Update app.py

app.py

@@ -12,9 +12,84 @@ from langchain.vectorstores import FAISS
 from langchain.chains import ConversationalRetrievalChain
 from transformers import pipeline
 
-pipe = pipeline('sentiment-analysis')
-text = st.text_area('enter some text')
+model_id = 'meta-llama/Llama-2-7b-chat-hf'
+device = f'cuda:{cuda.current_device()}' if cuda.is_available() else 'cpu'
+
+bnb_config = transformers.BitsAndBytesConfig(
+    load_in_4bit=True,
+    bnb_4bit_quant_type='nf4',
+    bnb_4bit_use_double_quant=True,
+    bnb_4bit_compute_dtype=bfloat16
+)
+
+hf_auth = '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'
+model_config = transformers.AutoConfig.from_pretrained(
+    model_id,
+    use_auth_token=hf_auth
+)
+
+model = transformers.AutoModelForCausalLM.from_pretrained(
+    model_id,
+    trust_remote_code=True,
+    config=model_config,
+    quantization_config=bnb_config,
+    device_map='auto',
+    use_auth_token=hf_auth
+)
+
+model.eval()
+
+tokenizer = transformers.AutoTokenizer.from_pretrained(
+    model_id,
+    use_auth_token=hf_auth
+)
+
+stop_list = ['\nHuman:', '\n```\n']
+
+stop_token_ids = [tokenizer(x)['input_ids'] for x in stop_list]
+stop_token_ids = [torch.LongTensor(x).to(device) for x in stop_token_ids]
+
+class StopOnTokens(StoppingCriteria):
+    def __call__(self, input_ids: torch.LongTensor, scores: torch.FloatTensor, **kwargs) -> bool:
+        for stop_ids in stop_token_ids:
+            if torch.eq(input_ids[0][-len(stop_ids):], stop_ids).all():
+                return True
+        return False
+
+stopping_criteria = StoppingCriteriaList([StopOnTokens()])
+
+generate_text = transformers.pipeline(
+    model=model, 
+    tokenizer=tokenizer,
+    return_full_text=True,  # langchain expects the full text
+    task='text-generation',
+    # we pass model parameters here too
+    stopping_criteria=stopping_criteria,  # without this model rambles during chat
+    temperature=0.1,  # 'randomness' of outputs, 0.0 is the min and 1.0 the max
+    max_new_tokens=512,  # max number of tokens to generate in the output
+    repetition_penalty=1.1  # without this output begins repeating
+)
+
+llm = HuggingFacePipeline(pipeline=generate_text)
+
+web_links = ["https://stanford-cs324.github.io/winter2022/lectures/introduction/"] 
+loader = WebBaseLoader(web_links)
+documents = loader.load()
+
+text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=20)
+all_splits = text_splitter.split_documents(documents)
+
+model_name = "sentence-transformers/all-mpnet-base-v2"
+model_kwargs = {"device": "cuda"}
+embeddings = HuggingFaceEmbeddings(model_name=model_name, model_kwargs=model_kwargs)
+vectorstore = FAISS.from_documents(all_splits, embeddings)
+
+chain = ConversationalRetrievalChain.from_llm(llm, vectorstore.as_retriever(), return_source_documents=True)
+
+chat_history = []
+
+text = st.text_area('Enter your query: ')
 
 if text:
-    out = pipe(text)
+    out = chain({"question": text, "chat_history": chat_history})
     st.json(out)