Update app.py

app.py

@@ -2,8 +2,6 @@ from langchain_community.vectorstores import FAISS
 from langchain_community.embeddings import HuggingFaceEmbeddings
 from langchain.prompts import PromptTemplate
 from langchain_together import Together
-from langchain_community.llms import huggingface_hub
-import os
 from langchain.retrievers.document_compressors import EmbeddingsFilter
 from langchain.retrievers import ContextualCompressionRetriever
 from langchain.memory import ConversationBufferWindowMemory
@@ -41,12 +39,12 @@ prompt = PromptTemplate(template=custom_prompt_template,
                         input_variables=['context', 'question', 'chat_history'])
 
 
-llm = huggingface_hub(
-        repo_id="mistralai/Mixtral-8x7B-Instruct-v0.1",
-        model_kwargs={"temperature": 0.7, "max_length": 512}
-    )
-
-embeddings_filter = EmbeddingsFilter(embeddings=embeddings, similarity_threshold=0.80)
+llm = Together(
+    model="mistralai/Mistral-7B-Instruct-v0.2",
+    temperature=0.7,
+    max_tokens=512,
+    together_api_key="48515099b0ed4e22e56da54e50feb4adfaaa901a444b0c34bb33c66abe7b2c61"
+)
 
 qa = ConversationalRetrievalChain.from_llm(
     llm=llm,