rakmohan

Docwise Agentic — Data skill for Claude Code

Data community

Full agentic RAG pipeline: adaptive chunking → Qdrant hybrid search (semantic + BM25 + RRF) → LangGraph ReAct agent → grounded answers with citations, streamed live.

How to install Docwise Agentic

This entry records only its repository, not the path inside it, so there is no exact command to give. Open rakmohan/docwise-agentic and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Docwise Agentic does

Full agentic RAG pipeline: adaptive chunking → Qdrant hybrid search (semantic + BM25 + RRF) → LangGraph ReAct agent → grounded answers with citations, streamed live. Multi-turn conversation, multi-hop reasoning, human-in-the-loop, LangSmith tracing, MCP server. LLM-agnostic — works with Claude or OpenAI.

Alternatives in Data

06 Ink React Terminal UI — Prompt 06: Verify and Fix the Ink/React Terminal UI Pipeline 2.3k ★
FACT — FACT – Fast Augmented Context Tools: FACT is a lean retrieval pattern that skips vector search 161 ★
Lecture To Notes — Lecture recordings → structured grounded notes + a synced HTML viewer: video, timestamped transcript and curat 100 ★

README

DocWise Agentic

Agentic document Q&A system powered by **LangGraph**, **Qdrant**, and **Claude**.

**Ingest** — upload PDFs, DOCX, or Markdown files. Documents are parsed, adaptively chunked by content type, embedded with FastEmbed, and stored in Qdrant with rich metadata.

**Query** — ask natural-language questions. A LangGraph ReAct agent autonomously searches, reasons across documents, and synthesizes grounded answers with citations — all streamed in real time.

**Predecessor:** [docwise](https://github.com/rakmohan/docwise) — same parsing/chunking/embedding layers, upgraded with a full LangGraph agentic pipeline.

Features

Autonomous agent — LangGraph state graph decides how many searches to run, when to ask for clarification, and when it has enough context to answer
Multi-hop retrieval — agent can issue multiple search_documents and get_document_chunks calls across a single question
Hybrid search — dense semantic search (FastEmbed) + BM25 keyword search fused with Reciprocal Rank Fusion (RRF)
Real-time streaming — SSE streams each step (query plan, tool calls, tool results, answer) to the UI as it happens
Multi-turn conversation — LangGraph MemorySaver checkpointer persists thread state across turns
Human-in-the-loop — agent can pause and ask the user a clarifying question before continuing
Grounded answers with citations — every answer references the source chunks it was drawn from
MCP server — exposes 4 tools over HTTP/SSE so Claude Desktop can query your documents directly
Document formats — PDF, DOCX, and Markdown supported out of the box
Observability — LangSmith traces every LLM call, tool call, and multi-turn thread automatically

Tech Stack

Layer	Technology
LLM	Anthropic Claude or OpenAI (claude-sonnet-4-6 default)
Agent framework	LangGraph (state graph + MemorySaver checkpointer)
Vector store	Qdrant (Docker service, horizon