justin/crop-chem-docs
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge pull request 'README: rewrite for crop-chem-docs as a product (was template README)' (#1) from readme-update into main

Browse Source
This commit was merged in pull request #1.
This commit is contained in:
Justin Paul
2026-05-25 17:51:20 -04:00
parent 4b21ba53a2 b1a712308c
commit 4c9b087da8
1 changed files with 110 additions and 67 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+110 -67
View File
@@ -1,103 +1,146 @@
# docs-mcp-template # crop-chem-docs
A reusable template for building hosted MCP servers over a product's MCP server over ~4,000 public US row-crop pesticide / herbicide / fertilizer labels — feeding the same Drawbar farm-advisor AI as the sibling [`seed-mcp`](https://git.jpaul.io/justin/seed-mcp). The advisor calls this MCP for label rates, REI/PHI, rotation restrictions, tank-mix guidance, and active-ingredient lookups.
public documentation. Distilled from one production build; everything
product-specific has been factored out.
The end product is a streamable-HTTP MCP server with ~15 tools that Built on [`docs-mcp-template`](https://git.jpaul.io/justin/docs-mcp-template) (same template lineage as seed-mcp). **In production** on trashpanda; the Drawbar advisor calls it via the `chem:` prefix.
any LLM client (Claude Desktop, Claude Code, Cursor, Copilot) can
call to answer questions against the docs, surface what changed
recently, and flag likely inconsistencies.
## What's here ## What's in the corpus
- **[PLAN.md](PLAN.md)** — comprehensive build guide. Phased **4,159 indexed pages** across two complementary sources:
approach (13 phases, ~2–3 weeks of focused work for the full
stack). Includes the design decisions, the gotchas, and a | Source | Pages | Notes |
per-product customization checklist. |---|---|---|
- **Scaffolded skeleton** — working FastMCP server with stub tools, | `bayer` | 91 | Bayer Crop Science US product pages — Warrant, Harness, Roundup, Liberty, Capreno, etc. Rich Next.js `__NEXT_DATA__` payload: active ingredients, label rates, MOA codes, supplemental PDFs (24c / 2EE / bulletins). robots.txt explicitly whitelists RAG indexing. |
Dockerfile, docker-compose, CI workflows, eval harness layout, | `epa_ppls` | 4,068 | EPA Pesticide Product Label System — every registered ag chemistry product. Authoritative source of truth for EPA reg numbers, master labels, signal words, registrant info, formulations. |
usage logging. Everything you need to `git clone` and start
filling in the product-specific bits. ## MCP tools
Same shape as the docs-mcp-template's standard tools (see [`docs_mcp/server.py`](docs_mcp/server.py)):
| Tool | Purpose |
|---|---|
| `search_docs` | Hybrid dense + BM25 + rerank search over the label corpus, filterable by source. |
| `get_page` | Full label record by `(source, source_key)`. Returns marketing copy + extracted PDF text + sidecar metadata. |
| `list_versions` | Facet discovery (sources, EPA registrant codes, label categories). |
| `crop_chem_api_lessons` | Curated agronomy / regulatory lessons — EPA reg-number normalization, label-supersession ordering, common tank-mix gotchas. |
| Plus the template's standard `diff_versions`, `bundle_changelog`, `weekly_digest` if needed. |
## Retrieval — eval-validated
From [`eval/results/with_rerank.md`](eval/results/with_rerank.md) (35 golden queries, k=5):
| Retriever | MRR | Recall@5 | nDCG@5 | Time (s) |
|---|---|---|---|---|
| **hybrid+rerank** | **0.672** | **0.638** | **0.621** | 823 |
| bm25 | 0.544 | 0.586 | 0.524 | 5 |
| dense+rerank | 0.171 | 0.143 | 0.149 | 805 |
| hybrid-rrf | 0.114 | 0.114 | 0.108 | 8 |
| dense | 0.027 | 0.086 | 0.041 | 5 |
**Deploy config**: `HYBRID_SEARCH=true` + `RERANK_URL=http://llama-rerank:8080`.
Pattern matches what seed-mcp found independently:
1. **Dense embedding alone is essentially useless** on this corpus (MRR 0.027). Variety codes, EPA reg numbers, and active-ingredient names have no semantic neighbors — `nomic-embed-text` returns noise.
2. **Hybrid-rrf (no rerank) is worse than BM25 alone.** RRF dilutes BM25's strong ranking with dense noise. Don't ship without rerank.
3. **BM25 alone (MRR 0.544, 5 sec) is a great fallback** when the rerank sidecar is unavailable.
4. **Rerank brings the win** — `hybrid+rerank` MRR 0.672 is 23% better than BM25 alone and dominates every other configuration.
**Note on rerank in production**: through 2026-05-25 the `llama-rerank` sidecar was attached to Docker's default `bridge` network instead of `drawbar-backend_default`, so chem-mcp's `RERANK_URL=http://llama-rerank:8080` was resolving via public DNS to a random IP and connection-refusing. The MCP fell back to dense+BM25 silently. Fixed via `docker network connect drawbar-backend_default llama-rerank`. Re-running the eval is on the follow-up list; expect the deployed MRR to lift toward the lab number.
## Quick start ## Quick start
```bash ```bash
git clone https://git.jpaul.io/justin/docs-mcp-template.git my-product-docs git clone https://git.jpaul.io/justin/crop-chem-docs.git
cd my-product-docs cd crop-chem-docs
git remote remove origin # detach from template
python -m venv venv && source venv/bin/activate python -m venv venv && source venv/bin/activate
pip install -r requirements.txt pip install -r requirements.txt
# Read PLAN.md before doing anything else. Pay particular attention to # Sample-scrape to verify wiring:
# Phase 1 (scraper) — that's the most product-specific phase. python -m scrape.runner --source bayer --limit 5
# Run the stub server (no corpus yet — just verifies the wiring): # Full refresh (be polite — bayer is small, epa_ppls is hours):
python -m docs_mcp.server --transport stdio python -m scrape.runner --source bayer --force
python -m scrape.runner --source epa_ppls --force
# Rebuild Chroma + BM25:
OLLAMA_URL=http://192.168.0.125:11434 PRODUCT_NAME=crop_chem \
python -m rag.index --rebuild
# Run the eval harness:
RERANK_URL=http://localhost:18080 python -m eval.run_eval \
--queries eval/queries.jsonl --k 5 \
--output eval/results/baseline.md
# Local MCP server (stdio for Claude Desktop dev):
PRODUCT_NAME=crop_chem python -m docs_mcp.server --transport stdio
``` ```
## Repo layout ## Repo layout
``` ```
. .
├── PLAN.md # The build guide. Read first. ├── CLAUDE.md # Canonical agent guide
├── PLAN.md # Template's 13-phase build guide
├── README.md ├── README.md
├── requirements.txt ├── requirements.txt
├── Dockerfile ├── Dockerfile
├── .gitignore ├── deploy/
│ ├── docker-compose.yml # Drop-in compose for Drawbar
│ ├── drawbar-compose-snippet.md # Notes on the parent compose merge
│ └── rerank-docker.md # llama-rerank service deployment
├── .gitea/workflows/ ├── .gitea/workflows/
│ ├── refresh.yml # Weekly scrape + index + image push │ ├── refresh.yml # Monthly cron: scrape + index + image push
│ └── image-only.yml # On-demand code-only ship │ └── image-only.yml # On-demand code-only ship cycle
├── scrape/ ├── scrape/
│ ├── README.md # Product-specific scraper goes here │ ├── runner.py # Dispatches `--source <id>`
│ └── changelog.py # Reusable: --json, --history-out │ ├── changelog.py # Reusable: --json, --history-out
│ └── sources/
│ ├── bayer.py # cropscience.bayer.us Next.js scraper
│ └── epa_ppls.py # EPA PPLS pagination + label PDFs
├── rag/ ├── rag/
│ ├── embeddings.py # Ollama embedder, swappable │ ├── embeddings.py # nomic-embed-text via Ollama
│ ├── chunk.py # Chunker — adjust per page format │ ├── chunk.py # Chunker w/ EPA-reg-number preamble
│ ├── index.py # Builds Chroma + (optionally) BM25 │ ├── index.py # Chroma + BM25 builder
│ └── bm25.py # SQLite FTS5 lexical index │ └── bm25.py # FTS5 lexical index
├── docs_mcp/ ├── docs_mcp/
│ ├── server.py # FastMCP server with stub tools │ ├── server.py # FastMCP — hybrid+rerank
│ ├── lessons.md # Curated knowledge layer
│ └── usage.py # TimedCall + JSONL telemetry │ └── usage.py # TimedCall + JSONL telemetry
├── eval/ ├── eval/
│ ├── queries.jsonl.example # Curate ~25 hand-labeled queries │ ├── queries.jsonl # 35 golden queries
│ ├── retrievers.py # Retriever protocol + implementations │ ├── retrievers.py # 5 named configurations
│ └── run_eval.py # MRR / Recall@k / nDCG@k harness │ ├── run_eval.py # MRR / Recall@k / nDCG@k
│ └── results/ # Baseline + with_rerank measurements
├── scripts/ ├── scripts/
│ ├── usage_report.py # Standalone log analyzer │ ├── usage_report.py
│ └── registry_gc.py # Container registry cleanup │ └── registry_gc.py # Container registry cleanup
└── deploy/ └── corpus/ # Committed scrape output (CI-refreshed)
└── docker-compose.yml # Hosting stack: MCP + reranker + Watchtower ├── bayer/
└── epa_ppls/
``` ```
## What's product-specific (must implement) ## Infrastructure
- `scrape/` — the scraper itself. The template gives you the corpus - **Registry**: pushes to `192.168.0.2:1234` (LAN, no CF body cap); deploys pull `git.jpaul.io/justin/crop-chem-docs:latest` (public, CF tunnel). Also tagged `:<sha12>` for rollback pinning and `:corpus-YYYY.MM.DD` for snapshot pinning.
layout contract and a working `changelog.py`; the actual extraction - **Embedder pool (CI)**: 3 GPU-pinned Ollama endpoints, weighted toward `.0.125` (RTX 40-series).
logic is yours. - **Reranker**: shared `llama-rerank` sidecar on trashpanda's Tesla P4 (`jina-reranker-v2-base-multilingual` via llama.cpp). Same container serves crop-chem-docs and seed-mcp.
- The corpus on disk (gitignored; rebuilt by CI). - **PRODUCT_NAME**: `crop_chem` — used in `crop_chem_docs` Chroma collection, `bm25/crop_chem_docs.db`, and the `crop_chem_api_lessons` tool name.
- The reranker GGUF model and llama.cpp container (commented in
`deploy/docker-compose.yml`).
- The reverse proxy / TLS layer in front of the public endpoint.
- The hand-curated knowledge surface (your product's API gotchas,
example scripts, anything the LLM should know that the docs
don't say).
## What's NOT product-specific (works as-is) ## Deploy mechanics
- FastMCP server skeleton + tool decoration pattern Same Watchtower auto-deploy chain as seed-mcp. On every push to `main` that touches `docs_mcp/`, `rag/`, `scrape/`, `requirements.txt`, `Dockerfile`, or `sources.json`:
- Chroma + Ollama embedding pipeline
- BM25 / SQLite FTS5 lexical index
- Hybrid retrieval (RRF) + reranker integration
- Eval harness (Retriever protocol, MRR/Recall/nDCG)
- Usage logging (TimedCall, JSONL, daily rotation)
- CI workflow shape (weekly + on-demand, retry-on-race, three-tag
image scheme)
- Registry GC script
- Standard tools: `search_docs`, `get_page`, `list_versions`,
`diff_versions`, `bundle_changelog`, `weekly_digest`,
`find_doc_inconsistencies`, etc.
## License 1. `image-only.yml` checks out main + committed corpus
2. Rebuilds Chroma + BM25 (~few min on the GPU pool)
3. `docker build` + push three tags to the LAN registry
4. Links the package to the repo via Gitea API
5. Watchtower on trashpanda polls `:latest` every 5 min → recreates `drawbar-backend-chem-mcp-1`
Internal template. Adjust before publishing. Corpus refresh runs monthly via `refresh.yml`. EPA PPLS is the slow source — ~hours at 1 req/sec at full scale.
## Sibling
[`seed-mcp`](https://git.jpaul.io/justin/seed-mcp) covers the row-crop seed-variety + yield-trial side of the advisor's tool catalog. Both MCPs are docs-mcp-template clones running side-by-side on trashpanda, sharing the Ollama pool and the `llama-rerank` sidecar.
See [`CLAUDE.md`](./CLAUDE.md) for canonical sidecar schemas, the EPA reg-number normalization rules, and label-supersession ordering.