Upload 2 files

app.py

@@ -0,0 +1,39 @@
+import os
+from langchain.vectorstores import FAISS
+from langchain.document_loaders import PyPDFLoader
+from langchain.chains.question_answering import load_qa_chain
+from langchain.prompts import PromptTemplate
+from langchain.memory import ConversationBufferMemory
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain.chains import RetrievalQA
+from langchain.document_loaders import UnstructuredFileLoader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.chains import RetrievalQAWithSourcesChain
+from huggingface_hub import notebook_login
+from transformers import pipeline
+from transformers import AutoTokenizer, AutoModelForCausalLM
+from langchain import HuggingFacePipeline
+from langchain.text_splitter import CharacterTextSplitter
+import textwrap
+import sys
+import torch
+os.environ['HuggingFaceHub_API_Token']= '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'
+loader = UnstructuredFileLoader('/content/Highway Traffic Act, R.S.O. 1990, c. H.8.pdf')
+documents = loader.load()
+text_splitter=CharacterTextSplitter(separator='\n',chunk_size=1500,chunk_overlap=300)
+text_chunks=text_splitter.split_documents(documents)
+embeddings = HuggingFaceEmbeddings(model_name='sentence-transformers/all-MiniLM-L6-v2',model_kwargs={'device': 'cuda'})
+vectorstore=FAISS.from_documents(text_chunks, embeddings)
+notebook_login()
+os.environ['HuggingFaceHub_API_Token']= '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'
+tokenizer = AutoTokenizer.from_pretrained("NousResearch/Llama-2-7b-hf")
+model = AutoModelForCausalLM.from_pretrained("NousResearch/Llama-2-7b-hf", device_map='auto',torch_dtype=torch.float16,load_in_4bit=True, token=True )
+pipe = pipeline("text-generation",model=model,tokenizer= tokenizer,torch_dtype=torch.bfloat16,device_map="auto",max_new_tokens = 1024,do_sample=True,top_k=10,num_return_sequences=1, eos_token_id=tokenizer.eos_token_id)
+
+llm=HuggingFacePipeline(pipeline=pipe, model_kwargs={'temperature':0.5})
+chain =  RetrievalQA.from_chain_type(llm=llm, chain_type = "stuff",return_source_documents=True, retriever=vectorstore.as_retriever())
+
+query = "Can goat and paint be transported in same truck ?"
+result=chain({"query": query}, return_only_outputs=True)
+wrapped_text = textwrap.fill(result['result'], width=500)
+wrapped_text

requirements.txt

@@ -0,0 +1,15 @@
+langchain
+torch
+accelerate
+sentence_transformers
+streamlit_chat
+streamlit
+faiss-cpu
+tiktoken
+transformers
+huggingface-hub
+pypdf
+python-dotenv
+replicate
+docx2txt
+