上传文件至 kg_lab_6.13

6.17 更新对检索工程数据复杂表达式的能力

kg_lab_6.13/vector_lab.py

@@ -1,12 +1,49 @@
 import os
 from langchain_community.vectorstores import FAISS
 from langchain_huggingface import HuggingFaceEmbeddings
+from langchain.embeddings.base import Embeddings
+from openai import OpenAI
+import requests
+import httpx
+import logging
+
+class SiliconFlowEmbeddings(Embeddings):
+    """SiliconFlow嵌入模型封装"""
+    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):
+        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):
+        return self._embed(texts)
+
+    def embed_query(self, text):
+        return self._embed([text])[0]
+
+
+# embeddings = Embedding(url="http://10.1.16.39:9995/v1", api_key="xxx", model_name="bge-m3")
+embeddings  = SiliconFlowEmbeddings(api_key="xxx")
 
 with open("./data/data.txt", 'r', encoding='utf-8') as file:
     txt_list = [line.strip() for line in file]
 
-embedding_path = "/data/Z_LLM_data/Embed_data/bge-m3"
-embeddings = HuggingFaceEmbeddings(model_name=embedding_path)
+# embedding_path = "/data/Z_LLM_data/Embed_data/bge-m3"
+# embeddings = HuggingFaceEmbeddings(model_name=embedding_path)
 
 faiss_archived = "./data/faiss_data/data"
 vectorstore_txt_faiss = FAISS.from_texts(txt_list, embeddings)