Update agent.py

agent.py

@@ -17,6 +17,10 @@ from langchain_core.tools import tool
 from langchain.tools.retriever import create_retriever_tool
 from supabase.client import Client, create_client
 from sentence_transformers import SentenceTransformer
+from sentence_transformers import SentenceTransformer
+from langchain.embeddings.base import Embeddings
+from typing import List
+import numpy as np
 
 load_dotenv()
 
@@ -122,14 +126,20 @@ with open("system_prompt.txt", "r", encoding="utf-8") as f:
 # System message
 sys_msg = SystemMessage(content=system_prompt)
 
-# Initialize SentenceTransformer with max_seq_length
-sentence_transformer = SentenceTransformer(
-    "sentence-transformers/all-mpnet-base-v2",
-    max_seq_length=2048  # Set max sequence length here
-)
+# Custom embedding class
+from sentence_transformers import SentenceTransformer
+from langchain_huggingface import HuggingFaceEmbeddings
+from supabase import create_client, Client
+from langchain_community.vectorstores import SupabaseVectorStore
+from langchain.tools import create_retriever_tool
+import os
+
+# Initialize SentenceTransformer and set max_seq_length
+sentence_transformer = SentenceTransformer("sentence-transformers/all-mpnet-base-v2")
+sentence_transformer.max_seq_length = 2048  # Set max sequence length
 
-# Initialize embeddings with the custom SentenceTransformer model
-embeddings = HuggingFaceEmbeddings(model=sentence_transformer)
+# Initialize embeddings with the model name (dim=768)
+embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2")
 
 # Initialize Supabase client
 supabase: Client = create_client(
@@ -137,19 +147,19 @@ supabase: Client = create_client(
     os.environ.get("SUPABASE_SERVICE_KEY")
 )
 
-# Create vector store
+# Initialize Supabase vector store
 vector_store = SupabaseVectorStore(
     client=supabase,
     embedding=embeddings,
     table_name="documents",
-    query_name="match_documents_langchain",
+    query_name="match_documents_langchain"
 )
 
 # Create retriever tool
 create_retriever_tool = create_retriever_tool(
     retriever=vector_store.as_retriever(),
     name="Question Search",
-    description="A tool to retrieve similar questions from a vector store.",
+    description="A tool to retrieve similar questions from a vector store."
 )