сделал первые 3 задачи из todo_people.md

search/main.py

@@ -270,6 +270,111 @@ async def qdrant_search(
     return response.points
 
 
+async def qdrant_search_dense_only(
+    client: AsyncQdrantClient,
+    dense_vector: list[float],
+    question_data: Question,
+) -> Any | None:
+    must_conditions: []
+
+    if question_data.date_range:
+        must_conditions.append(
+            models.FieldCondition(
+                key="metadata.start",
+                range=models.Range(
+                    gte=question_data.date_range.from_,
+                    lte=question_data.date_range.to_,
+                ),
+            )
+        )
+
+    if question_data.asker:
+        must_conditions.append(
+            models.FieldCondition(
+                key="metadata.participants",
+                match=models.MatchValue(value=question_data.asker),
+            )
+        )
+
+    search_filter = models.Filter(must=must_conditions) if must_conditions else None
+
+    response = await client.query_points(
+        collection_name=QDRANT_COLLECTION_NAME,
+        prefetch=[
+            models.Prefetch(
+                query=dense_vector,
+                using=QDRANT_DENSE_VECTOR_NAME,
+                limit=DENSE_PREFETCH_K,
+                filter=search_filter,
+            ),
+        ],
+        query=models.FusionQuery(fusion=models.Fusion.RRF),
+        limit=RETRIEVE_K,
+        with_payload=True,
+    )
+
+    if not response.points:
+        return None
+
+    return response.points
+
+
+def collect_query_variants(question: Question) -> list[str]:
+    variants: list[str] = []
+    seen: set[str] = set()
+
+    def add_query(text: str | None) -> None:
+        if text is None:
+            return
+        normalized = text.strip()
+        if not normalized:
+            return
+        if normalized in seen:
+            return
+        seen.add(normalized)
+        variants.append(normalized)
+
+    add_query(question.search_text)
+    add_query(question.text)
+
+    for variant in question.variants or []:
+        add_query(variant)
+
+    return variants
+
+
+def collect_hyde_queries(question: Question, base_queries: list[str]) -> list[str]:
+    hyde_queries: list[str] = []
+    seen: set[str] = set(base_queries)
+
+    for hyde_query in question.hyde or []:
+        normalized = hyde_query.strip()
+        if not normalized:
+            continue
+        if normalized in seen:
+            continue
+        seen.add(normalized)
+        hyde_queries.append(normalized)
+
+    return hyde_queries
+
+
+def deduplicate_points(points: list[Any]) -> list[Any]:
+    unique_points: list[Any] = []
+    seen_ids: set[str] = set()
+
+    for point in points:
+        point_id = str(getattr(point, "id", ""))
+        if not point_id:
+            continue
+        if point_id in seen_ids:
+            continue
+        seen_ids.add(point_id)
+        unique_points.append(point)
+
+    return unique_points
+
+
 def extract_message_ids(point: Any) -> list[str]:
     payload = point.payload or {}
     metadata = payload.get("metadata") or {}
@@ -334,18 +439,31 @@ async def health() -> dict[str, str]:
 
 @app.post("/search", response_model=SearchAPIResponse)
 async def search(payload: SearchAPIRequest) -> SearchAPIResponse:
-    query = payload.question.text.strip()
+    queries = collect_query_variants(payload.question)
-    if not query:
+    if not queries:
-        raise HTTPException(status_code=400, detail="question.text is required")
+        raise HTTPException(status_code=400, detail="question.search_text or question.text is required")
 
+    hyde_queries = collect_hyde_queries(payload.question, queries)
+    query = queries[0]
     client: httpx.AsyncClient = app.state.http
     qdrant: AsyncQdrantClient = app.state.qdrant
 
-    dense_vector = await embed_dense(client, query)
+    all_points: list[Any] = []
-    sparse_vector = await embed_sparse(query)
+    for query_variant in queries:
-    best_points = await qdrant_search(qdrant, dense_vector, sparse_vector, payload.question)
+        dense_vector = await embed_dense(client, query_variant)
+        sparse_vector = await embed_sparse(query_variant)
+        points = await qdrant_search(qdrant, dense_vector, sparse_vector, payload.question)
+        if points:
+            all_points.extend(list(points))
 
-    if best_points is None:
+    for hyde_query in hyde_queries:
+        hyde_dense_vector = await embed_dense(client, hyde_query)
+        hyde_points = await qdrant_search_dense_only(qdrant, hyde_dense_vector, payload.question)
+        if hyde_points:
+            all_points.extend(list(hyde_points))
+
+    best_points = deduplicate_points(all_points)
+    if not best_points:
         return SearchAPIResponse(results=[])
 
     best_points = await rerank_points(client, query, list(best_points))