DEDUPEDWho it is forSomeone whose RAG answers keep missing facts that are clearly in the source PDF.
The problemMost RAG tools chunk blindly, so a table or clause gets split and the right passage never comes back.
The outcomeDocuments chunked with a template that fits them, with chunks you have inspected and corrected by hand.
What you need first
- Docker 24.0.0 or later and Docker Compose v2.26.1 or later
- A starting machine of 4 CPU cores, 16 GB RAM and 50 GB free disk
- An LLM, an embedding model and a reranker, added with their service address and API key after sign-in
- If you use Elasticsearch, vm.max_map_count set to at least 262144
Steps
- Deploy RAGFlow with Docker as in the README and sign in
- Upload a document and pick a chunking template that fits its type
- Open the chunk visualization and review where the text was split
- Adjust chunks by hand where needed; the README calls this human intervention
- Ask a question and click through the traceable citations to confirm the right chunk was used
Prompt for your agent
In my infiniflow/ragflow instance, upload <document>, try two chunking templates, and compare how each splits <section>. Recommend the template that keeps <section> intact and explain why.
Caveat. Template choice is a judgement call per document type; the README lists the feature but not which template suits which file.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for infiniflow/ragflow and "See and fix how your documents are chunked"
Add Deduped to Claude Code once
claude mcp add --transport http deduped https://dedupedai.com/mcp
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer