上传文件至 /

4.3更新

utils.py

@@ -120,6 +120,17 @@ def get_keywords_v3(input_str):
     else:
         return None
 
+def get_keywords_v4(input_str):
+    import re
+    matches = re.findall(r'【(.*?)】', input_str)
+
+    # 获取第一个和第二个【】里的内容（索引为0和1）
+    first = matches[0] if len(matches) >= 1 else None
+    second = matches[1] if len(matches) >= 2 else None
+
+    return first, second
+
+
 
 def normalize_text(text: str, synonym_dict: dict) -> str:
     import re
@@ -141,3 +152,5 @@ def normalize_text(text: str, synonym_dict: dict) -> str:
 
 
 
+
+

vector_load.py

@@ -1,9 +1,44 @@
 import os
 from langchain_community.vectorstores import FAISS
-from langchain_huggingface import HuggingFaceEmbeddings
+# from langchain_huggingface import HuggingFaceEmbeddings
 
-embedding_path = "/data/Z_LLM_data/Embed_data/bge-m3"
-embeddings = HuggingFaceEmbeddings(model_name=embedding_path)
+# embedding_path = "/data/Z/Z_llm_dm/vector_data/bge-m3"
+# embeddings = HuggingFaceEmbeddings(model_name=embedding_path)
+
+
+from typing import List
+import requests
+from langchain.embeddings.base import Embeddings
+
+
+class SiliconFlowEmbeddings(Embeddings):
+    def __init__(self, api_key: str, model: str = "bge-m3"):
+        self.api_key = api_key
+        self.model = model
+        self.url = "http://10.1.16.39:9995/v1/embeddings"
+        self.headers = {
+            "Authorization": f"Bearer {self.api_key}",
+            "Content-Type": "application/json"
+        }
+
+    def _embed(self, input: List[str]) -> List[List[float]]:
+        payload = {
+            "model": self.model,
+            "input": input,
+            "encoding_format": "float"
+        }
+        response = requests.post(self.url, json=payload, headers=self.headers)
+        response.raise_for_status()
+        data = response.json()
+        return [item["embedding"] for item in data["data"]]
+
+    def embed_documents(self, texts: List[str]) -> List[List[float]]:
+        return self._embed(texts)
+
+    def embed_query(self, text: str) -> List[float]:
+        return self._embed([text])[0]
+
+embeddings = SiliconFlowEmbeddings(api_key="sk-ftnofbucchwnscojohyxwmfzgaykdxihafnlphohsinftkbr")
 
 def Mixed_retrieval(input_path):
     file_name = os.path.splitext(os.path.basename(input_path))[0]
@@ -33,6 +68,8 @@ def Mixed_retrieval(input_path):
 
     return retriever_txt_faiss1, retriever_txt_faiss2, retriever_txt_faiss3
 
+
+
 def interface_search(input_str, retriever_txt_faiss1, retriever_txt_faiss2, retriever_txt_faiss3):
     index_keyword1 = []
     for i in retriever_txt_faiss1.invoke(input_str):