Mahdi Bazrafshan
e693b9bbfc
Grounded Ask owns the product chat UI: persistent thread_id across a Chat Session, New chat / Continue conversation, and a sidebar that lists Conversations from the Conversation Record with formatted run metadata (timing, tokens, evidence chunks). Co-authored-by: Cursor <cursoragent@cursor.com>
1.3 KiB
1.3 KiB
Grounded Ask
Upload docs, ask one question, read the answer plus the passages it used.
Domain language: CONTEXT.md · product ADR: docs/adr/0001-separate-app-tenant-profiles.md · API Sources: tamasino-ai-api ADR-0023
Prerequisites
tamasino-ai-apirunning- A tenant API key with upload scopes and
threads:run:
cd ../tamasino-ai-api
uv run python -m src.cli.provision_tenant --slug acme --domain fire \
--scopes files:write,domains:read,domains:write,points:read,points:write,retrieval:read,threads:run
How to use (local)
- Open the app (usually
http://localhost:8502). - Connect — paste an API key that includes
files:write,domains:read,domains:write, andthreads:run(Hybrid Console’s key is fine if it has those). - Add documents — create or pick a topic (domain), upload CSV / Excel / Word, wait for “chunks indexed”.
- Ask — type a question → read the answer and Passages used.
Each ask is single-turn (no chat history). Questions search the whole tenant corpus.
Setup
cd tamasino-ai-grounded-ask
cp .env.example .env
uv sync
uv run streamlit run app.py
Connections are stored locally in data/tenant_profiles.json (gitignored).