Add application file

baby.py

@@ -0,0 +1,201 @@
+import openai
+import os
+from langchain.vectorstores import Chroma
+from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain.text_splitter import CharacterTextSplitter
+from langchain.chat_models import AzureChatOpenAI
+from langchain.document_loaders import DirectoryLoader
+from langchain.chains import RetrievalQA  
+from langchain.vectorstores import Pinecone
+import pinecone      
+from pinecone.core.client.configuration import Configuration as OpenApiConfiguration
+import gradio as gr
+import time
+
+# socks.set_default_proxy(socks.SOCKS5, "http://u477827:4rfgt54r@http.internetpsa.inetpsa.com", 80)
+# socket.socket = socks.socksocket
+
+
+
+# with open('2.txt') as f:
+#     state_of_the_union = f.read()
+# text_splitter = CharacterTextSplitter(chunk_size=500, chunk_overlap=50)
+# texts = text_splitter.create_documents([state_of_the_union])
+# print(texts[0])
+# print(texts[1])
+
+os.environ["OPENAI_API_TYPE"] = "azure"
+os.environ["OPENAI_API_KEY"] = "f930f70cf65f48a8a750a22c813ba1b3"
+os.environ["OPENAI_API_BASE"] = "https://stla-baby.openai.azure.com/"
+os.environ["OPENAI_API_VERSION"] = "2023-05-15"
+os.environ["OPENAI_PROXY"] = 'http://u477827:4rfgt54r@http.internetpsa.inetpsa.com:80'
+
+# openai.api_type = "azure"
+# openai.api_key = "f930f70cf65f48a8a750a22c813ba1b3"
+# openai.api_base = "https://stla-baby.openai.azure.com/"
+# openai.api_version = "2023-05-15"  # subject to change
+# # openai.proxy = 'http://u477827:4rfgt54r@http.internetpsa.inetpsa.com:80'
+# openai.proxy = 'http://u477827:4rfgt54r@http.ntlm.internetpsa.inetpsa.com:8080'
+
+
+chat = AzureChatOpenAI(
+    deployment_name="Chattester",
+    temperature=0,
+)
+
+embeddings = OpenAIEmbeddings(deployment="model_embedding")
+
+
+openapi_config = OpenApiConfiguration.get_default_copy()
+# openapi_config.verify_ssl = True
+openapi_config.proxy = "http://u477827:4rfgt54r@http.internetpsa.inetpsa.com:80"
+# openapi_config.proxy = "http://u477827:4rfgt54r@http.ntlm.internetpsa.inetpsa.com:8080"
+
+pinecone.init(      
+	api_key='0def3ea0-93cd-4ead-b0c6-2ab44b3ede21',      
+	environment='asia-southeast1-gcp-free',
+    openapi_config=openapi_config      
+)
+index_name = 'stla-baby'     
+index = pinecone.Index(index_name)
+# index.delete(delete_all=True, namespace='')
+# print(pinecone.whoami())
+# print(index.describe_index_stats())
+
+
+
+global vectordb
+vectordb = Chroma(persist_directory='db', embedding_function=embeddings)
+global vectordb_p
+vectordb_p = Pinecone.from_existing_index(index_name, embeddings)
+
+# loader = DirectoryLoader('./documents', glob='**/*.txt')
+# documents = loader.load()
+# text_splitter = CharacterTextSplitter(chunk_size=500, chunk_overlap=200)
+# split_docs = text_splitter.split_documents(documents)
+# print(split_docs)
+# vectordb = Chroma.from_documents(split_docs, embeddings, persist_directory='db')
+
+
+
+# question = "what is LCDV ?"
+# rr = vectordb.similarity_search(query=question, k=4)
+# vectordb.similarity_search(question)
+# print(type(rr))
+# print(rr)
+def chathmi(message, history):
+    response = "I don't know"
+    print(message)
+    response = QAQuery_p(message)
+    time.sleep(0.3)
+    print(history)
+    return response
+
+# chatbot = gr.Chatbot().style(color_map =("blue", "pink"))
+# chatbot = gr.Chatbot(color_map =("blue", "pink"))
+
+demo = gr.ChatInterface(
+    chathmi,
+    title="STLA BABY - YOUR FRIENDLY GUIDE",
+    )
+
+# demo = gr.Interface(
+#     chathmi,
+#     ["text", "state"],
+#     [chatbot, "state"],
+#     allow_flagging="never",
+# )
+
+def CreatDb_P():
+    global vectordb_p
+    index_name = 'stla-baby'
+    loader = DirectoryLoader('./documents', glob='**/*.txt')
+    documents = loader.load()
+    text_splitter = CharacterTextSplitter(chunk_size=500, chunk_overlap=200)
+    split_docs = text_splitter.split_documents(documents)
+    print(split_docs)
+    pinecone.Index(index_name).delete(delete_all=True, namespace='')
+    vectordb_p = Pinecone.from_documents(split_docs, embeddings, index_name = "stla-baby")
+    print("Pinecone Updated Done")
+    print(index.describe_index_stats())
+
+def QAQuery_p(question: str):
+    global vectordb_p
+    # vectordb = Chroma(persist_directory='db', embedding_function=embeddings)
+    retriever = vectordb_p.as_retriever()
+    retriever.search_kwargs['k'] = 3
+    # retriever.search_kwargs['fetch_k'] = 100
+
+    qa = RetrievalQA.from_chain_type(llm=chat, chain_type="stuff", retriever=retriever, return_source_documents = True)
+    # qa = VectorDBQA.from_chain_type(llm=chat, chain_type="stuff", vectorstore=vectordb, return_source_documents=True)
+    # res = qa.run(question)
+    res = qa({"query": question})
+    
+    print("-" * 20)
+    print("Question:", question)
+    # print("Answer:", res)
+    print("Answer:", res['result'])
+    print("-" * 20)
+    print("Source:", res['source_documents'])
+    response = res['result']
+    # response = res['source_documents']
+    return response
+
+def CreatDb():
+    global vectordb
+    loader = DirectoryLoader('./documents', glob='**/*.txt')
+    documents = loader.load()
+    text_splitter = CharacterTextSplitter(chunk_size=500, chunk_overlap=200)
+    split_docs = text_splitter.split_documents(documents)
+    print(split_docs)
+    vectordb = Chroma.from_documents(split_docs, embeddings, persist_directory='db')
+    vectordb.persist()
+
+def QAQuery(question: str):
+    global vectordb
+    # vectordb = Chroma(persist_directory='db', embedding_function=embeddings)
+    retriever = vectordb.as_retriever()
+    retriever.search_kwargs['k'] = 3
+    # retriever.search_kwargs['fetch_k'] = 100
+
+    qa = RetrievalQA.from_chain_type(llm=chat, chain_type="stuff", retriever=retriever, return_source_documents = True)
+    # qa = VectorDBQA.from_chain_type(llm=chat, chain_type="stuff", vectorstore=vectordb, return_source_documents=True)
+    # res = qa.run(question)
+    res = qa({"query": question})
+    
+    print("-" * 20)
+    print("Question:", question)
+    # print("Answer:", res)
+    print("Answer:", res['result'])
+    print("-" * 20)
+    print("Source:", res['source_documents'])
+
+
+# Used to complete content
+def completeText(Text): 
+    deployment_id="Chattester"
+    prompt = Text
+    completion = openai.Completion.create(deployment_id=deployment_id,
+                                        prompt=prompt, temperature=0)                              
+    print(f"{prompt}{completion['choices'][0]['text']}.")
+
+# Used to chat
+def chatText(Text): 
+    deployment_id="Chattester"
+    conversation = [{"role": "system", "content": "You are a helpful assistant."}]
+    user_input = Text
+    conversation.append({"role": "user", "content": user_input})
+    response = openai.ChatCompletion.create(messages=conversation,
+        deployment_id="Chattester")
+    print("\n" + response["choices"][0]["message"]["content"] + "\n")
+
+if __name__ == '__main__':
+    # chatText("what is AI?")
+    # CreatDb()
+    # QAQuery("what is COFOR ?")
+    # CreatDb_P()
+    # QAQuery_p("what is GST ?")
+    demo.queue().launch()
+    pass
+
+

requirements.txt

@@ -0,0 +1,5 @@
+chromadb
+langchain
+openai
+gradio
+pinecone-client