Files
ai-service/README.md
Grendgi 24c5d89c7b
All checks were successful
CI / test (push) Successful in 13s
Build and Deploy / build-and-deploy (push) Successful in 20s
Add generic LLM worker
2026-06-08 13:52:29 +03:00

80 lines
2.7 KiB
Markdown

# AI Service
Technical AI job service for Portal workloads.
The first version owns only AI job lifecycle and metrics. Business data stays in
domain services such as `telephony`, `monitoring-tg` and `monitoring-pf`.
## Generic job contract
The service is intentionally domain-agnostic:
- `owner_service` names the caller, for example `telephony`, `monitoring-tg`,
`monitoring-pf` or a future Portal module.
- `owner_ref` is the caller's stable object reference, for example
`beeline/{call_id}` or `channel/{message_id}`.
- `task_type` describes the technical task class, for example
`transcribe`, `call_analysis`, `tg_analysis`, `pf_competitor_analysis`.
- `model_profile` selects a runtime profile, for example `whisperx`,
`qwen2.5-14b`, `vision`, or a future provider profile.
- `input` and `result` are JSON payloads owned by the caller and worker.
This keeps AI service as shared infrastructure rather than a telephony-specific
service.
## Built-in workers
The first built-in worker processes `llm_chat` and `chat_completion` jobs whose
`model_profile` equals `LLM_MODEL`.
Input can be either explicit messages:
```json
{
"messages": [
{"role": "system", "content": "Answer as JSON."},
{"role": "user", "content": "Classify this text"}
],
"max_tokens": 256
}
```
or compact `system` / `user` fields. The completed job result contains
`content`, `model`, `usage` and `duration_ms`.
## API
- `POST /api/v1/jobs` creates one job.
- `POST /api/v1/jobs/batch` creates many jobs with shared defaults.
- `POST /api/v1/jobs/claim` atomically claims pending jobs for a worker.
- `GET /api/v1/jobs/{id}` returns technical job state and result.
- `POST /api/v1/jobs/{id}/complete` stores a successful job result.
- `POST /api/v1/jobs/{id}/fail` stores a failed job category and message.
- `POST /api/v1/jobs/{id}/retry` resets failed/running jobs to `pending`.
- `GET /api/v1/stats` returns queue and error counters.
- `GET /api/v1/providers/status` checks configured AI providers without
returning secrets.
- `GET /healthz` returns process health.
- `GET /readyz` checks PostgreSQL readiness.
## Configuration
- `HTTP_HOST`, default `0.0.0.0`
- `HTTP_PORT`, default `8080`
- `DATABASE_URL`, required
- `MIGRATE_ON_START`, default `true`
- `LLM_BASE_URL`, primary OpenAI-compatible LLM endpoint
- `LLM_API_KEY`, primary LLM API key
- `LLM_MODEL`, default `qwen2.5-14b`
- `LLM_TIMEOUT`, default `5m`
- `WHISPERX_URL`, WhisperX endpoint for transcription jobs
- `WORKER_ID`, default hostname
- `WORKER_POLL_INTERVAL`, default `2s`
- `WORKER_CLAIM_LIMIT`, default `4`
## Next integration step
`telephony` should first mirror low-risk analysis jobs into this service while
continuing local processing. Remote execution can then be enabled by feature
flag per task type.