feat: per-source RAG configuration (retrieval strategies, chunking, exposure, prescreen)

Introduces a per-source config contract that makes RAG behavior strategy-dispatched instead of a single hardcoded path. Every source gains a validated JSONB config; an empty/absent config reproduces current behavior byte-for-byte, and the whole path is gated by PER_SOURCE_RETRIEVAL_ENABLED.

Foundation: sources.config JSONB column + migration 0022_source_config; SourceConfig/ChunkingConfig/RetrievalConfig pydantic models (strict on write, lenient on read); ChunkerCreator and RetrieverCreator.register registries; config threaded through the upload routes, ingest/remote/connector workers, and reingest.

Retrieval: a Dispatcher groups sources by retriever key (all-classic collapses to today's single ClassicRAG under one shared token budget; non-classic retrievers get their own instance), removing the previous single-global-retriever collapse in stream_processor. Per-source chunks, score_threshold (honored for pgvector/mongodb, safely ignored elsewhere), and rephrase_query toggle. New PATCH /api/sources/<id>/config with team-aware (effective_write_owner) authz and a requires_reingest signal.

Chunking strategies: recursive, markdown, parent_child (selectable per source; re-ingest to apply). Search exposure: per-source prefetch vs agentic_tool for agentic/research agents. Map-reduce prescreen: optional LLM relevance pre-filter implemented as a composable post-retrieval stage that wraps any retriever.

Backend and frontend (shared Retrieval options panel + edit modal) with tests; backend suite and frontend vitest green. Excludes the wiki and GraphRAG flagships.
This commit is contained in:
Alex committed 2026-06-20 21:54:23 +01:00
1 parent cfda009be0
commit f6400cd736
53 files changed
+4313 -74

No files matched your search

+7 -4
View File
@@ -33,7 +33,7 @@ class TestIngestTask:
mock_worker.assert_called_once_with(
ANY, "dir", ["pdf"], "job1", "/path", "file.pdf", "user1",
file_name_map=None, idempotency_key=None, source_id=None,
file_name_map=None, config=None, idempotency_key=None, source_id=None,
)
assert result == {"status": "ok"}
@@ -50,7 +50,8 @@ class TestIngestTask:
mock_worker.assert_called_once_with(
ANY, "dir", ["pdf"], "job1", "/path", "file.pdf", "user1",
file_name_map=name_map, idempotency_key=None, source_id=None,
file_name_map=name_map, config=None, idempotency_key=None,
source_id=None,
)
@@ -66,7 +67,7 @@ class TestIngestRemoteTask:
mock_worker.assert_called_once_with(
ANY, {"url": "http://x"}, "job1", "user1", "web",
idempotency_key=None, source_id=None,
config=None, idempotency_key=None, source_id=None,
)
assert result == {"status": "ok"}
@@ -168,6 +169,7 @@ class TestIngestConnectorTask:
operation_mode="upload",
doc_id=None,
sync_frequency="never",
config=None,
idempotency_key=None,
source_id=None,
)
@@ -207,6 +209,7 @@ class TestIngestConnectorTask:
operation_mode="sync",
doc_id="doc1",
sync_frequency="daily",
config=None,
idempotency_key=None,
source_id=None,
)
@@ -600,7 +603,7 @@ class TestIngestIdempotency:
worker_calls = []
def _fake_worker(self, directory, formats, job_name, file_path,
filename, user, file_name_map=None,
filename, user, file_name_map=None, config=None,
idempotency_key=None, source_id=None):
worker_calls.append(filename)
return {"status": "ok", "directory": directory}