Update chain.py

chain.py

@@ -3,6 +3,10 @@ from langchain import PromptTemplate
 from langchain.chat_models import ChatOpenAI
 from langchain.chains import RetrievalQA
 import openai
+from langchain import HuggingFacePipeline
+from transformers import AutoTokenizer
+import transformers
+import torch
 
 openai.api_key = "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"
 
@@ -44,16 +48,30 @@ def create_question_answering_chain(retriever):
         qa_chain (obj): The initialized retrieval QA chain.
     """
     # Initialize the OpenAI language model with specified temperature, model name, and API key.
-    turbo_llm = ChatOpenAI(
-        temperature=0,
-        model_name='gpt-3.5-turbo',
-        openai_api_key = openai.api_key
+    model = "meta-llama/Llama-2-7b-chat-hf"
+    
+    tokenizer = AutoTokenizer.from_pretrained(model)
+    
+    pipeline = transformers.pipeline(
+        "text-generation", #task
+        model=model,
+        tokenizer=tokenizer,
+        torch_dtype=torch.bfloat16,
+        trust_remote_code=True,
+        device_map="auto",
+        max_length=1000,
+        do_sample=True,
+        top_k=10,
+        num_return_sequences=1,
+        eos_token_id=tokenizer.eos_token_id
     )
+    
+    llm = HuggingFacePipeline(pipeline = pipeline, model_kwargs = {'temperature':0})
 
     # Initialize the retrieval QA chain with the language model, chain type, document retriever,
     # and a flag indicating whether to return source documents.
     qa_chain = RetrievalQA.from_chain_type(
-          llm=turbo_llm,
+          llm=llm,
           chain_type='stuff',
           retriever=retriever,
           verbose=False,