Update app.py

app.py

@@ -1,44 +1,46 @@
 import gradio as gr
+import torch
+import transformers
+from transformers import AutoTokenizer
+from langchain import LLMChain, HuggingFacePipeline, PromptTemplate
 
 def greet(text):
-     
-    from langchain.chat_models import ChatOllama
-    from langchain.document_loaders import WebBaseLoader
-    from langchain.chains.summarize import load_summarize_chain
-    
-    loader = WebBaseLoader("https://lilianweng.github.io/posts/2023-06-23-agent/")
-    docs = loader.load()
-    
-    llm = ChatOllama(temperature=0, model_name="falcon:7b")
-    chain = load_summarize_chain(llm, chain_type="stuff")
-    
-    chain.run(docs)
 
-    from langchain.chains.llm import LLMChain
-    from langchain.prompts import PromptTemplate
-    from langchain.chains.combine_documents.stuff import StuffDocumentsChain
-    
-    # Define prompt
-    prompt_template = """Write a concise summary of the following:
-    "{text}"
-    CONCISE SUMMARY:"""
-    prompt = PromptTemplate.from_template(prompt_template)
-    
-    # Define LLM chain
-    llm = ChatOllama(temperature=0, model_name="falcon:7b")
-    llm_chain = LLMChain(llm=llm, prompt=prompt)
-    
-    # Define StuffDocumentsChain
-    stuff_chain = StuffDocumentsChain(
-        llm_chain=llm_chain, document_variable_name="text"
+    model = "meta-llama/Llama-2-7b-chat-hf"
+    tokenizer = AutoTokenizer.from_pretrained(model)
+    
+    pipeline = transformers.pipeline(
+    "text-generation",
+    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
     )
-    
-    docs = loader.load()
-    summary = stuff_chain.run(docs)
+
+    llm = HuggingFacePipeline(pipeline = pipeline, model_kwargs = {'temperature':0})
+
+    template = """
+              Write a summary of the following text delimited by triple backticks.
+              Return your response which covers the key points of the text.
+              ```{text}```
+              SUMMARY:
+               """
+    
+    prompt = PromptTemplate(template=template, input_variables=["text"])
+    llm_chain = LLMChain(prompt=prompt, llm=llm)
+
+    summary = llm_chain.run(text)
     
     return summary
 
 with gr.Blocks() as demo:
+    
     text = gr.Textbox(label="Text")
     summary = gr.Textbox(label="Summary")
     greet_btn = gr.Button("Submit")