Update app.py

app.py

@@ -87,7 +87,6 @@ from langchain.document_loaders import DirectoryLoader, TextLoader
 from langchain.embeddings import HuggingFaceEmbeddings
 from langchain.indexes import VectorstoreIndexCreator
 from langchain.indexes.vectorstore import VectorStoreIndexWrapper
-from langchain.llms import HuggingFaceLLM
 from langchain.text_splitter import CharacterTextSplitter
 
 __import__('pysqlite3')
@@ -97,6 +96,7 @@ sys.modules['sqlite3'] = sys.modules.pop('pysqlite3')
 from langchain.vectorstores import Chroma
 import gradio as gr
 from transformers import pipeline
+from sentence_transformers import SentenceTransformer
 
 docs = []
 
@@ -118,11 +118,23 @@ splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=10)
 docs = splitter.split_documents(docs)
 
 # Convert the document chunks to embedding and save them to the vector store
-vectorstore = Chroma.from_documents(docs, embedding=HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2"), persist_directory="./data")
+embedding_model = SentenceTransformer("sentence-transformers/all-MiniLM-L6-v2")
+embeddings = HuggingFaceEmbeddings(embedding_model=embedding_model)
+vectorstore = Chroma.from_documents(docs, embedding=embeddings, persist_directory="./data")
 vectorstore.persist()
 
-# Load the Hugging Face model
-llm = HuggingFaceLLM(pipeline("text-generation", model="EleutherAI/gpt-neo-2.7B"))
+# Load the Hugging Face model for text generation
+generator = pipeline("text-generation", model="EleutherAI/gpt-neo-2.7B")
+
+class HuggingFaceLLMWrapper:
+    def __init__(self, generator):
+        self.generator = generator
+    
+    def __call__(self, prompt, max_length=512):
+        result = self.generator(prompt, max_length=max_length, num_return_sequences=1)
+        return result[0]['generated_text']
+
+llm = HuggingFaceLLMWrapper(generator)
 
 chain = ConversationalRetrievalChain.from_llm(
     llm,
@@ -159,3 +171,4 @@ with gr.Blocks() as demo:
 demo.launch(debug=True)
 
 
+