restore

app.py

@@ -1,61 +1,40 @@
 from langchain.chat_models import ChatOpenAI
 import gradio as gr
-
 import os
+
 from langchain.embeddings.openai import OpenAIEmbeddings
 from langchain.vectorstores import DeepLake
-from langchain.text_splitter import CharacterTextSplitter
-from langchain.document_loaders import SeleniumURLLoader
 from langchain import PromptTemplate
 from langchain import OpenAI
+from langchain.vectorstores import DeepLake
+
+os.environ['OPENAI_API_KEY'] = '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'
+os.environ["ACTIVELOOP_TOKEN"] = "eyJhbGciOiJIUzUxMiIsImlhdCI6MTY5NTE5MTAyNiwiZXhwIjoxNzU4MzQ5NDA3fQ.eyJpZCI6InV0a2Fyc2h0aXdhcmkifQ.PK_iz7uybeSmgqFvOYrICw-CQDbDY1aOjYhkMu-0Jle6gU33dCwxah7bmy39O0hPN4jYLu_RfLuU-XejyNvXrw"
 
 def predict(query,history):
-    print("Starting")
-    os.environ['OPENAI_API_KEY'] = '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'
-    os.environ["ACTIVELOOP_TOKEN"] = "eyJhbGciOiJIUzUxMiIsImlhdCI6MTY5NTE5MTAyNiwiZXhwIjoxNzU4MzQ5NDA3fQ.eyJpZCI6InV0a2Fyc2h0aXdhcmkifQ.PK_iz7uybeSmgqFvOYrICw-CQDbDY1aOjYhkMu-0Jle6gU33dCwxah7bmy39O0hPN4jYLu_RfLuU-XejyNvXrw"
-    
-    llm = ChatOpenAI(temperature=1.0, model='gpt-3.5-turbo-0613')
-    
-    # URLs of articles to scrape
-    urls = ["https://modelwise.ai/product/","https://modelwise.ai/category/blog-articles/","https://modelwise.ai/company/"]
-    
-    # Load documents using Selenium
-    loader = SeleniumURLLoader(urls=urls)
-    docs_not_splitted = loader.load()
-    
-    # Split documents into smaller chunks
-    text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
-    docs = text_splitter.split_documents(docs_not_splitted)
-    
-    # Create OpenAIEmbeddings instance
-    embeddings = OpenAIEmbeddings(model="text-embedding-ada-002")
-    
-    # Specify your ActiveLoop organization ID
-    my_activeloop_org_id = "utkarshtiwari"
-    my_activeloop_dataset_name = "chatbot_modelwise"
-    dataset_path = f"hub://{my_activeloop_org_id}/{my_activeloop_dataset_name}"
-    db = DeepLake(dataset_path=dataset_path, embedding_function=embeddings)
-    
-    # Add documents to the Deep Lake dataset
-    db.add_documents(docs)
-    
+
     template = """You are an exceptional customer support chatbot for the company Modelwise that gently answers questions related to the company.
-    
+
     You know the following context information.
-    
+
     {chunks_formatted}
-    
-    Answer the following question from a customer. Use only information from the context. If you don't know the answer just ask the customer to contact Arnold and provide his contact details. Do not make up any answer. If you know the answer, then don't tell the customer to contact Arnold unless the customer specifically asks to contact someone.
-    
+
+    Answer the following question from a customer. Use only information from the context. If you don't know the answer just ask the customer to contact Arnold and provide  his contact details. Do not make up any answer.
+
     Question: {query}
-    
+
     Answer:"""
-    
+
     # Create a PromptTemplate instance
     prompt = PromptTemplate(
         input_variables=["chunks_formatted", "query"],
         template=template,
     )
+
+    my_activeloop_org_id = "utkarshtiwari"
+    my_activeloop_dataset_name = "chatbot_modelwise"
+    dataset_path = f"hub://{my_activeloop_org_id}/{my_activeloop_dataset_name}"
+    db = DeepLake(dataset_path=dataset_path, read_only=True)
     # Retrieve relevant chunks from the Knowledge Base
     docs = db.similarity_search(query)
     retrieved_chunks = [doc.page_content for doc in docs]