Upload 8 files

app.py

@@ -0,0 +1,69 @@
+import os
+import pathlib
+import re
+import gradio as gr
+from langchain.docstore.document import Document
+from langchain.document_loaders import TextLoader
+from langchain.text_splitter import CharacterTextSplitter
+from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain.vectorstores import FAISS
+
+os.environ["OPENAI_API_KEY"] = "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"
+
+from langchain.prompts.chat import (
+    ChatPromptTemplate,
+    SystemMessagePromptTemplate,
+    HumanMessagePromptTemplate,
+)
+from langchain.chat_models import ChatOpenAI
+from langchain.chains import RetrievalQAWithSourcesChain
+
+# Set the data store directory
+DATA_STORE_DIR = "data_store"
+
+if os.path.exists(DATA_STORE_DIR):
+    vector_store = FAISS.load_local(
+        DATA_STORE_DIR,
+        OpenAIEmbeddings()
+    )
+else:
+    print(f"Missing files. Upload index.faiss and index.pkl files to {DATA_STORE_DIR} directory first")
+
+system_template = """Use the following pieces of context to answer the user's question.
+Take note of the sources and include them in the answer in the format: "SOURCES: source1", use "SOURCES" in capital letters regardless of the number of sources.
+If you don't know the answer, just say "I don't know", don't try to make up an answer.
+----------------
+{summaries}"""
+
+messages = [
+    SystemMessagePromptTemplate.from_template(system_template),
+    HumanMessagePromptTemplate.from_template("{question}")
+]
+prompt = ChatPromptTemplate.from_messages(messages)
+
+llm = ChatOpenAI(model_name="gpt-3.5-turbo", temperature=0,
+                 max_tokens=256)  # Modify model_name if you have access to GPT-4
+
+chain_type_kwargs = {"prompt": prompt}
+chain = RetrievalQAWithSourcesChain.from_chain_type(
+    llm=llm,
+    chain_type="stuff",
+    retriever=vector_store.as_retriever(),
+    return_source_documents=True,
+    chain_type_kwargs=chain_type_kwargs
+)
+
+
+def chatbot_interface(query):
+    result = chain(query)
+    return result['answer']
+
+
+# Create a Gradio interface
+gr.Interface(
+    fn=chatbot_interface,
+    inputs="text",
+    outputs="text",
+    title="LLM Chatbot",
+    description="Chat with the LLM Chatbot on Custom Data"
+).launch()

data_store/index.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83b6ab5883ed5446048cac782f8be8027281e3f68ed1ae5f829d6b3cf3ee1de6
+size 36695

gradio_pr.py

@@ -0,0 +1,89 @@
+import gradio as gr
+import os
+import pathlib
+import random
+#import torch
+#import transformers
+from langchain.document_loaders import TextLoader
+from langchain.text_splitter import CharacterTextSplitter
+from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain.vectorstores import FAISS
+from langchain.prompts.chat import (
+    ChatPromptTemplate,
+    SystemMessagePromptTemplate,
+    HumanMessagePromptTemplate,
+)
+from langchain.chat_models import ChatOpenAI
+from langchain.chains import RetrievalQAWithSourcesChain
+
+os.environ["OPENAI_API_KEY"] = "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"
+
+# Set the data store directory
+DATA_STORE_DIR = "data_store"
+
+if os.path.exists(DATA_STORE_DIR):
+    vector_store = FAISS.load_local(
+        DATA_STORE_DIR,
+        OpenAIEmbeddings()
+    )
+else:
+    print(f"Missing files. Upload index.faiss and index.pkl files to {DATA_STORE_DIR} directory first")
+
+system_template = """Use the following pieces of context to answer the user's question.
+Take note of the sources and include them in the answer in the format: "SOURCES: source1", use "SOURCES" in capital letters regardless of the number of sources.
+If you don't know the answer, just say "I don't know", don't try to make up an answer.
+----------------
+{summaries}"""
+
+messages = [
+    SystemMessagePromptTemplate.from_template(system_template),
+    HumanMessagePromptTemplate.from_template("{question}")
+]
+prompt = ChatPromptTemplate.from_messages(messages)
+
+llm = ChatOpenAI(model_name="gpt-3.5-turbo", temperature=0, max_tokens=256)
+
+chain_type_kwargs = {"prompt": prompt}
+chain = RetrievalQAWithSourcesChain.from_chain_type(
+    llm=llm,
+    chain_type="stuff",
+    retriever=vector_store.as_retriever(),
+    return_source_documents=True,
+    chain_type_kwargs=chain_type_kwargs
+)
+
+
+class Chatbot:
+    def __init__(self):
+        self.query = None
+
+    def chat(self, query):
+        self.query = query
+        result = chain(query)
+        return result['answer']
+
+
+chatbot = Chatbot()
+
+
+# Create a Gradio interface
+def chat_interface(query):
+    response = chatbot.chat(query)
+    return response
+
+
+# inputs = gr.inputs.Textbox(lines=2, placeholder="Enter your message here...")
+# outputs = gr.outputs.Textbox()
+
+# chat_interface = gr.ChatInterface(chat_interface, inputs=inputs, outputs=outputs)
+#
+# chat_interface.launch()
+gr.ChatInterface(
+    chat_interface,
+    chatbot=gr.Chatbot(height=300),
+    textbox=gr.Textbox(placeholder="Ask me a yes or no question"),
+    description="Ask Yes Man any question",
+    theme="soft",
+    cache_examples=True,
+    clear_btn="Clear",
+).launch()

main.py

@@ -0,0 +1,21 @@
+import time
+import gradio as gr
+
+
+def slow_echo(message, history):
+    for i in range(len(message)):
+        time.sleep(0.3)
+        yield "You typed: " + message[: i + 1]
+
+
+gr.ChatInterface(
+    slow_echo,
+    # chatbot=gr.Chatbot(height=200),
+    # textbox=gr.Textbox(placeholder="Ask me a yes or no question"),
+    description="Ask Yes Man any question",
+    theme="soft",
+    css="",
+    examples=["Hello", "Am I cool?", "Are tomatoes vegetables?"],
+    cache_examples=True,
+    clear_btn="Clear",
+).queue().launch()

streamlit_app.py

@@ -0,0 +1,99 @@
+import os
+import pathlib
+import re
+import streamlit as st
+from streamlit_chat import message
+from langchain.docstore.document import Document
+from langchain.document_loaders import TextLoader
+from langchain.text_splitter import CharacterTextSplitter
+from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain.vectorstores import FAISS
+
+st.set_page_config(
+    page_title="LLM Chatbot"
+)
+st.header(" LLM Chatbot on Custom data")
+st.sidebar.header("Instructions")
+st.sidebar.info(
+    '''This is a web application that allows you to interact with 
+    your custom data
+    '''
+)
+st.sidebar.info('''Enter a query in the text box and press enter
+    to receive a response''')
+
+st.sidebar.info('''
+This project works perfectly even on your own data
+''')
+
+os.environ["OPENAI_API_KEY"] = "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"
+
+from langchain.prompts.chat import (
+    ChatPromptTemplate,
+    SystemMessagePromptTemplate,
+    HumanMessagePromptTemplate,
+)
+from langchain.chat_models import ChatOpenAI
+from langchain.chains import RetrievalQAWithSourcesChain
+
+# Initialize Streamlit
+st.title("Stanlito AI Chatbot")
+
+# Set the data store directory
+DATA_STORE_DIR = "data_store"
+
+# Upload the files `$DATA_STORE_DIR/index.faiss` and `$DATA_STORE_DIR/index.pkl` to local
+if os.path.exists(DATA_STORE_DIR):
+    vector_store = FAISS.load_local(
+        DATA_STORE_DIR,
+        OpenAIEmbeddings()
+    )
+else:
+    st.write(f"Missing files. Upload index.faiss and index.pkl files to {DATA_STORE_DIR} directory first")
+
+# Define system template
+system_template = """Use the following pieces of context to answer the user's question.
+Take note of the sources and include them in the answer in the format: "SOURCES: source1", use "SOURCES" in capital letters regardless of the number of sources.
+If you don't know the answer, just say "I don't know", don't try to make up an answer.
+----------------
+{summaries}"""
+
+# Create the prompt
+messages = [
+    SystemMessagePromptTemplate.from_template(system_template),
+    HumanMessagePromptTemplate.from_template("{question}")
+]
+prompt = ChatPromptTemplate.from_messages(messages)
+
+# Load the language model
+llm = ChatOpenAI(model_name="gpt-3.5-turbo", temperature=0,
+                 max_tokens=256)  # Modify model_name if you have access to GPT-4
+
+# Create the chain
+chain_type_kwargs = {"prompt": prompt}
+chain = RetrievalQAWithSourcesChain.from_chain_type(
+    llm=llm,
+    chain_type="stuff",
+    retriever=vector_store.as_retriever(),
+    return_source_documents=True,
+    chain_type_kwargs=chain_type_kwargs
+)
+
+
+# Define function to print the result
+def print_result(result):
+    output_text = f"""### Question:
+    {query}
+    Answer:
+    {result['answer']}
+    """
+    st.markdown(output_text)
+
+
+# Get user input
+query = st.text_input("Ask a question")
+
+# Process user input
+if query:
+    result = chain(query)
+    print_result(result)