Find answers from the community

Updated last month

Creating a Query Engine on Top of an Existing Vector Store

At a glance
The community member has a LlamaIndex pipeline that tokenizes, extracts entities, and stores the results in a vector store. They want to create a query engine on top of this vector store to ask questions about the indexed documents. However, the vector store already has embeddings from previous pipeline runs, so the community member does not want to use VectorStoreIndex.from_documents(..). The community member is asking what they should do in this situation.
hi everyone! i have a llamaindex pipeline which tokenizes, extracts entities, etc from a list of documents and stores it in the vector_store; after that, how do i create a query engine on top of that vector store so that i can ask questions about the documents indexed in the vector store? that vector store already has embeddings from previous piplien runs, so i don't want to use VectorStoreIndex.from_documents(..) because the embeddings are already in the data store - what do i do?

pipeline = IngestionPipeline(
transformations=[
SummaryExtractor(summaries=["self"], llm=qa_llm),
QuestionsAnsweredExtractor(llm=qa_llm, questions=1),
EntityExtractor(label_entities=True, llm=qa_llm),
embed_model,
],
vector_store=vector_store,
)
Add a reply
Sign up and join the conversation on Discord