fix: unified_search + ai_proactive get API key from DB, fix model names for Ollama Cloud

- query_understanding.py: get API key/base_url/provider_type from ai_providers DB - embedding.py: get API key from DB, pass db+tenant_id through call chain - routes.py: pass db+tenant_id to llm_analyze_query and llm_aggregate_results - search_engine.py: pass db+tenant_id to generate_embedding - unified_search/jobs.py: pass db+tenant_id to generate_embedding - Fix all default model names: ollama/deepseek-v4 -> ollama/deepseek-v4-flash - Ollama Cloud has no embedding endpoint; embedding calls fail gracefully
2026-07-19 02:22:25 +02:00
parent ef4f0cc494
commit 4a43745b50
9 changed files with 147 additions and 37 deletions
@@ -87,7 +87,7 @@ async def index_file(ctx: dict[str, Any], file_id: str) -> None:
            embedding_text = f"{name} {content_text[:5000]}"

            if embedding_text.strip():
-                embedding = await generate_embedding(embedding_text)
+                embedding = await generate_embedding(embedding_text, db=db, tenant_id=tenant_id)
                if embedding:
                    await db.execute(
                        text("UPDATE files SET embedding = cast(:emb AS vector) WHERE id = :fid"),