_mode)
    node_postprocessors = [postproc, reranker]
    node_postprocessors = [processor for processor in node_postprocessors if processor is not None]
    query_engine = RetrieverQueryEngine(retriever, node_postprocessors=node_postprocessors)

Now, I want to use nominic-embeddings via lmstudio, whose basic code is this

Make sure to pip install openai first

from openai import OpenAI
client = OpenAI(base_url="http://localhost:1234/v1", api_key="lm-studio")

def get_embedding(text, model="nomic-ai/nomic-embed-text-v1.5-GGUF"):
   text = text.replace("\n", " ")
   return client.embeddings.create(input = [text], model=model).data[0].embedding

print(get_embedding("Once upon a time, there was a cat."))

However, this gives me embeddings directly, whereas I want to use in the above code (specifically in place of vectorstoreindex)
How can I do that?

[GildeshAbhay]

can you tell me the links to their github issues page please!

[nethi]

Take a look at this example and work-around: run-llama/llama_index#15021

You have to pass lmstudio embedding as embed_model argument