feat(ingestion): add bounded, benchmark-aligned embedding execution
Why: - Plan 001 Phase 4 needs batched, concurrency-bounded embedding wired into the inline upload path, with process-wide capacity/timeout/chunk-limit guards (ADR-0017). - The BM25 analyzer and dense-model config are ported from the `emet` evaluation lab, which benchmarked them against the real Farsi corpus (bm25-fa-norm-stop; nomic-embed-text-v2-moe at 768-dim; text-embedding-3-large at native 3072-dim), closing open items in ADR-0001/ADR-0005. Changes: - New: embedding ports, orchestration (embed_chunks), request-bounds helpers, and dense/sparse adapters (analyzers.py, bm25.py, openai_compatible.py). - upload.py now parses/chunks/embeds inline behind INGESTION_MAX_CONCURRENCY (503), INGESTION_TIMEOUT_SECONDS (504), and the chunk-count ceiling (413); every failure path still writes a terminal job row. - Lifespan builds and warms both dense embedders at startup (fail-soft) and creates the sparse embedder and concurrency semaphore. - httpx moves from dev to main dependencies (adapters use it directly). Impact: - Qdrant point upserts are still Phase 5 -- chunks_indexed stays 0. - New EMBEDDING_* env vars documented in .env.example; safe defaults. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
This commit is contained in:
@@ -17,10 +17,22 @@ from src.application.auth.errors import (
|
||||
TenantInactiveError,
|
||||
)
|
||||
from src.application.files.errors import FileTooLargeError, InvalidUploadError
|
||||
from src.application.ingestion.errors import DocumentParseError, UnsupportedSourceTypeError
|
||||
from src.application.ingestion.errors import (
|
||||
ChunkLimitExceededError,
|
||||
DocumentParseError,
|
||||
EmbedderError,
|
||||
IngestionAtCapacityError,
|
||||
IngestionTimeoutError,
|
||||
UnsupportedSourceTypeError,
|
||||
)
|
||||
|
||||
logger = structlog.get_logger(__name__)
|
||||
|
||||
# A fixed backoff hint, not a computed retry budget: ADR-0017 rejects a
|
||||
# request outright at capacity rather than queueing it, so there is no
|
||||
# in-process estimate of when a slot will free up to report instead.
|
||||
_CAPACITY_RETRY_AFTER_SECONDS = 1
|
||||
|
||||
# (exception type, status code, stable error code)
|
||||
_MAPPING: tuple[tuple[type[Exception], int, str], ...] = (
|
||||
(InvalidApiKeyError, status.HTTP_401_UNAUTHORIZED, "invalid_api_key"),
|
||||
@@ -30,6 +42,9 @@ _MAPPING: tuple[tuple[type[Exception], int, str], ...] = (
|
||||
(DocumentParseError, status.HTTP_400_BAD_REQUEST, "validation_error"),
|
||||
(UnsupportedSourceTypeError, status.HTTP_415_UNSUPPORTED_MEDIA_TYPE, "unsupported_media_type"),
|
||||
(FileTooLargeError, status.HTTP_413_CONTENT_TOO_LARGE, "payload_too_large"),
|
||||
(ChunkLimitExceededError, status.HTTP_413_CONTENT_TOO_LARGE, "payload_too_large"),
|
||||
(EmbedderError, status.HTTP_502_BAD_GATEWAY, "embedder_error"),
|
||||
(IngestionTimeoutError, status.HTTP_504_GATEWAY_TIMEOUT, "ingestion_timeout"),
|
||||
)
|
||||
|
||||
|
||||
@@ -66,6 +81,14 @@ def register_exception_handlers(app: FastAPI) -> None:
|
||||
|
||||
app.add_exception_handler(exc_type, _handler)
|
||||
|
||||
@app.exception_handler(IngestionAtCapacityError)
|
||||
def _capacity_handler(request: Request, exc: IngestionAtCapacityError) -> JSONResponse:
|
||||
return JSONResponse(
|
||||
status_code=status.HTTP_503_SERVICE_UNAVAILABLE,
|
||||
content=_envelope("ingestion_at_capacity", str(exc), _request_id(request)),
|
||||
headers={"Retry-After": str(_CAPACITY_RETRY_AFTER_SECONDS)},
|
||||
)
|
||||
|
||||
@app.exception_handler(RequestValidationError)
|
||||
def _validation_handler(request: Request, exc: RequestValidationError) -> JSONResponse:
|
||||
return JSONResponse(
|
||||
|
||||
Reference in New Issue
Block a user