try to leverage ChatGPT to query questions

app.py

@@ -1,42 +1,85 @@
-from transformers import AutoTokenizer, AutoModel
-from langchain.document_loaders import TextLoader
-from langchain.embeddings import HuggingFaceEmbeddings
-from langchain.llms import HuggingFaceHub
-from langchain.text_splitter import CharacterTextSplitter
+import streamlit as st
+from dotenv import load_dotenv
+import pickle
+from PyPDF2 import PdfReader
+from streamlit_extras.add_vertical_space import add_vertical_space
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.embeddings.openai import OpenAIEmbeddings
 from langchain.vectorstores import FAISS
-
-# 选择 embedding 算法
-model_name = "sentence-transformers/all-mpnet-base-v2"
-model_kwargs = {'device': 'cpu'}
-encode_kwargs = {'normalize_embeddings': False}
-eb = HuggingFaceEmbeddings(
-    model_name=model_name,
-    model_kwargs=model_kwargs,
-    encode_kwargs=encode_kwargs
-)
-# 从文件读取数据
-loader = TextLoader("./test.txt")
-docs = loader.load()
-# 分词
-text_splitter = CharacterTextSplitter(chunk_size=100, chunk_overlap=50)
-tl = []
-for doc in docs:
-    for t in text_splitter.split_text(doc.page_content):
-        tl.append(t)
-# 向量数据库
-vector_store = FAISS.from_texts(tl, eb)
-query = '为什么client不直接从data server拉取数据'
-docs = vector_store.similarity_search(query, k=4)
-
-# 构造提问
-context = ''
-for i in range(len(docs)):
-    context += f'{i+1}、{docs[i].page_content}\n'
-prompt = f'已知:\n{context}\n问题:\n{query}'
-print(prompt)
-
-tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm-6b-int4", trust_remote_code=True)
-model = AutoModel.from_pretrained("THUDM/chatglm-6b-int4", trust_remote_code=True).float()
-model = model.eval()
-response, history = model.chat(tokenizer, prompt, history=[])
-print(response)
+from langchain.llms import OpenAI
+from langchain.chains.question_answering import load_qa_chain
+from langchain.callbacks import get_openai_callback
+import os
+ 
+# Sidebar contents
+with st.sidebar:
+    st.title('🤗💬 LLM Chat App')
+    st.markdown('''
+    ## About
+    This app is an LLM-powered chatbot built using:
+    - [Streamlit](https://streamlit.io/)
+    - [LangChain](https://python.langchain.com/)
+    - [OpenAI](https://platform.openai.com/docs/models) LLM model
+ 
+    ''')
+    add_vertical_space(5)
+    st.write('Made with ❤️ by [Prompt Engineer](https://youtube.com/@engineerprompt)')
+ 
+load_dotenv()
+ 
+def main():
+    st.header("Chat with PDF 💬")
+ 
+ 
+    # upload a PDF file
+    pdf = st.file_uploader("Upload your PDF", type='pdf')
+ 
+    # st.write(pdf)
+    if pdf is not None:
+        pdf_reader = PdfReader(pdf)
+        
+        text = ""
+        for page in pdf_reader.pages:
+            text += page.extract_text()
+ 
+        text_splitter = RecursiveCharacterTextSplitter(
+            chunk_size=1000,
+            chunk_overlap=200,
+            length_function=len
+            )
+        chunks = text_splitter.split_text(text=text)
+ 
+        # # embeddings
+        store_name = pdf.name[:-4]
+        st.write(f'{store_name}')
+        # st.write(chunks)
+ 
+        if os.path.exists(f"{store_name}.pkl"):
+            with open(f"{store_name}.pkl", "rb") as f:
+                VectorStore = pickle.load(f)
+            # st.write('Embeddings Loaded from the Disk')s
+        else:
+            embeddings = OpenAIEmbeddings()
+            VectorStore = FAISS.from_texts(chunks, embedding=embeddings)
+            with open(f"{store_name}.pkl", "wb") as f:
+                pickle.dump(VectorStore, f)
+ 
+        # embeddings = OpenAIEmbeddings()
+        # VectorStore = FAISS.from_texts(chunks, embedding=embeddings)
+ 
+        # Accept user questions/query
+        query = st.text_input("Ask questions about your PDF file:")
+        # st.write(query)
+ 
+        if query:
+            docs = VectorStore.similarity_search(query=query, k=3)
+ 
+            llm = OpenAI()
+            chain = load_qa_chain(llm=llm, chain_type="stuff")
+            with get_openai_callback() as cb:
+                response = chain.run(input_documents=docs, question=query)
+                print(cb)
+            st.write(response)
+ 
+if __name__ == '__main__':
+    main()

requirements.txt

@@ -1,13 +1,6 @@
-protobuf
-transformers==4.27.1
-cpm_kernels
-torch>=1.10
-gradio
-mdtex2html
-sentencepiece
-accelerate
-langchain
-sentence_transformers
-unstructured
-pdf2image
-faiss-cpu
+langchain==0.0.154
+PyPDF2==3.0.1
+python-dotenv==1.0.0
+streamlit==1.18.1
+faiss-cpu==1.7.4
+streamlit-extras