|
|
8ef0c93e47
|
feat: migrate to typed messages, drop base64
CI / Lint (pull_request) Failing after 1m22s
CI / Test (pull_request) Failing after 1m21s
CI / Release (pull_request) Has been skipped
CI / Notify (pull_request) Successful in 1s
- Switch OnMessage → OnTypedMessage with natsutil.Decode[messages.VoiceRequest]
- Return *messages.VoiceResponse with raw []byte audio (no base64)
- Use messages.DocumentSource for RAG sources
- Remove strVal/boolVal helpers
- Add .dockerignore, GOAMD64=v3 in Dockerfile
- Update tests for typed structs (7 tests pass)
|
2026-02-20 07:10:51 -05:00 |
|
|
|
2e66cac1e9
|
feat: rewrite voice-assistant in Go
Replace Python voice assistant with Go for smaller container images.
Uses handler-base Go module for NATS, health, telemetry, and all service clients.
- Full pipeline: STT → embed → Milvus → rerank → LLM → TTS
- Base64 audio encode/decode
- Dockerfile: multi-stage golang:1.25-alpine → scratch
- CI: Gitea Actions with lint/test/release/docker/notify
|
2026-02-19 18:00:58 -05:00 |
|
|
|
77d6822a63
|
refactor: consolidate to handler-base, migrate to pyproject.toml, add tests
|
2026-02-02 07:10:54 -05:00 |
|
|
|
f0b626a5e7
|
feat: Add voice assistant handler and Kubeflow pipeline
- voice_assistant.py: Standalone NATS handler with full RAG pipeline
- voice_assistant_v2.py: Handler-base implementation
- pipelines/voice_pipeline.py: KFP SDK pipeline definitions
- Dockerfiles for both standalone and handler-base versions
Pipeline: STT → Embeddings → Milvus → Rerank → LLM → TTS
|
2026-02-01 20:32:37 -05:00 |
|
