feat: add chunk BM25 and reproducible RRF retrieval

backend/tests/test_vector_runtime.py

@@ -23,7 +23,7 @@ def test_real_local_model_vectors_retrieval_and_http_restart(migrated_database):
         "HF_HUB_DISABLE_IMPLICIT_TOKEN": "1",
         "TOKENIZERS_PARALLELISM": "false",
     }
-    query = {"query": "合成测试中交通安排应查阅哪份资料？"}
+    query = {"query": "合成测试中交通安排应查阅哪份资料？", "top_k": 3}
     with server(migrated_database, environment_overrides=options) as client:
         ids = []
         for topic, body in [
@@ -75,6 +75,18 @@ def test_real_local_model_vectors_retrieval_and_http_restart(migrated_database):
         assert {h["knowledge_id"] for h in first["results"]} == set(ids)
         assert all(-1 <= h["score"] <= 1 for h in first["results"])
         assert first["config"]["space"]["spec"]["revision"] == SMALL_ZH.revision
+        response = client.post(
+            "/api/retrieval/hybrid", json={**query, "candidate_k": 3}, timeout=60
+        )
+        assert response.status_code == 200, response.text
+        hybrid = response.json()
+        assert hybrid["vector_version_id"] == version["id"]
+        assert hybrid["text_index_version_id"] == text_["id"]
+        assert hybrid["config"]["space"]["spec"]["revision"] == SMALL_ZH.revision
+        assert {h["knowledge_id"] for h in hybrid["results"]} == set(ids)
+        assert hybrid["vector_candidates"]
+        keyword = client.post("/api/retrieval/chunks", json=query).json()
+        assert keyword["mode"] == "keyword_chunks" and keyword["results"]
     with migrated_database.connect() as c:
         assert (
             c.scalar(
@@ -89,3 +101,15 @@ def test_real_local_model_vectors_retrieval_and_http_restart(migrated_database):
         response = client.post("/api/retrieval/vector", json=query, timeout=60)
         assert response.status_code == 200, response.text
         assert response.json()["results"] == first["results"]
+        for result, endpoint in [(hybrid, "hybrid"), (keyword, "chunks")]:
+            assert client.get(f"/api/retrieval/runs/{result['run_id']}").json() == result
+            response = client.post(
+                f"/api/retrieval/{endpoint}",
+                json={**query, **({"candidate_k": 3} if endpoint == "hybrid" else {})},
+                timeout=60,
+            )
+            assert response.status_code == 200, response.text
+            assert response.json()["results"] == result["results"]
+            if endpoint == "hybrid":
+                assert response.json()["lexical_candidates"] == result["lexical_candidates"]
+                assert response.json()["vector_candidates"] == result["vector_candidates"]