Update app.py

app.py

@@ -4,11 +4,9 @@ from chromadb.utils import embedding_functions
 from PyPDF2 import PdfReader
 from gradio_client import Client
 
-
-# Starte ChromaDB
 # Initialisiere ChromaDB
-#client_chroma = chromadb.Client()
-client_chroma = chromadb.PersistentClient(path = "./tmp", settings = None,)
+client_chroma = chromadb.Client()
+#client_croma = chromadb.PersistentClient(path="/")
 collection_name = "pdf_collection"
 collection = client_chroma.get_or_create_collection(name=collection_name)
 
@@ -16,34 +14,14 @@ collection = client_chroma.get_or_create_collection(name=collection_name)
 embedding_function = embedding_functions.DefaultEmbeddingFunction()
 
 client = Client("Qwen/Qwen2.5-72B-Instruct")
-def ask_llm(llm_prompt_input):
-    # Erstelle Embedding für den Prompt
-    query_embedding = embedding_function([llm_prompt_input])[0]
-    
-    # Führe die Ähnlichkeitssuche durch
-    results = collection.query(
-        query_embeddings=[query_embedding],
-        n_results=3
-    )
-    
-    # Formatiere die Ergebnisse
-    formatted_results = []
-    for i, doc in enumerate(results["documents"][0]):
-        metadata = results["metadatas"][0][i]
-        filename = metadata["filename"]
-        formatted_results.append(f"{doc}\n")
-
-    #queri = "\n".join(formatted_results)
-    #return "\n".join(formatted_results)
-    print(join(formatted_results))
-    
+def ask_llm(llm_prompt_input): 
     result = client.predict(
-		query=llm_prompt_input,
+		query=f"{llm_prompt_input}",
 		history=[],
 		system="You are Qwen, created by Alibaba Cloud. You are a helpful assistant.",
 		api_name="/model_chat"
 )
-    
+    print(result)
     return result
    
 def process_pdf(file):