feat: 데일 카네기 챗봇

.gitignore

@@ -0,0 +1,265 @@
+# File created using '.gitignore Generator' for Visual Studio Code: https://bit.ly/vscode-gig
+# Created by https://www.toptal.com/developers/gitignore/api/visualstudiocode,macos,circuitpython,python,pythonvanilla
+# Edit at https://www.toptal.com/developers/gitignore?templates=visualstudiocode,macos,circuitpython,python,pythonvanilla
+
+### CircuitPython ###
+.Trashes
+.metadata_never_index
+.fseventsd/
+boot_out.txt
+
+### macOS ###
+# General
+.DS_Store
+.AppleDouble
+.LSOverride
+
+# Icon must end with two \r
+Icon
+
+
+# Thumbnails
+._*
+
+# Files that might appear in the root of a volume
+.DocumentRevisions-V100
+.fseventsd
+.Spotlight-V100
+.TemporaryItems
+.VolumeIcon.icns
+.com.apple.timemachine.donotpresent
+
+# Directories potentially created on remote AFP share
+.AppleDB
+.AppleDesktop
+Network Trash Folder
+Temporary Items
+.apdisk
+
+### macOS Patch ###
+# iCloud generated files
+*.icloud
+
+### Python ###
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+### Python Patch ###
+# Poetry local configuration file - https://python-poetry.org/docs/configuration/#local-configuration
+poetry.toml
+
+# ruff
+.ruff_cache/
+
+# LSP config files
+pyrightconfig.json
+
+### PythonVanilla ###
+# Byte-compiled / optimized / DLL files
+
+# C extensions
+
+# Distribution / packaging
+
+# Installer logs
+
+# Unit test / coverage reports
+
+# Translations
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+
+
+### VisualStudioCode ###
+.vscode/*
+!.vscode/settings.json
+!.vscode/tasks.json
+!.vscode/launch.json
+!.vscode/extensions.json
+!.vscode/*.code-snippets
+
+# Local History for Visual Studio Code
+.history/
+
+# Built Visual Studio Code Extensions
+*.vsix
+
+### VisualStudioCode Patch ###
+# Ignore all local history of files
+.history
+.ionide
+
+# End of https://www.toptal.com/developers/gitignore/api/visualstudiocode,macos,circuitpython,python,pythonvanilla
+
+# Custom rules (everything added below won't be overriden by 'Generate .gitignore File' if you use 'Update' option)
+*.ipynb
+*.pdf

README.md

@@ -1,13 +1,14 @@
 ---
 title: Talk2carnegie
-emoji: 🚀
+emoji: 🧙🏻‍♂️
 colorFrom: blue
 colorTo: purple
 sdk: gradio
 sdk_version: 3.35.2
 app_file: app.py
 pinned: false
-license: mit
+license: openrail
+duplicated_from: anpigon/talktosayno
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,88 @@
+import gradio as gr
+from langchain.chains import RetrievalQAWithSourcesChain
+from langchain.chat_models import ChatOpenAI
+from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain.prompts.chat import (
+    ChatPromptTemplate,
+    HumanMessagePromptTemplate,
+    SystemMessagePromptTemplate,
+)
+from langchain.vectorstores import Chroma
+
+from constants import persist_directory
+
+embedding = OpenAIEmbeddings()
+vector_store = Chroma(persist_directory=persist_directory, embedding_function=embedding)
+retriever = vector_store.as_retriever(search_kwargs={"k": 5})
+
+llm = ChatOpenAI(model_name="gpt-3.5-turbo", temperature=0)
+
+system_template = """Your name is Dale Carnegie. You act like Dale Carnegie. 
+Never reveal that it is an AI. Use the following pieces of context to answer the users question shortly.
+Given the following summaries of a long document and a question, create a final answer with references.
+If you don't know the answer, just say that "I don't know", don't try to make up an answer.
+----------------
+{summaries}
+
+You MUST answer in Korean and in Markdown format:"""
+
+messages = [
+    SystemMessagePromptTemplate.from_template(system_template),
+    HumanMessagePromptTemplate.from_template("{question}"),
+]
+
+prompt = ChatPromptTemplate.from_messages(messages)
+
+chain_type_kwargs = {"prompt": prompt}
+
+chain = RetrievalQAWithSourcesChain.from_chain_type(
+    llm=llm,
+    chain_type="stuff",
+    retriever=retriever,
+    return_source_documents=True,
+    chain_type_kwargs=chain_type_kwargs,
+    reduce_k_below_max_tokens=True,
+    verbose=True,
+)
+
+
+# 채팅봇의 응답을 처리하는 함수를 정의합니다.
+def respond(message, chat_history):
+    result = chain(message)
+
+    bot_message = result["answer"]
+    source_documents = result["source_documents"]
+    
+    # 문서 출처를 이쁘게 출력합니다.
+    # if source_documents:
+    #     bot_message += "\n\n**문서 출처:**\n"
+    #     for doc in source_documents:
+    #         source = doc.metadata['source']
+    #         page = doc.metadata['page']
+    #         bot_message += f"1. {source}({page})\n"
+
+    # 채팅 기록에 사용자의 메시지와 봇의 응답을 추가합니다.
+    chat_history.append((message, bot_message))        
+
+    # 수정된 채팅 기록을 반환합니다.
+    return "", chat_history
+
+
+# gr.Blocks()를 사용하여 인터페이스를 생성합니다.
+with gr.Blocks(theme=gr.themes.Glass()) as demo:
+    gr.Image("images/avatar.webp", label="데일 카네기", show_label=False).style(height=156, width=104)
+    gr.Markdown("# 안녕하세요. 데일 카네기와 대화해보세요.")
+    chatbot = gr.Chatbot(label="채팅창")  # '채팅창'이라는 레이블을 가진 채팅봇 컴포넌트를 생성합니다.
+    msg = gr.Textbox(label="입력")  # '입력'이라는 레이블을 가진 텍스트박스를 생성합니다.
+    clear = gr.Button("초기화")  # '초기화'라는 레이블을 가진 버튼을 생성합니다.
+
+    msg.submit(
+        respond, [msg, chatbot], [msg, chatbot]
+    )  # 텍스트박스에 메시지를 입력하고 제출하면 respond 함수가 호출되도록 합니다.
+    clear.click(
+        lambda: None, None, chatbot, queue=False
+    )  # '초기화' 버튼을 클릭하면 채팅 기록을 초기화합니다.
+
+demo.launch(
+    debug=True
+)  # 인터페이스를 실행합니다. 실행하면 사용자는 '입력' 텍스트박스에 메시지를 작성하고 제출할 수 있으며, '초기화' 버튼을 통해 채팅 기록을 초기화 할 수 있습니다.

constants.py

@@ -0,0 +1 @@
+persist_directory = 'db'

db/chroma-collections.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98b04e5e0287d1f8f2a33a1c1db066db89a5100338498dbfba57284c6835dc6a
+size 557

db/chroma-embeddings.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88c09fa2ec0451da7cbc6a669495dc18fdc0cf76726c23b3df4ef024f6dcbb45
+size 19170317

db/index/id_to_uuid_bbb02123-23a2-41be-8b48-43d7d15f02d4.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e7ab43887a04020a42fadb7b985f5f994be44e882bf143c711787ccb572aa1e
+size 49066

db/index/index_bbb02123-23a2-41be-8b48-43d7d15f02d4.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c3e77da9bdfa6719a85b58ca26c0f40be2ef57d0ae68d9998c8880da56f1f58
+size 9546608

db/index/index_metadata_bbb02123-23a2-41be-8b48-43d7d15f02d4.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01f2a30711ac971224add2d51009c6a9cf7aa4031ac2b6425dfab4a6a8725bf1
+size 105

db/index/uuid_to_id_bbb02123-23a2-41be-8b48-43d7d15f02d4.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:999c5b118385adc1eeaa5309367ca772b094756f84575ae2aebc4b08e2c32785
+size 57409

ingest.py

@@ -0,0 +1,27 @@
+from langchain.document_loaders import PyPDFDirectoryLoader
+from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.vectorstores import Chroma
+
+from constants import persist_directory
+
+loader = PyPDFDirectoryLoader("docs/")
+documents = loader.load()
+
+text_splitter = RecursiveCharacterTextSplitter(
+    chunk_size=1000,
+    chunk_overlap=200,
+    separators=["\n\n", "\n", ".", "!", ",", " ", ""],
+    keep_separator=True,
+)
+texts = text_splitter.split_documents(documents)
+
+embedding = OpenAIEmbeddings()
+
+vectordb = Chroma.from_documents(
+    documents=texts,
+    embedding=embedding,
+    persist_directory=persist_directory,
+)
+
+vectordb.persist()

requirements.txt

@@ -0,0 +1,6 @@
+openai==0.27.8
+langchain==0.0.196
+pypdf==3.9.1
+chromadb==0.3.26
+tiktoken==0.4.0
+gradio==3.34.0