Spaces:
Sleeping
Sleeping
| import os | |
| from langchain.chains import RetrievalQA | |
| from langchain.llms import OpenAI | |
| from langchain.document_loaders import PyPDFLoader | |
| from langchain.indexes import VectorstoreIndexCreator | |
| from langchain.text_splitter import CharacterTextSplitter | |
| from langchain.embeddings import OpenAIEmbeddings | |
| from langchain.vectorstores import Chroma | |
| import gradio as gr | |
| import tempfile | |
| #定义查询函数qa | |
| def qa(file, openaikey, query, chain_type, k): | |
| os.environ["OPENAI_API_KEY"] = openaikey | |
| # load document 加载PDF文件 | |
| loader = PyPDFLoader(file.name) | |
| documents = loader.load() | |
| # split the documents into chunks 将PDF文件分割成小块 | |
| text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0) | |
| texts = text_splitter.split_documents(documents) | |
| # select which embeddings we want to use 使用 OpenAI 的embeddings模型为每个文本块创建一个向量嵌入 | |
| embeddings = OpenAIEmbeddings() | |
| # create the vectorestore to use as the index 创建一个向量存储VectorStore，用于后续的搜索。 | |
| db = Chroma.from_documents(texts, embeddings) | |
| # expose this index in a retriever interface 使用这个向量存储VectorStore创建一个检索器retriever | |
| retriever = db.as_retriever( | |
| search_type="similarity", search_kwargs={"k": k}) | |
| # create a chain to answer questions 然后使用这个检索器和 OpenAI 的模型创建一个问答链来回答问题。 | |
| qa = RetrievalQA.from_chain_type( | |
| llm=OpenAI(), chain_type=chain_type, retriever=retriever, return_source_documents=True) | |
| result = qa({"query": query}) | |
| print(result['result']) | |
| return result["result"] | |
| iface = gr.Interface( | |
| fn=qa, | |
| inputs=[ | |
| gr.inputs.File(label="上传PDF"), | |
| gr.inputs.Textbox(label="OpenAI API Key"), | |
| gr.inputs.Textbox(label="你的问题"), | |
| #longchain的文档documents分析功能的不同类型，具体见https://python.langchain.com.cn/docs/modules/chains/document/的解释 | |
| gr.inputs.Dropdown(choices=['stuff', 'map_reduce', "refine", "map_rerank"], label="Chain type"), | |
| gr.inputs.Slider(minimum=1, maximum=5, default=2, label="Number of relevant chunks"), | |
| ], | |
| outputs="text", | |
| title="你可以问我关于你上传的PDF文件的任何信息！", | |
| description="1) 上传一个PDF文件. 2)输入你的OpenAI API key.这将产生费用 3) 输入问题然后点击运行." | |
| ) | |
| iface.launch() | |