Revert to copying code

app.py

@@ -1,6 +1,182 @@
-"""Main entrypoint for NoteBot on HuggingFace spaces."""
+"""Main entry point for NoteBot."""
+
+import argparse
+import os
+from pathlib import Path
+from typing import Callable, Final
+
+import gradio as gr
+from dotenv import load_dotenv
+from langchain.chains import ConversationalRetrievalChain
+from langchain.chat_models import ChatOpenAI
+from langchain.document_loaders import GitLoader
+from langchain.embeddings import OpenAIEmbeddings
+from langchain.memory import ConversationBufferMemory
+from langchain.text_splitter import MarkdownTextSplitter
+from langchain.vectorstores import FAISS
+
+ROOT_PATH: Final = Path(__file__).parent.parent
+DATA_PATH: Final = ROOT_PATH / "data"
+NOTES_PATH: Final = DATA_PATH / "notes"
+DB_PATH: Final = DATA_PATH / "db"
+NOTE_REPO_URL: Final = "https://github.com/slangenbach/notes.git"
+
+
+class NoteBot:
+    """Base class for interacting with NoteBot."""
+
+    def __init__(self, chain) -> None:
+        self.chain = chain
+
+    def get_response(self, question: str) -> dict:
+        return self.chain({"question": question})
+
+    def chat(self, message: str, history: list) -> str:
+        response = self.get_response(question=message)
+
+        return response["answer"]
+
+
+def filter_notes(file_path: str) -> bool:
+    """
+    Filter out none markdown notes and READMEs.
+
+    Args:
+        file_path (str): Path to file
+
+    Returns:
+        bool: Whether to filter out a note
+    """
+    return file_path.endswith(".md") and not file_path.endswith("README.md")
+
+
+def load_and_ingest_notes(note_repo_url: str, embedding) -> None:
+    """
+    Load markdown notes from Git repo and ingest them into vector store.
+
+    Args:
+        note_repo_url (str): URL of Git repo to load notes from
+        embeddings: Embeddings to use for vector store
+    """
+    loader = GitLoader(
+        repo_path=str(NOTES_PATH),
+        clone_url=note_repo_url,
+        file_filter=filter_notes,
+    )
+    splitter = MarkdownTextSplitter()
+    docs = loader.load_and_split(text_splitter=splitter)
+    db = FAISS.from_documents(documents=docs, embedding=embedding)
+    db.save_local(folder_path=str(DB_PATH))
+
+
+def get_chain(db):
+    """
+    Get LangChain to interact with notes.
+
+    Args:
+        db: Vector store
+
+    Returns:
+        LangChain chain
+    """
+    llm = ChatOpenAI(temperature=0)
+    memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)
+    chain = ConversationalRetrievalChain.from_llm(
+        llm=llm, retriever=db.as_retriever(), memory=memory
+    )
+
+    return chain
+
+
+def get_ui(chat_function: Callable) -> gr.ChatInterface:
+    """
+    Create NoteBot user interface
+
+    Args:
+        chat_function (Callable): Function to chat with NoteBot
+
+    Returns:
+        gr.ChatInterface: User Interface
+    """
+    ui = gr.ChatInterface(
+        fn=chat_function,
+        title="NoteBot",
+        examples=[
+            "List the title of all notes I can ask you about",
+            "Generate a brief summary of my LangChain notes",
+            "Do I have some notes related to COBOL?",
+        ],
+        cache_examples=False,
+    )
+
+    return ui
+
+
+def get_parser() -> argparse.ArgumentParser:
+    """
+    Get argument parser for CLI options.
+
+    Returns:
+        argparse.ArgumentParser: Parser
+    """
+    parser = argparse.ArgumentParser(description="Welcome to NoteBot")
+    parser.add_argument(
+        "--note-repo-url",
+        help="URL of Git repo to load notes from",
+        default=NOTE_REPO_URL,
+    )
+    parser.add_argument(
+        "--llm", help="LLM used by NoteBot", choices=["GPT"], default="GPT"
+    )
+    parser.add_argument(
+        "--openai-api-key", help="API key to interact with OpenAI models"
+    )
+
+    return parser
+
+
+def set_openai_api_key(key: str | None) -> None:
+    """
+    Set OpenAI API key enviroment variable if it has not been set already.
+
+    Args:
+        key (str | None): OpenAI API key
+    """
+    if not os.environ.get("OPENAI_API_KEY"):
+        if key:
+            os.environ["OPENAI_API_KEY"] = key
+        else:
+            load_dotenv()
+
+
+def app(run_local: bool = True):
+    """
+    Launch NoteBot app.
+
+    Args:
+        run_local (bool, optional): Whether to launch Notebook locally. Defaults to True.
+    """
+    if run_local:
+        parser = get_parser()
+        args = parser.parse_args()
+        repo_url = args.note_repo_url
+        set_openai_api_key(args.openai_api_key)
+    else:
+        repo_url = NOTE_REPO_URL
+        set_openai_api_key(key=None)
+
+    embedding = OpenAIEmbeddings()  # pyright: ignore[reportGeneralTypeIssues]
+
+    if not NOTES_PATH.exists() and not DB_PATH.exists():
+        load_and_ingest_notes(note_repo_url=repo_url, embedding=embedding)
+
+    db = FAISS.load_local(folder_path=str(DB_PATH), embeddings=embedding)
+    chain = get_chain(db=db)
+    notebot = NoteBot(chain=chain)
+    ui = get_ui(chat_function=notebot.chat)
+
+    ui.launch()
 
-from notebot.app import app
 
 if __name__ == "__main__":
-    app(run_local=False)
+    app()

notebot-0.1.1-py3-none-any.whl

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:70d4577e2a24cdbac83f5ddb9d9370e9bdebe1109ebdac66089caf1614d53f34
-size 4478

requirements.txt

@@ -1 +1,87 @@
-./notebot-0.1.1-py3-none-any.whl
+aiofiles==23.1.0 ; python_version >= "3.10" and python_version < "4.0"
+aiohttp==3.8.5 ; python_version >= "3.10" and python_version < "4.0"
+aiosignal==1.3.1 ; python_version >= "3.10" and python_version < "4.0"
+altair==5.0.1 ; python_version >= "3.10" and python_version < "4.0"
+anyio==3.7.1 ; python_version >= "3.10" and python_version < "4.0"
+async-timeout==4.0.2 ; python_version >= "3.10" and python_version < "4.0"
+attrs==23.1.0 ; python_version >= "3.10" and python_version < "4.0"
+certifi==2023.7.22 ; python_version >= "3.10" and python_version < "4.0"
+charset-normalizer==3.2.0 ; python_version >= "3.10" and python_version < "4.0"
+click==8.1.6 ; python_version >= "3.10" and python_version < "4.0"
+colorama==0.4.6 ; python_version >= "3.10" and python_version < "4.0" and platform_system == "Windows"
+contourpy==1.1.0 ; python_version >= "3.10" and python_version < "4.0"
+cycler==0.11.0 ; python_version >= "3.10" and python_version < "4.0"
+dataclasses-json==0.5.9 ; python_version >= "3.10" and python_version < "4.0"
+exceptiongroup==1.1.2 ; python_version >= "3.10" and python_version < "3.11"
+faiss-cpu==1.7.4 ; python_version >= "3.10" and python_version < "4.0"
+fastapi==0.100.1 ; python_version >= "3.10" and python_version < "4.0"
+ffmpy==0.3.1 ; python_version >= "3.10" and python_version < "4.0"
+filelock==3.12.2 ; python_version >= "3.10" and python_version < "4.0"
+fonttools==4.41.1 ; python_version >= "3.10" and python_version < "4.0"
+frozenlist==1.4.0 ; python_version >= "3.10" and python_version < "4.0"
+fsspec==2023.6.0 ; python_version >= "3.10" and python_version < "4.0"
+gitdb==4.0.10 ; python_version >= "3.10" and python_version < "4.0"
+gitpython==3.1.32 ; python_version >= "3.10" and python_version < "4.0"
+gradio-client==0.3.0 ; python_version >= "3.10" and python_version < "4.0"
+gradio==3.39.0 ; python_version >= "3.10" and python_version < "4.0"
+greenlet==2.0.2 ; python_version >= "3.10" and python_version < "4.0" and (platform_machine == "win32" or platform_machine == "WIN32" or platform_machine == "AMD64" or platform_machine == "amd64" or platform_machine == "x86_64" or platform_machine == "ppc64le" or platform_machine == "aarch64")
+h11==0.14.0 ; python_version >= "3.10" and python_version < "4.0"
+httpcore==0.17.3 ; python_version >= "3.10" and python_version < "4.0"
+httpx==0.24.1 ; python_version >= "3.10" and python_version < "4.0"
+huggingface-hub==0.16.4 ; python_version >= "3.10" and python_version < "4.0"
+idna==3.4 ; python_version >= "3.10" and python_version < "4.0"
+jinja2==3.1.2 ; python_version >= "3.10" and python_version < "4.0"
+jsonschema-specifications==2023.7.1 ; python_version >= "3.10" and python_version < "4.0"
+jsonschema==4.18.4 ; python_version >= "3.10" and python_version < "4.0"
+kiwisolver==1.4.4 ; python_version >= "3.10" and python_version < "4.0"
+langchain==0.0.249 ; python_version >= "3.10" and python_version < "4.0"
+langsmith==0.0.16 ; python_version >= "3.10" and python_version < "4.0"
+linkify-it-py==2.0.2 ; python_version >= "3.10" and python_version < "4.0"
+markdown-it-py==2.2.0 ; python_version >= "3.10" and python_version < "4.0"
+markdown-it-py[linkify]==2.2.0 ; python_version >= "3.10" and python_version < "4.0"
+markupsafe==2.1.3 ; python_version >= "3.10" and python_version < "4.0"
+marshmallow-enum==1.5.1 ; python_version >= "3.10" and python_version < "4.0"
+marshmallow==3.20.1 ; python_version >= "3.10" and python_version < "4.0"
+matplotlib==3.7.2 ; python_version >= "3.10" and python_version < "4.0"
+mdit-py-plugins==0.3.3 ; python_version >= "3.10" and python_version < "4.0"
+mdurl==0.1.2 ; python_version >= "3.10" and python_version < "4.0"
+multidict==6.0.4 ; python_version >= "3.10" and python_version < "4.0"
+mypy-extensions==1.0.0 ; python_version >= "3.10" and python_version < "4.0"
+numexpr==2.8.4 ; python_version >= "3.10" and python_version < "4.0"
+numpy==1.25.2 ; python_version >= "3.10" and python_version < "4.0"
+openai==0.27.8 ; python_version >= "3.10" and python_version < "4.0"
+openapi-schema-pydantic==1.2.4 ; python_version >= "3.10" and python_version < "4.0"
+orjson==3.9.2 ; python_version >= "3.10" and python_version < "4.0"
+packaging==23.1 ; python_version >= "3.10" and python_version < "4.0"
+pandas==2.0.3 ; python_version >= "3.10" and python_version < "4.0"
+pillow==10.0.0 ; python_version >= "3.10" and python_version < "4.0"
+pydantic==1.10.12 ; python_version >= "3.10" and python_version < "4.0"
+pydub==0.25.1 ; python_version >= "3.10" and python_version < "4.0"
+pyparsing==3.0.9 ; python_version >= "3.10" and python_version < "4.0"
+python-dateutil==2.8.2 ; python_version >= "3.10" and python_version < "4.0"
+python-dotenv==1.0.0 ; python_version >= "3.10" and python_version < "4.0"
+python-multipart==0.0.6 ; python_version >= "3.10" and python_version < "4.0"
+pytz==2023.3 ; python_version >= "3.10" and python_version < "4.0"
+pyyaml==6.0.1 ; python_version >= "3.10" and python_version < "4.0"
+referencing==0.30.0 ; python_version >= "3.10" and python_version < "4.0"
+regex==2023.6.3 ; python_version >= "3.10" and python_version < "4.0"
+requests==2.31.0 ; python_version >= "3.10" and python_version < "4.0"
+rpds-py==0.9.2 ; python_version >= "3.10" and python_version < "4.0"
+semantic-version==2.10.0 ; python_version >= "3.10" and python_version < "4.0"
+six==1.16.0 ; python_version >= "3.10" and python_version < "4.0"
+smmap==5.0.0 ; python_version >= "3.10" and python_version < "4.0"
+sniffio==1.3.0 ; python_version >= "3.10" and python_version < "4.0"
+sqlalchemy==2.0.19 ; python_version >= "3.10" and python_version < "4.0"
+starlette==0.27.0 ; python_version >= "3.10" and python_version < "4.0"
+tenacity==8.2.2 ; python_version >= "3.10" and python_version < "4.0"
+tiktoken==0.4.0 ; python_version >= "3.10" and python_version < "4.0"
+toolz==0.12.0 ; python_version >= "3.10" and python_version < "4.0"
+tqdm==4.65.0 ; python_version >= "3.10" and python_version < "4.0"
+typing-extensions==4.7.1 ; python_version >= "3.10" and python_version < "4.0"
+typing-inspect==0.9.0 ; python_version >= "3.10" and python_version < "4.0"
+tzdata==2023.3 ; python_version >= "3.10" and python_version < "4.0"
+uc-micro-py==1.0.2 ; python_version >= "3.10" and python_version < "4.0"
+urllib3==1.26.16 ; python_version >= "3.10" and python_version < "4.0"
+uvicorn==0.23.2 ; python_version >= "3.10" and python_version < "4.0"
+websockets==11.0.3 ; python_version >= "3.10" and python_version < "4.0"
+yarl==1.9.2 ; python_version >= "3.10" and python_version < "4.0"