import gradio as gr from langchain.llms import Replicate from langchain.vectorstores import Pinecone from langchain.text_splitter import CharacterTextSplitter from langchain.document_loaders import PyPDFLoader from langchain.llms import HuggingFaceHub from langchain.vectorstores import Chroma from langchain.embeddings import HuggingFaceEmbeddings from langchain.chains import ConversationalRetrievalChain from datasets import load_dataset import os key = os.environ.get('API') os.environ["REPLICATE_API_TOKEN"] = key import sentence_transformers def loading_pdf(): return "Loading..." def pdf_changes(pdf_doc): loader = PyPDFLoader(pdf_doc.name) documents = loader.load() text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0) texts = text_splitter.split_documents(documents) embeddings = HuggingFaceEmbeddings() db = Chroma.from_documents(texts, embeddings) retriever = db.as_retriever(search_kwargs={'k': 2}) llm = Replicate( model="a16z-infra/llama13b-v2-chat:df7690f1994d94e96ad9d568eac121aecf50684a0b0963b25a41cc40061269e5", input={"temperature": 0.2, "max_length": 3000, "length_penalty":1.5, "num_beams":3} ) global qa qa = ConversationalRetrievalChain.from_llm( llm, retriever, return_source_documents=True ) return "Ready" def text(history, text): result = qa({'question': text, 'chat_history': history}) history.append((text, result['answer'])) return history,"" css=""" #col-container {max-width: 700px; margin-left: auto; margin-right: auto;} """ title = """