Upload 6 files

.chainlit/config.toml

@@ -0,0 +1,78 @@
+[project]
+# Whether to enable telemetry (default: true). No personal data is collected.
+enable_telemetry = false
+
+# List of environment variables to be provided by each user to use the app.
+user_env = []
+
+# Duration (in seconds) during which the session is saved when the connection is lost
+session_timeout = 3600
+
+# Enable third parties caching (e.g LangChain cache)
+cache = false
+
+# Follow symlink for asset mount (see https://github.com/Chainlit/chainlit/issues/317)
+# follow_symlink = false
+
+[features]
+# Show the prompt playground
+prompt_playground = true
+
+# Authorize users to upload files with messages
+multi_modal = true
+
+# Allows user to use speech to text
+[features.speech_to_text]
+    enabled = false
+    # See all languages here https://github.com/JamesBrill/react-speech-recognition/blob/HEAD/docs/API.md#language-string
+    # language = "en-US"
+
+[UI]
+# Name of the app and chatbot.
+name = "Chatbot"
+
+# Show the readme while the conversation is empty.
+show_readme_as_default = true
+
+# Description of the app and chatbot. This is used for HTML tags.
+# description = ""
+
+# Large size content are by default collapsed for a cleaner ui
+default_collapse_content = true
+
+# The default value for the expand messages settings.
+default_expand_messages = false
+
+# Hide the chain of thought details from the user in the UI.
+hide_cot = false
+
+# Link to your github repo. This will add a github button in the UI's header.
+# github = ""
+
+# Specify a CSS file that can be used to customize the user interface.
+# The CSS file can be served from the public directory or via an external link.
+# custom_css = "/public/test.css"
+
+# Override default MUI light theme. (Check theme.ts)
+[UI.theme.light]
+    #background = "#FAFAFA"
+    #paper = "#FFFFFF"
+
+    [UI.theme.light.primary]
+        #main = "#F80061"
+        #dark = "#980039"
+        #light = "#FFE7EB"
+
+# Override default MUI dark theme. (Check theme.ts)
+[UI.theme.dark]
+    #background = "#FAFAFA"
+    #paper = "#FFFFFF"
+
+    [UI.theme.dark.primary]
+        #main = "#F80061"
+        #dark = "#980039"
+        #light = "#FFE7EB"
+
+
+[meta]
+generated_by = "0.7.400"

Dockerfile

@@ -0,0 +1,16 @@
+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
+RUN chown -R user:user $HOME/app
+RUN chmod -R 755 $HOME/app
+COPY ./requirements.txt ~/app/requirements.txt
+# Install the requirements
+RUN pip install --no-cache-dir -r requirements.txt
+COPY . .
+ENV ENV_FILE_PATH /.env
+EXPOSE 7860
+CMD ["chainlit", "run", "app.py", "--port", "7860"]

app.py

@@ -0,0 +1,136 @@
+import os
+from typing import List
+
+from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.vectorstores.chroma import Chroma
+from langchain.chains import (
+    ConversationalRetrievalChain,
+)
+from langchain.chat_models import ChatOpenAI
+from langchain.prompts.chat import (
+    ChatPromptTemplate,
+    SystemMessagePromptTemplate,
+    HumanMessagePromptTemplate,
+)
+from langchain.docstore.document import Document
+from langchain.memory import ChatMessageHistory, ConversationBufferMemory
+from langsmith_config import setup_langsmith_config
+import openai
+import chainlit as cl
+
+openai.api_key = os.environ["OPENAI_API_KEY"]
+setup_langsmith_config()
+
+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.
+
+And if the user greets with greetings like Hi, hello, How are you, etc reply accordingly as well.
+
+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():
+    files = None
+
+    # Wait for the user to upload a file
+    while files == None:
+        files = await cl.AskFileMessage(
+            content="Please upload a text file to begin!",
+            accept=["text/plain"],
+            max_size_mb=20,
+            timeout=180,
+        ).send()
+
+    file = files[0]
+
+    msg = cl.Message(
+        content=f"Processing `{file.name}`...", disable_human_feedback=True
+    )
+    await msg.send()
+
+    # Decode the file
+    text = file.content.decode("utf-8")
+
+    # Split the text into chunks
+    texts = text_splitter.split_text(text)
+
+    # Create a 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
+    )
+
+    message_history = ChatMessageHistory()
+
+    memory = ConversationBufferMemory(
+        memory_key="chat_history",
+        output_key="answer",
+        chat_memory=message_history,
+        return_messages=True,
+    )
+
+    # Create a chain that uses the Chroma vector store
+    chain = ConversationalRetrievalChain.from_llm(
+        ChatOpenAI(model_name="gpt-3.5-turbo", temperature=0, streaming=True),
+        chain_type="stuff",
+        retriever=docsearch.as_retriever(),
+        memory=memory,
+        return_source_documents=True,
+    )
+
+    # 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: cl.Message):
+    chain = cl.user_session.get("chain")  # type: ConversationalRetrievalChain
+    cb = cl.AsyncLangchainCallbackHandler()
+
+    res = await chain.acall(message.content, callbacks=[cb])
+    answer = res["answer"]
+    source_documents = res["source_documents"]  # type: List[Document]
+
+    text_elements = []  # type: List[cl.Text]
+
+    if source_documents:
+        for source_idx, source_doc in enumerate(source_documents):
+            source_name = f"source_{source_idx}"
+            # Create the text element referenced in the message
+            text_elements.append(
+                cl.Text(content=source_doc.page_content, name=source_name)
+            )
+        source_names = [text_el.name for text_el in text_elements]
+
+        if source_names:
+            answer += f"\nSources: {', '.join(source_names)}"
+        else:
+            answer += "\nNo sources found"
+
+    await cl.Message(content=answer, elements=text_elements).send()

chainlit.md

@@ -0,0 +1,12 @@
+# Welcome to Chainlit! 🚀🤖
+
+This is a demo project to help you get started with Chainlit. It contains a simple implementation of a Chainlit bot that can be deployed to the Huggingface Spaces platform, with Docker.
+- Langchain
+- Chainlit
+- ChromaDB
+
+
+## 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! 💬

langsmith_config.py

@@ -0,0 +1,8 @@
+import os
+
+def setup_langsmith_config():
+    os.environ["LANGCHAIN_ENDPOINT"] = "https://api.smith.langchain.com" # Update with your API URL if using a hosted instance of Langsmith.
+    os.environ["LANGCHAIN_API_KEY"] = os.environ["LANGCHAIN_API_KEY"] # Update with your API key
+    os.environ["LANGCHAIN_TRACING_V2"] = "true"
+    project_name = "qa-chainlit-langchain-demo" # Update with your project name
+    os.environ["LANGCHAIN_PROJECT"] = project_name # Optional: "default" is used if not set

requirements.txt

@@ -0,0 +1,5 @@
+chainlit
+openai
+tiktoken
+langchain
+chromadb