Workflow · workflow
Query multiple documents using LlamaIndex, LangChain, and Milvus
LLMs are useful for personal projects but the challenge is deploying them in production for multi-document querying — querying a single document is insufficient, and without query decomposition, LLMs cannot answer questions that require information from multiple sources.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Multi-document query submitted
A complex question requiring information from multiple documents is submitted to the decomposable query engine.
Tools used
LlamaIndexLangChainMilvusOpenAI
Outcome
Decomposable queries successfully answer complex multi-document questions by breaking them into simpler targeted sub-queries, routing each to the right data source via a keyword index, and combining results with a vector store index.
What failed first
Without decomposable queries, the LLM application returns a response indicating insufficient context to answer a question that spans multiple documents.
Grounding & classification
Source type: technical build writeup
11 fields verified against source quotes, 1 dropped as unverifiable.
knowledge searchragknowledge basefailure mode describedtools describedworkflow describedtechnical build writeuprag answering