# Talie chatbot service

Architecture decisions live in [`docs/adr`](docs/adr). The first implementation
milestone is documented in the [ingestion vertical-slice plan](docs/plans/001-ingestion-vertical-slice.md).

## Provisioning the datastores

Both schema steps run as explicit deployment steps. The application performs no
DDL at startup — not for Postgres (ADR-0009) and not for Qdrant (ADR-0001,
"Collection provisioning").

```bash
docker compose up -d                          # Postgres, MinIO, Qdrant
uv run alembic upgrade head                   # Postgres schema
uv run python -m src.cli.qdrant_bootstrap     # the `chunks` collection
uv run fastapi dev src/main.py
```

Both commands are idempotent and safe to re-run. `qdrant_bootstrap` verifies an
existing collection against the pinned schema and exits non-zero on a mismatch,
rather than leaving a silently degraded sparse index in place.

## Local Langfuse

This repo includes a root-level development Compose file for Langfuse:

- [`docker-compose.langfuse.yml`](docker-compose.langfuse.yml)
- [`.env.langfuse.example`](.env.langfuse.example)

Start Langfuse locally:

```bash
cp .env.langfuse.example .env.langfuse
# edit .env.langfuse and replace CHANGE_ME values

docker compose --env-file .env.langfuse -f docker-compose.langfuse.yml up -d
```

Open:

```text
http://localhost:3000
```

If the chatbot app runs on your host machine, configure it with:

```env
LANGFUSE_HOST=http://localhost:3000
```

If the chatbot app later runs inside the same Compose project/network as
Langfuse, configure it with:

```env
LANGFUSE_HOST=http://langfuse-web:3000
```

A future app stack can be launched together with Langfuse using multiple Compose
files:

```bash
docker compose \
  -f docker-compose.yml \
  -f docker-compose.langfuse.yml \
  --env-file .env \
  --env-file .env.langfuse \
  up -d
```