init

Dockerfile

@@ -0,0 +1,11 @@
+FROM python:3.9
+RUN useradd -m -u 1000 user
+USER user
+ENV HOME=/home/user \
+    PATH=/home/user/.local/bin:$PATH
+WORKDIR $HOME/app
+COPY --chown=user . $HOME/app
+COPY ./requirements.txt ~/app/requirements.txt
+RUN pip install -r requirements.txt
+COPY . .
+CMD ["chainlit", "run", "app.py", "--port", "7860"]

app.py

@@ -0,0 +1,110 @@
+import chainlit as cl
+import tiktoken
+import os
+from dotenv import load_dotenv
+# from langchain.document_loaders import PyMuPDFLoader
+from langchain_community.document_loaders import PyMuPDFLoader
+from langchain_openai import OpenAIEmbeddings
+# from langchain_community.chat_models import OpenAIEmbeddings
+
+from langchain_core.prompts import ChatPromptTemplate
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+# from langchain.vectorstores import Pinecone
+from langchain_community.vectorstores import Pinecone
+from operator import itemgetter
+from langchain.schema.runnable import RunnablePassthrough
+from langchain_openai import ChatOpenAI
+from langchain.schema.runnable.config import RunnableConfig
+from langchain_core.output_parsers import StrOutputParser
+
+load_dotenv()
+
+RAG_PROMPT = """
+
+CONTEXT:
+{context}
+
+QUERY:
+{question}
+
+You are a car specialist and can only provide your answers from the context. 
+
+Don't tell in your response that you are getting it from the context.
+
+"""
+
+init_settings = {
+    "model": "gpt-3.5-turbo",
+    "temperature": 0,
+    "max_tokens": 500,
+    "top_p": 1,
+    "frequency_penalty": 0,
+    "presence_penalty": 0,
+}
+
+# embeddings = OpenAIEmbeddings(model="text-embedding-3-small")
+
+def tiktoken_len(text):
+    tokens = tiktoken.encoding_for_model("gpt-3.5-turbo").encode(
+        text,
+    )
+    return len(tokens)
+
+car_manual = PyMuPDFLoader(os.environ.get('pdfurl'))
+
+car_manual_data = car_manual.load()
+
+text_splitter = RecursiveCharacterTextSplitter(
+chunk_size = 400,
+chunk_overlap = 50,
+length_function = tiktoken_len)
+    
+car_manual_chunks = text_splitter.split_documents(car_manual_data)
+
+embedding_model = OpenAIEmbeddings(model="text-embedding-3-small")
+vector_store = Pinecone.from_documents(car_manual_chunks, embedding_model, index_name=os.environ.get('index'))
+retriever = vector_store.as_retriever()
+
+rag_prompt = ChatPromptTemplate.from_template(RAG_PROMPT)
+
+model = ChatOpenAI(model="gpt-3.5-turbo")
+
+
+
+@cl.on_chat_start
+async def main():
+    # text_splitter = RecursiveCharacterTextSplitter(
+    # chunk_size = 400,
+    # chunk_overlap = 50,
+    # length_function = tiktoken_len)
+    
+    # car_manual_chunks = text_splitter.split_documents(car_manual_data)
+
+    # embedding_model = OpenAIEmbeddings(model="text-embedding-3-small")
+    # vector_store = Pinecone.from_documents(car_manual_chunks, embedding_model, index_name=os.environ.get('index'))
+    # retriever = vector_store.as_retriever()
+
+    # rag_prompt = ChatPromptTemplate.from_template(RAG_PROMPT)
+
+    # model = ChatOpenAI(model="gpt-3.5-turbo")
+
+    mecanic_qa_chain = (
+        {"context": itemgetter("question") | retriever, "question": itemgetter("question")}
+        | RunnablePassthrough.assign(context=itemgetter("context"))
+        | rag_prompt | model | StrOutputParser()
+    )
+
+    cl.user_session.set("runnable", mecanic_qa_chain)
+
+
+
+@cl.on_message
+async def on_message(message: cl.Message):
+    runnable = cl.user_session.get("runnable")
+    msg = cl.Message(content="")
+
+    async for chunk in runnable.astream(
+        {"question":message.content},
+        config=RunnableConfig(callbacks=[cl.LangchainCallbackHandler()]),
+    ):
+        await msg.stream_token(chunk)

chainlit.md

@@ -0,0 +1,14 @@
+# Welcome to Chainlit! 🚀🤖
+
+Hi there, Developer! 👋 We're excited to have you on board. Chainlit is a powerful tool designed to help you prototype, debug and share applications built on top of LLMs.
+
+## Useful Links 🔗
+
+- **Documentation:** Get started with our comprehensive [Chainlit Documentation](https://docs.chainlit.io) 📚
+- **Discord Community:** Join our friendly [Chainlit Discord](https://discord.gg/k73SQ3FyUh) to ask questions, share your projects, and connect with other developers! 💬
+
+We can't wait to see what you create with Chainlit! Happy coding! 💻😊
+
+## Welcome screen
+
+To modify the welcome screen, edit the `chainlit.md` file at the root of your project. If you do not want a welcome screen, just leave this file empty.

requirements.txt

@@ -0,0 +1,10 @@
+chainlit==0.7.700
+cohere==4.37
+openai
+tiktoken
+python-dotenv==1.0.0
+langchain
+langchain-community
+langchain-openai
+pymupdf
+pinecone-client