Chris-o-O bolts legal-tuned search and a wider model menu onto mike-intell

Two upgrades in one move: find documents by meaning, and pick from a much larger roster of AI models.

searchintegration

Chris-o-O added semantic search to this fork. Instead of matching keywords, it finds documents by meaning, powered by Voyage AI, a vendor whose models are tuned specifically for legal text. Results keep their page numbers attached, so a hit tells you not just which document but where in it the relevant passage sits.

The second piece is a wider choice of AI models. Through OpenRouter, a service that routes requests to many providers behind a single connection, users can now reach GPT-4o, Mistral, Llama and others alongside the engines already supported, each with their own key. One caveat worth flagging: documents uploaded before this lands won't appear in semantic search until they're re-indexed, so don't assume your back catalogue is covered on day one.

So what Anyone who lives in document review should watch this - meaning-based search plus the freedom to swap AI engines is a genuinely practical pairing.

View this fork on GitHub →

Spotted something wrong? Or know the PR text has fresher detail than the writeup above?

Commits in this thread

1 commit from Chris-o-O/mike-intell, oldest first. Source extracted verbatim from the harvested git log.

SHA Subject Author Date

3279a584 Add OpenRouter multi-model support and Voyage AI semantic search Claude 2026-05-07 ↗ GitHub

SHA	Subject	Author	Date
`3279a584`	Add OpenRouter multi-model support and Voyage AI semantic search	Claude	2026-05-07	↗ GitHub
commit body OpenRouter: extends the LLM provider abstraction to support GPT-4o, GPT-4 Turbo, Mistral Large, Llama 3.3 70B, and Gemma 3 27B via a single OpenRouter API key. Follows the same provider pattern as Claude and Gemini - new openrouter.ts adapter, model routing by prefix, per-user API key stored in user_profiles, and full UI integration (model toggle, availability checks, account settings key field). Semantic search: adds Voyage AI embeddings (voyage-law-2, optimised for legal documents) to index document chunks at upload time (fire-and-forget, controlled by VOYAGE_API_KEY env var). Chunks are stored in a new document_chunks pgvector table. A /search/semantic endpoint and a semantic_search LLM tool enable concept-level retrieval. A new SemanticSearchWidget in ProjectPage exposes document search by meaning. https://claude.ai/code/session_01NJxa5NasJ9qhaMkzEyqr2u

commit body

OpenRouter: extends the LLM provider abstraction to support GPT-4o,
GPT-4 Turbo, Mistral Large, Llama 3.3 70B, and Gemma 3 27B via a
single OpenRouter API key. Follows the same provider pattern as Claude
and Gemini - new openrouter.ts adapter, model routing by prefix, per-user
API key stored in user_profiles, and full UI integration (model toggle,
availability checks, account settings key field).

Semantic search: adds Voyage AI embeddings (voyage-law-2, optimised for
legal documents) to index document chunks at upload time (fire-and-forget,
controlled by VOYAGE_API_KEY env var). Chunks are stored in a new
document_chunks pgvector table. A /search/semantic endpoint and a
semantic_search LLM tool enable concept-level retrieval. A new
SemanticSearchWidget in ProjectPage exposes document search by meaning.

https://claude.ai/code/session_01NJxa5NasJ9qhaMkzEyqr2u

Capture this thread into my fork

Download a single Markdown prompt that tells Claude how to port every commit above into your working tree — adapting paths and structure to match your repo. Run it via claude -p < capture-thread-172.md from inside the repo you want the changes in.

⬇ Download capture-thread-172.md