添加search方法

nodes/chunk_and_embedding.py

@@ -57,7 +57,7 @@ def chunks_embedding(texts: list[str], api_key: str) -> list[list[float]]:
         
         if "output" in result and "embeddings" in result["output"]:
             embeddings_list = result["output"]["embeddings"]
-            embeddings_list.sort(key=lambda x: x["text_index"])
+            embeddings_list.sort(key=lambda x: x["text_index"]) # 按文本索引排序，确保顺序一致
             
             # --- 核心修复：对每个浮点数保留 8 位小数，解决精度过高报错 ---
             final_vectors = []

nodes/embedding.py

@@ -0,0 +1,46 @@
+import requests
+
+def chunks_embedding(texts: list[str], api_key: str) -> list[list[float]]:
+    if not texts:
+        return []
+
+    MODEL_NAME = "text-embedding-v4" 
+    url = "https://dashscope.aliyuncs.com/api/v1/services/embeddings/text-embedding/text-embedding"
+    headers = {
+        "Authorization": f"Bearer {api_key}",
+        "Content-Type": "application/json"
+    }
+    payload = {
+        "model": MODEL_NAME,
+        "input": {"texts": texts},
+        "parameters": {"text_type": "document", "dimension": 1536}
+    }
+
+    try:
+        response = requests.post(url, headers=headers, json=payload, timeout=60)
+        response.raise_for_status()
+        result = response.json()
+        
+        if "output" in result and "embeddings" in result["output"]:
+            embeddings_list = result["output"]["embeddings"]
+            embeddings_list.sort(key=lambda x: x["text_index"])
+            
+            # --- 核心修复：对每个浮点数保留 8 位小数，解决精度过高报错 ---
+            final_vectors = []
+            for item in embeddings_list:
+                # 将每个 float 限制在 8 位精度以内
+                rounded_vector = [round(float(val), 8) for val in item["embedding"]]
+                final_vectors.append(rounded_vector)
+            return final_vectors
+        else:
+            return [None] * len(texts)
+    except Exception as e:
+        print(f"Alibaba Embedding Error: {e}")
+        return [None] * len(texts)
+    
+def main(text: str, api_key: str):
+    
+    vector = chunks_embedding([text], api_key)[0]
+    return {
+        'vector': vector
+    }