Download RAG_app.py from Mikeer/RAGURL: direct link, hf CLI and curl.
- Browser
- Download file 2.97 kB
-
https://huggingface.co/spaces/Mikeer/RAGURL/resolve/main/RAG_app.py
- Command line
-
hf download hf://spaces/Mikeer/RAGURL/RAG_app.py
-
curl -L -o RAG_app.py https://huggingface.co/spaces/Mikeer/RAGURL/resolve/main/RAG_app.py
2.97 kB
| import os | |
| os.environ["LANGCHAIN_PROJECT"] = f"RAG_workflow_2" | |
| os.environ['LANGCHAIN_TRACING_V2'] = 'true' | |
| os.environ['LANGCHAIN_ENDPOINT'] = 'https://api.smith.langchain.com' | |
| os.environ['LANGCHAIN_API_KEY'] = "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" | |
| with open("openai.txt","r") as f: | |
| key=f.read() | |
| with open("google.txt","r") as f1: | |
| key2=f1.read() | |
| os.environ['OPENAI_API_KEY'] = "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" | |
| from langchain_community.document_loaders import WebBaseLoader | |
| import os | |
| import gradio as gr | |
| from langchain_groq import ChatGroq | |
| from langchain.text_splitter import RecursiveCharacterTextSplitter | |
| from langchain_community.vectorstores import Chroma | |
| from langchain_core.output_parsers import StrOutputParser | |
| from langchain_core.runnables import RunnablePassthrough | |
| from langchain.schema import AIMessage, HumanMessage, SystemMessage | |
| from langchain import hub | |
| from langchain_community.document_loaders import PyPDFLoader | |
| from langchain_openai import OpenAIEmbeddings # Importing OpenAI Embeddings | |
| # Set the google key | |
| os.environ["GOOGLE_API_KEY"]="AIzaSyCHgWZbKzPsgA4DjWUPB8FJHqXLglhSwmI" | |
| from langchain_google_genai import ChatGoogleGenerativeAI | |
| # Initialize the google LLM | |
| llm = ChatGoogleGenerativeAI( | |
| model="gemini-1.5-pro", | |
| temperature=0, | |
| max_tokens=None, | |
| timeout=None, | |
| max_retries=2 | |
| ) | |
| # Function to process the content from a URL and get a response from LLM | |
| def process_url(url, user_query): | |
| # Load the content from the URL | |
| loader = WebBaseLoader(web_paths=[url]) | |
| docs = loader.load() | |
| # Split the text | |
| text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200) | |
| splits = text_splitter.split_documents(docs) | |
| # Embed the splits | |
| embeddings = OpenAIEmbeddings() # Initialize OpenAI Embeddings | |
| vectorstore = Chroma.from_documents(documents=splits, embedding=embeddings) | |
| retriever = vectorstore.as_retriever(search_kwargs={"k": 5}) | |
| # Prompt | |
| prompt = hub.pull("rlm/rag-prompt") | |
| # Chain | |
| rag_chain = ( | |
| {"context": retriever | (lambda docs: "\n\n".join(doc.page_content for doc in docs)), "question": RunnablePassthrough()} | |
| | prompt | |
| | llm | |
| | StrOutputParser() | |
| ) | |
| # Get the response from the LLM | |
| response = rag_chain.invoke(user_query) | |
| return response | |
| # Gradio interface | |
| def gradio_interface(url, user_query): | |
| response = process_url(url, user_query) | |
| return response | |
| # Create Gradio app | |
| demo_interface = gr.Interface( | |
| fn=gradio_interface, | |
| inputs=[ | |
| gr.Textbox(label="输入 URL"), | |
| gr.Textbox(label="询问关于网站的问题") | |
| ], | |
| outputs="text", | |
| title="RAG连接问答", | |
| description="输入一个URL然后询问关于URL的相关的问题." | |
| ) | |
| # Launch the app | |
| demo_interface.launch(share=True, debug=True) |