prova chroma

app.py

@@ -1,4 +1,4 @@
-import os
+'''import os
 import gradio as gr
 import requests
 import inspect
@@ -198,4 +198,48 @@ if __name__ == "__main__":
     print("-"*(60 + len(" App Starting ")) + "\n")
 
     print("Launching Gradio Interface for Basic Agent Evaluation...")
-    demo.launch(debug=True, share=False)
+    demo.launch(debug=True, share=False)
+'''
+import json
+from langchain_chroma import Chroma
+from langchain_huggingface import HuggingFaceEmbeddings
+from langchain.tools.retriever import create_retriever_tool
+
+import chromadb
+chromadb.config.Settings.telemetry_enabled = False
+
+
+if __name__=='__main__':
+    with open('metadata.jsonl', 'r') as jsonl_file:
+        json_list = list(jsonl_file)
+
+    json_QA = []
+    for json_str in json_list:
+        json_data = json.loads(json_str)
+        json_QA.append(json_data)
+
+    # Usa gli stessi embeddings
+    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2")
+    print(1)
+
+    # Inizializza Chroma
+
+    from langchain.schema import Document
+    from langchain_community.vectorstores import Chroma
+
+    # Prepara la lista di documenti
+    docs = []
+    print("orig:",len(json_QA))
+    for sample in json_QA:
+        print(len(docs))
+        content = f"Question : {sample['Question']}\n\nFinal answer : {sample['Final answer']}"
+        metadata = {"source": sample['task_id']}
+        doc = Document(page_content=content, metadata=metadata)
+        docs.append(doc)
+
+    # Inizializza il vector store Chroma
+    vector_store = Chroma.from_documents(
+        documents=docs,
+        embedding=embeddings,
+        persist_directory="./chroma_db" 
+    )