Update app.py

app.py

@@ -16,7 +16,7 @@ token=""
 repo_id = "mistralai/Mixtral-8x7B-Instruct-v0.1"
 emb = "sentence-transformers/all-mpnet-base-v2"
 hf = HuggingFaceEmbeddings(model_name=emb)
-db = Chroma(persist_directory="./chroma_langchain_db")
+db = Chroma(persist_directory="./chroma_langchain_db",HuggingFaceEmbeddings(model_name=emb))
 #db.persist()
 # Load the document, split it into chunks, embed each chunk and load it into the vector store.
 #raw_documents = TextLoader('state_of_the_union.txt').load()
@@ -25,7 +25,7 @@ def embed_fn(inp):
     documents = text_splitter.split_text(inp)
     out_emb= hf.embed_documents(documents)
     string_representation = dumps(out_emb, pretty=True)
-    db.from_texts(documents,HuggingFaceEmbeddings(model_name=emb))
+    db.from_texts(documents)
 def proc_doc(doc_in):
     for doc in doc_in:
         if doc.endswith(".txt"):
@@ -57,11 +57,13 @@ def read_pdf(pdf_path):
     return text
 def run_llm(input_text,history):
     MAX_TOKENS=20000
-    qur= hf.embed_query(input_text)
-    docs = db.similarity_search_by_vector(qur, k=3)
-    
-    print(docs)
-
+    try:
+        qur= hf.embed_query(input_text)
+        docs = db.similarity_search_by_vector(qur, k=3)
+        
+        print(docs)
+    except Exception as e:
+        print(e)
     callbacks = [StreamingStdOutCallbackHandler()]  
     llm = HuggingFaceEndpoint(  
     endpoint_url=repo_id,