Update app.py

app.py

@@ -2,7 +2,8 @@ import streamlit as st
 from dotenv import load_dotenv
 from PyPDF2 import PdfReader
 from langchain.text_splitter import CharacterTextSplitter
-from langchain.embeddings import OpenAIEmbeddings, HuggingFaceInstructEmbeddings, HuggingFaceEmbeddings
+from langchain.embeddings import OpenAIEmbeddings, HuggingFaceInstructEmbeddings
+from langchain.embeddings import HuggingFaceEmbeddings, SentenceTransformerEmbeddings
 from langchain.vectorstores import FAISS
 from langchain.memory import ConversationBufferMemory
 from langchain.chains import ConversationalRetrievalChain
@@ -43,8 +44,13 @@ def get_vector_store(text_chunks):
     
     # For Huggingface Embeddings
 
-    embeddings = HuggingFaceInstructEmbeddings(model_name = "hkunlp/instructor-xl")
+    #embeddings = HuggingFaceInstructEmbeddings(model_name = "hkunlp/instructor-xl")
+    #embeddings = HuggingFaceInstructEmbeddings(model_name = "sentence-transformers/all-MiniLM-L6-v2")
+    embeddings = HuggingFaceEmbeddings(model_name="all-MiniLM-L6-v2")
 
+    HUGGINGFACEHUB_API_TOKEN = "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"
+#model_id = "sentence-transformers/all-MiniLM-L6-v2"
+    
     vectorstore = FAISS.from_texts(texts = text_chunks, embedding = embeddings)
     
     return vectorstore
@@ -58,7 +64,14 @@ def get_conversation_chain(vector_store):
 
     # HuggingFace Model
 
-    llm = HuggingFaceHub(repo_id="tiiuae/falcon-40b-instruct", model_kwargs={"temperature":0.5, "max_length":512})
+    #llm = HuggingFaceHub(repo_id="tiiuae/falcon-40b-instruct", model_kwargs={"temperature":0.5, "max_length":512})
+    repo_id="HuggingFaceH4/starchat-beta"
+    llm = HuggingFaceHub(repo_id=repo_id,
+                     model_kwargs={"min_length":100,
+                                   "max_new_tokens":1024, "do_sample":True,
+                                   "temperature":0.1,
+                                   "top_k":50,
+                                   "top_p":0.95, "eos_token_id":49155})
 
     memory = ConversationBufferMemory(memory_key='chat_history', return_messages=True)