Upload 4 files

Dockerfile

@@ -0,0 +1,11 @@
+FROM python:3.10
+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 +1,74 @@
+import chainlit as cl
+import asyncio
+import wandb
+import pandas as pd
+import pinecone
+import os
+from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain.embeddings import CacheBackedEmbeddings
+from langchain.storage import LocalFileStore
+from langchain.vectorstores import Pinecone
+from langchain.chains import RetrievalQA
+from langchain.callbacks import StdOutCallbackHandler
+from langchain.chat_models import ChatOpenAI
+import langchain
+from langchain.cache import InMemoryCache
+
+pinecone.init(
+    api_key= os.environ['PINECONE_API_KEY'],
+    environment= os.environ['PINECONE_ENV']
+)
+
+index_name = 'movie-review-index'
+index = pinecone.Index(index_name)
+
+
+@cl.on_chat_start
+async def on_chat_start():
+
+    msg = cl.Message(
+        content=f"Loading Dataset ...", disable_human_feedback=True
+    )
+    await msg.send()
+    
+    text_field = "text"
+
+    store = LocalFileStore("./cache/")
+
+    core_embeddings_model = OpenAIEmbeddings()
+    embedder = CacheBackedEmbeddings.from_bytes_store(
+        core_embeddings_model,
+        store,
+        namespace= core_embeddings_model.model
+    )
+    vectorstore = Pinecone(
+        index, embedder.embed_query, text_field
+    )
+    # docsearch = Pinecone.from_existing_index(
+    #     index_name=index_name, embedding=embedder.embed_query, namespace=None
+    # )
+    llm = ChatOpenAI(model="gpt-3.5-turbo", temperature=0)
+    retriever = vectorstore.as_retriever()
+    handler = StdOutCallbackHandler()
+
+    qa_with_sources_chain = RetrievalQA.from_chain_type(
+        llm=llm,
+        retriever=retriever,
+        callbacks=[handler],
+        return_source_documents=True
+    )
+    langchain.llm_cache = InMemoryCache()
+    # Let the user know that the system is ready
+    msg.content = f"Dataset loading is done. You can now ask questions!"
+    await msg.update()
+
+    cl.user_session.set("chain", qa_with_sources_chain)
+
+@cl.on_message
+async def main(message:str):
+    chain = cl.user_session.get("chain")
+    output = chain({"query":message})
+    # print(output)
+    msg = cl.Message(content=f"{output['result']}")
+    # msg.prompt = output
+    await msg.send()

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 +1,16 @@
+requests 
+scrapy
+selenium
+numpy==1.25.2
+openai==0.27.8
+python-dotenv==1.0.0
+pandas
+scikit-learn
+ipykernel
+matplotlib
+plotly
+wandb
+chainlit
+pinecone-client[grpc]
+tiktoken
+langchain