README.md

@@ -114,10 +114,10 @@ docker exec -it ai-ollama ollama pull toshk0/nomic-embed-text-v2-moe:Q6_K
 
 ```bash
 # 检查服务状态
-docker compose ps
+docker ps
 
 # 查看后端日志，找到自动生成的 API Key
-docker compose logs -f ai-service | grep "Default API Key"
+docker logs -f ai-service | grep "Default API Key"
 ```
 
 > **重要**: 后端首次启动时会自动生成一个默认 API Key，请从日志中复制该 Key，用于前端配置。

ai-service/app/core/qdrant_client.py

@@ -8,7 +8,7 @@ import logging
 from typing import Any
 
 from qdrant_client import AsyncQdrantClient
-from qdrant_client.models import Distance, PointStruct, VectorParams, MultiVectorConfig
+from qdrant_client.models import Distance, PointStruct, VectorParams, QueryRequest
 
 from app.core.config import get_settings
 
@@ -61,8 +61,7 @@ class QdrantClient:
         collection_name = self.get_collection_name(tenant_id)
 
         try:
-            collections = await client.get_collections()
-            exists = any(c.name == collection_name for c in collections.collections)
+            exists = await client.collection_exists(collection_name)
 
             if not exists:
                 if use_multi_vector:
@@ -213,36 +212,42 @@ class QdrantClient:
             try:
                 logger.info(f"[AC-AISVC-10] Searching in collection: {collection_name}")
                 
+                exists = await client.collection_exists(collection_name)
+                if not exists:
+                    logger.warning(f"[AC-AISVC-10] Collection {collection_name} does not exist")
+                    continue
+                
                 try:
-                    results = await client.search(
+                    results = await client.query_points(
                         collection_name=collection_name,
-                        query_vector=(vector_name, query_vector),
+                        query=query_vector,
+                        using=vector_name,
                         limit=limit,
                         with_vectors=with_vectors,
+                        score_threshold=score_threshold,
                     )
                 except Exception as e:
-                    if "vector name" in str(e).lower() or "Not existing vector" in str(e):
+                    if "vector name" in str(e).lower() or "Not existing vector" in str(e) or "using" in str(e).lower():
                         logger.info(
                             f"[AC-AISVC-10] Collection {collection_name} doesn't have vector named '{vector_name}', "
                             f"trying without vector name (single-vector mode)"
                         )
-                        results = await client.search(
+                        results = await client.query_points(
                             collection_name=collection_name,
-                            query_vector=query_vector,
+                            query=query_vector,
                             limit=limit,
                             with_vectors=with_vectors,
+                            score_threshold=score_threshold,
                         )
                     else:
                         raise
                 
                 logger.info(
-                    f"[AC-AISVC-10] Collection {collection_name} returned {len(results)} raw results"
+                    f"[AC-AISVC-10] Collection {collection_name} returned {len(results.points)} raw results"
                 )
 
                 hits = []
-                for result in results:
-                    if score_threshold is not None and result.score < score_threshold:
-                        continue
+                for result in results.points:
                     hit = {
                         "id": str(result.id),
                         "score": result.score,

ai-service/pyproject.toml

@@ -14,7 +14,7 @@ dependencies = [
     "tenacity>=8.2.0",
     "sqlmodel>=0.0.14",
     "asyncpg>=0.29.0",
-    "qdrant-client>=1.7.0",
+    "qdrant-client>=1.9.0,<2.0.0",
     "tiktoken>=0.5.0",
     "openpyxl>=3.1.0",
     "python-docx>=1.1.0",