Spaces:
Build error
Build error
| import gradio as gr | |
| import fitz | |
| import os | |
| from langchain.embeddings.openai import OpenAIEmbeddings | |
| from langchain.text_splitter import CharacterTextSplitter | |
| from langchain_community.vectorstores.faiss import FAISS | |
| from langchain.chains.question_answering import load_qa_chain | |
| from langchain_community.llms import OpenAI | |
| openai_api_key = os.environ.get('OPENAI_API_KEY') | |
| def read_pdf(pdf_file, prompt): | |
| try: | |
| text = "" | |
| with open(pdf_file.name, "rb") as file: | |
| doc = fitz.open(file) | |
| for page in doc: | |
| text += page.get_text() | |
| # split the text into several chunks | |
| text_splitter = CharacterTextSplitter( | |
| separator = "\n", | |
| chunk_size = 1000, | |
| chunk_overlap = 200, | |
| length_function = len, | |
| ) | |
| texts = text_splitter.split_text(text) | |
| # download embedding from OpenAI | |
| embeddings = OpenAIEmbeddings(api_key=openai_api_key) | |
| docsearch = FAISS.from_texts(texts, embeddings) | |
| chain = load_qa_chain(OpenAI(api_key=openai_api_key), chain_type="stuff") | |
| docs = docsearch.similarity_search(prompt) | |
| answer = chain.run(input_documents = docs, question = prompt) | |
| return answer | |
| except Exception as e: | |
| return f"Error: {str(e)}" | |
| iface = gr.Interface( | |
| read_pdf, | |
| inputs=["file","text"], | |
| outputs="text", | |
| title="PDF Reader", | |
| description="Upload a PDF file!", | |
| ) | |
| iface.launch(share=True) |