saravanakumardb1 a77b3ff931 refactor(extraction-service): provider-agnostic transcription — OpenAI + Azure Speech + Mock ... - TranscriptionProvider interface with transcribe() + isConfigured() - OpenAITranscriptionProvider: Whisper API (existing behavior) - AzureTranscriptionProvider: Azure Speech REST API for short audio - MockTranscriptionProvider: deterministic results for testing - Factory: getSTT() singleton with env-driven auto-detection - STT_PROVIDER=openai|azure|mock (explicit) - Auto-detect: AZURE_SPEECH_KEY → azure, OPENAI_API_KEY → openai, else mock - Config: add STT_PROVIDER, AZURE_SPEECH_KEY, AZURE_SPEECH_REGION env vars - Route refactored: audio download (common) → provider.transcribe() (swappable) - deriveFilename() extracted to types.ts (shared by route + providers) - 35 transcription tests (was 12), 171 total passing - Follows same pattern as @bytelyst/llm provider abstraction		2026-04-06 11:30:22 -07:00
..
evals	docs(local-llm): update original setup doc to redirect to docs/ structure	2026-02-19 13:01:35 -08:00
python	fix(devops): harden local shared-service docker bring-up	2026-03-22 12:34:38 -07:00
src	refactor(extraction-service): provider-agnostic transcription — OpenAI + Azure Speech + Mock	2026-04-06 11:30:22 -07:00
.env.example	feat(extraction): scaffold extraction-service + @bytelyst/extraction package	2026-02-14 13:31:40 -08:00
Dockerfile	feat(extraction): back product rate limits with valkey	2026-03-31 08:08:53 +00:00
package.json	feat(extraction): back product rate limits with valkey	2026-03-31 08:08:53 +00:00
supervisord.conf	fix(extraction-service): run python sidecar on railway	2026-02-17 11:32:40 -08:00
tsconfig.json	feat(extraction): scaffold extraction-service + @bytelyst/extraction package	2026-02-14 13:31:40 -08:00