How to Build ChatGPT like Custom Chatbot in 3 simple steps!

Hi there! ??

Today, we are going to learn how to make a custom chatGPT-like chatbot in three simple steps, to which you can chat generally like chatGPT and to whom you can also provide your own data in csv and pdf and chat with your files!

Step 1

Get Open-AI API Key

First and foremost, you need an OpenAI API Key.

To do so:

1. Create an OpenAI account/Log into your account.
2. Navigate to the API section.
3. Generate a new API key.

Once you have your Open AI API key, set it as a system environment variable:

$setx OPENAI_API_KEY "your_openai_api_key" /M        

Download and Install Python & Required Packages

Go to https://www.python.org/downloads/ and download the latest version of python

Once, python is installed open your command prompt and run these commands to install Chainlit, OpenAI & Langchain, these are the libraries with the help of which we would build our own chatbot.

$pip install chainlit
$pip install chainlit openai
$pip install langchain        

Once, these packages are installed, run the following command to verify chainlit's installation

$chainlit hello        

Step 2

Create a new file app.py and paste the following code into it

from langchain.chat_models import ChatOpenAI
from langchain.prompts import ChatPromptTemplate
from langchain.schema import StrOutputParser
from langchain.schema.runnable import Runnable
from langchain.schema.runnable.config import RunnableConfig
import chainlit as cl

@cl.on_chat_start
async def on_chat_start():
    model = ChatOpenAI(streaming=True)
    prompt = ChatPromptTemplate.from_messages(
        [(
                "system",
                "You're an AI chatbot who provides accurate answers to questions.",
            ),
            ("human", "{question}"),
        ])
    runnable = prompt | model | StrOutputParser()
    cl.user_session.set("runnable", runnable)

@cl.on_message
async def on_message(message: cl.Message):
    runnable = cl.user_session.get("runnable")  # type: Runnable
    msg = cl.Message(content="")
    async for chunk in runnable.astream(
        {"question": message.content},
        config=RunnableConfig(callbacks=[cl.LangchainCallbackHandler()]),
    ):
        await msg.stream_token(chunk)
    await msg.send()        

Step 3

Once, you have that file created, go to that directory, and run the following command:

$chainlit run app.py        

Voila! You have your chatbot running! ??

Extra Steps

To have the ability to add your custom pdfs and chat with them, replace the code in app.py with the following code:

from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.vectorstores import Chroma
from langchain.chains import RetrievalQAWithSourcesChain
from langchain.chat_models import ChatOpenAI
from langchain.prompts.chat import (
    ChatPromptTemplate,
    SystemMessagePromptTemplate,
    HumanMessagePromptTemplate,
)
import os
import io
import chainlit as cl
import PyPDF2
from io import BytesIO
from dotenv import load_dotenv

load_dotenv()
OPENAI_API_KEY= os.getenv("OPENAI_API_KEY")

# text_splitter and system template
text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=100)

system_template = """Use the following pieces of context to answer the users question.
If you don't know the answer, just say that you don't know, don't try to make up an answer.
ALWAYS return a "SOURCES" part in your answer.
The "SOURCES" part should be a reference to the source of the document from which you got your answer.

Example of your response should be:

```
The answer is foo
SOURCES: xyz
```

Begin!
----------------
{summaries}"""


messages = [
    SystemMessagePromptTemplate.from_template(system_template),
    HumanMessagePromptTemplate.from_template("{question}"),
]
prompt = ChatPromptTemplate.from_messages(messages)
chain_type_kwargs = {"prompt": prompt}


@cl.on_chat_start
async def on_chat_start():

    # Sending an image with the local file path
    elements = [
    cl.Image(name="image1", display="inline", path="./robot.jpeg")
    ]
    await cl.Message(content="Hello there, Welcome to AskAnyQuery related to Data!", elements=elements).send()
    files = None

    # Wait for the user to upload a PDF file
    while files is None:
        files = await cl.AskFileMessage(
            content="Please upload a PDF file to begin!",
            accept=["application/pdf"],
            max_size_mb=20,
            timeout=180,
        ).send()

    file = files[0]

    msg = cl.Message(content=f"Processing `{file.name}`...")
    await msg.send()

    # Read the PDF file
    pdf_stream = BytesIO(file.content)
    pdf = PyPDF2.PdfReader(pdf_stream)
    pdf_text = ""
    for page in pdf.pages:
        pdf_text += page.extract_text()

    # Split the text into chunks
    texts = text_splitter.split_text(pdf_text)

    # Create metadata for each chunk
    metadatas = [{"source": f"{i}-pl"} for i in range(len(texts))]

    # Create a Chroma vector store
    embeddings = OpenAIEmbeddings()
    docsearch = await cl.make_async(Chroma.from_texts)(
        texts, embeddings, metadatas=metadatas
    )

    # Create a chain that uses the Chroma vector store
    chain = RetrievalQAWithSourcesChain.from_chain_type(
        ChatOpenAI(temperature=0),
        chain_type="stuff",
        retriever=docsearch.as_retriever(),
    )
    

    # Save the metadata and texts in the user session
    cl.user_session.set("metadatas", metadatas)
    cl.user_session.set("texts", texts)

    # Let the user know that the system is ready
    msg.content = f"Processing `{file.name}` done. You can now ask questions!"
    await msg.update()

    cl.user_session.set("chain", chain)


@cl.on_message
async def main(message:str):

    chain = cl.user_session.get("chain")  # type: RetrievalQAWithSourcesChain
    cb = cl.AsyncLangchainCallbackHandler(
        stream_final_answer=True, answer_prefix_tokens=["FINAL", "ANSWER"]
    )
    cb.answer_reached = True
    res = await chain.acall(message, callbacks=[cb])

    answer = res["answer"]
    sources = res["sources"].strip()
    source_elements = []
    
    # Get the metadata and texts from the user session
    metadatas = cl.user_session.get("metadatas")
    all_sources = [m["source"] for m in metadatas]
    texts = cl.user_session.get("texts")

    if sources:
        found_sources = []

        # Add the sources to the message
        for source in sources.split(","):
            source_name = source.strip().replace(".", "")
            # Get the index of the source
            try:
                index = all_sources.index(source_name)
            except ValueError:
                continue
            text = texts[index]
            found_sources.append(source_name)
            # Create the text element referenced in the message
            source_elements.append(cl.Text(content=text, name=source_name))

        if found_sources:
            answer += f"\nSources: {', '.join(found_sources)}"
        else:
            answer += "\nNo sources found"

    if cb.has_streamed_final_answer:
        cb.final_stream.elements = source_elements
        await cb.final_stream.update()
    else:
        await cl.Message(content=answer, elements=source_elements).send()        

Happy Coding! ??