Fix LangChain import compatibility for space runtime

csv_result.py

@@ -1,6 +1,6 @@
 # 1️⃣ Imports
 import pandas as pd
-from langchain.schema import Document
+from langchain_core.documents import Document
 import os
 from dotenv import load_dotenv
 from functions.data_to_vectors import create_vectorstore

functions/data_to_vectors.py

@@ -1,39 +1,12 @@
-# __package__ = "functions"
-# from langchain.text_splitter import RecursiveCharacterTextSplitter
-# from langchain_huggingface import HuggingFaceEmbeddings
-# from langchain_community.vectorstores import Chroma
-# from langchain.schema import Document
-# def create_vectorstore(text,store):
-#     print("data loaded......")
-#     documents = [Document(page_content=text)]
-#     # Chunk text
-#     text_splitter = RecursiveCharacterTextSplitter(
-#         chunk_size=500,
-#         chunk_overlap=200
-#     )
-#     docs_chunks = text_splitter.split_documents(documents)
-    
-#     # Embeddings
-#     embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
-    
-#     # Chroma vectorstore
-#     vectorstore = Chroma.from_documents(
-#         documents=docs_chunks,
-#         embedding=embeddings,
-#         persist_directory=store
-#     )
-#     print(f"✅ Stored {len(docs_chunks)} chunks in ChromaDB")
-#     return vectorstore
+__package__ = "functions"
 
-__package__ = "functions"
-
-from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_text_splitters import RecursiveCharacterTextSplitter
 from langchain_community.vectorstores import Chroma
-from langchain.schema import Document
+from langchain_core.documents import Document
+from langchain_core.embeddings import Embeddings
 from sentence_transformers import SentenceTransformer
-from langchain.embeddings.base import Embeddings  # 👈 base class
 
-# Custom wrapper for SentenceTransformer
+
 class SentenceTransformerEmbeddings(Embeddings):
     def __init__(self, model_name="sentence-transformers/all-MiniLM-L6-v2", device="cpu"):
         self.model = SentenceTransformer(model_name, device=device)
@@ -48,23 +21,16 @@ class SentenceTransformerEmbeddings(Embeddings):
 def create_vectorstore(text, store):
     print("data loaded......")
     documents = [Document(page_content=text)]
-    print(text)
-    # Chunk text
-    text_splitter = RecursiveCharacterTextSplitter(
-        chunk_size=500,
-        chunk_overlap=200
-    )
+
+    text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=200)
     docs_chunks = text_splitter.split_documents(documents)
 
-    # Use custom embedding wrapper
     embeddings = SentenceTransformerEmbeddings()
-
-    # Chroma vectorstore
     vectorstore = Chroma.from_documents(
         documents=docs_chunks,
         embedding=embeddings,
-        persist_directory=store
+        persist_directory=store,
     )
 
-    print(f"✅ Stored {len(docs_chunks)} chunks in ChromaDB")
+    print(f"Stored {len(docs_chunks)} chunks in ChromaDB")
     return vectorstore