Upload 7 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+db/chroma.sqlite3 filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,65 @@
+from langchain_openai import OpenAIEmbeddings
+from langchain_chroma import Chroma
+from langchain_openai import ChatOpenAI
+from langchain.chains import RetrievalQAWithSourcesChain
+import gradio as gr
+import os
+from dotenv import load_dotenv
+
+load_dotenv()
+
+
+openai_api_key = os.getenv("OPENAI_API_KEY")
+
+persist_directory = "db"
+
+embeddings = OpenAIEmbeddings()
+
+vector_store = Chroma(
+    persist_directory=persist_directory,
+    embedding_function=embeddings
+)
+retriever = vector_store.as_retriever(search_kwargs={"k": 3})
+
+llm = ChatOpenAI(model_name="gpt-4o", temperature=0.1)  # Modify model_name if you have access to GPT-4
+
+chain = RetrievalQAWithSourcesChain.from_chain_type(
+    llm=llm,
+    chain_type="stuff",
+    retriever = retriever,
+    return_source_documents=True)
+
+def respond(message, chat_history):  # 채팅봇의 응답을 처리하는 함수를 정의합니다.
+    result = chain.invoke(message)
+
+    bot_message = '<strong>' + result['answer'] + '</strong><br><br>'
+
+    for i, doc in enumerate(result['source_documents']):
+        text = doc.page_content[0:500].replace('\n', ' ')
+        page = str(doc.metadata['page'])
+        bot_message += '[' + '관련내용:' + doc.page_content[0:500].replace('\n', ' ') + '...' + '] '
+
+        # 빨간색 스타일 적용
+        bot_message += '<span style="color:red;">' + doc.metadata['source'] + '</span>'
+
+        # 파란색 스타일 적용
+        bot_message += '<span style="color:blue;">' + '(' +  page + '쪽)</span> '
+
+    chat_history.append((message, bot_message))  # 채팅 기록에 사용자의 메시지와 봇의 응답을 추가합니다.
+
+    return "", chat_history
+
+with gr.Blocks() as demo:  # gr.Blocks()를 사용하여 인터페이스를 생성합니다.
+    gr.Markdown("<div style='font-size: 30px; font-weight: bold;'>2023 유치원 생활기록부 QnA chatbot</div>")
+    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.
+    gr.Markdown("2023 유치원 생활기록부 기재요령 <a href='https://www.moe.go.kr/sn3hcv/doc.html?fn=65fcc64258de266d005f7156e03f04f2&rs=/upload/synap/202407/'>미리보기</a>")
+    gr.Markdown("2023 유치원 생활기록부 기재요령 다운로드 <a href='https://www.moe.go.kr/boardCnts/viewRenew.do?boardID=312&boardSeq=97281&lev=0&searchType=null&statusYN=W&page=1&s=moe&m=0301&opType=N'>이동하기</a>")
+    gr.Markdown("정확한 내용은 원본을 꼭 확인하시기 바랍니다.")
+    gr.Markdown('제작: 교사 서동성')
+
+demo.launch()  # 인터페이스를 실행합니다. 실행하면 사용자는 '입력' 텍스트박스에 메시지를 작성하고 제출할 수 있으며, '초기화' 버튼을 통해 채팅 기록을 초기화 할 수 있습니다.

db/1421bd68-8c9c-43d7-88da-a21aaec7146e/data_level0.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f18abd8c514282db82706e52b0a33ed659cd534e925a6f149deb7af9ce34bd8e
+size 6284000

db/1421bd68-8c9c-43d7-88da-a21aaec7146e/header.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:effaa959ce2b30070fdafc2fe82096fc46e4ee7561b75920dd3ce43d09679b21
+size 100

db/1421bd68-8c9c-43d7-88da-a21aaec7146e/length.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc19b1997119425765295aeab72d76faa6927d4f83985d328c26f20468d6cc76
+size 4000

db/1421bd68-8c9c-43d7-88da-a21aaec7146e/link_lists.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855
+size 0

db/chroma.sqlite3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:743b1d39ccd530beb250c80c98893b6bfd625bc6d3402b5bcdb75f2d05ced3ef
+size 1941504

requirements.txt

@@ -0,0 +1,136 @@
+aiofiles==23.2.1
+aiohttp==3.9.5
+aiosignal==1.3.1
+annotated-types==0.7.0
+anyio==4.4.0
+asgiref==3.8.1
+attrs==23.2.0
+backoff==2.2.1
+bcrypt==4.2.0
+build==1.2.1
+cachetools==5.4.0
+certifi==2024.7.4
+charset-normalizer==3.3.2
+chroma-hnswlib==0.7.6
+chromadb==0.5.5
+click==8.1.7
+coloredlogs==15.0.1
+contourpy==1.2.1
+cycler==0.12.1
+dataclasses-json==0.6.7
+Deprecated==1.2.14
+distro==1.9.0
+dnspython==2.6.1
+email_validator==2.2.0
+fastapi==0.111.1
+fastapi-cli==0.0.4
+ffmpy==0.3.2
+filelock==3.15.4
+flatbuffers==24.3.25
+fonttools==4.53.1
+frozenlist==1.4.1
+fsspec==2024.6.1
+google-auth==2.32.0
+googleapis-common-protos==1.63.2
+gradio==4.39.0
+gradio_client==1.1.1
+grpcio==1.65.1
+h11==0.14.0
+httpcore==1.0.5
+httptools==0.6.1
+httpx==0.27.0
+huggingface-hub==0.24.2
+humanfriendly==10.0
+idna==3.7
+importlib_metadata==8.0.0
+importlib_resources==6.4.0
+Jinja2==3.1.4
+jsonpatch==1.33
+jsonpointer==3.0.0
+kiwisolver==1.4.5
+kubernetes==30.1.0
+langchain==0.2.11
+langchain-chroma==0.1.2
+langchain-community==0.2.10
+langchain-core==0.2.23
+langchain-openai==0.1.17
+langchain-text-splitters==0.2.2
+langsmith==0.1.93
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+marshmallow==3.21.3
+matplotlib==3.9.1
+mdurl==0.1.2
+mmh3==4.1.0
+monotonic==1.6
+mpmath==1.3.0
+multidict==6.0.5
+mypy-extensions==1.0.0
+numpy==1.26.4
+oauthlib==3.2.2
+onnxruntime==1.18.1
+openai==1.37.0
+opentelemetry-api==1.26.0
+opentelemetry-exporter-otlp-proto-common==1.26.0
+opentelemetry-exporter-otlp-proto-grpc==1.26.0
+opentelemetry-instrumentation==0.47b0
+opentelemetry-instrumentation-asgi==0.47b0
+opentelemetry-instrumentation-fastapi==0.47b0
+opentelemetry-proto==1.26.0
+opentelemetry-sdk==1.26.0
+opentelemetry-semantic-conventions==0.47b0
+opentelemetry-util-http==0.47b0
+orjson==3.10.6
+overrides==7.7.0
+packaging==24.1
+pandas==2.2.2
+pillow==10.4.0
+posthog==3.5.0
+protobuf==4.25.4
+pyasn1==0.6.0
+pyasn1_modules==0.4.0
+pydantic==2.8.2
+pydantic_core==2.20.1
+pydub==0.25.1
+Pygments==2.18.0
+pyparsing==3.1.2
+pypdf==4.3.1
+PyPika==0.48.9
+pyproject_hooks==1.1.0
+python-dateutil==2.9.0.post0
+python-dotenv==1.0.1
+python-env==1.0.0
+python-multipart==0.0.9
+pytz==2024.1
+PyYAML==6.0.1
+regex==2024.7.24
+requests==2.32.3
+requests-oauthlib==2.0.0
+rich==13.7.1
+rsa==4.9
+ruff==0.5.4
+semantic-version==2.10.0
+shellingham==1.5.4
+six==1.16.0
+sniffio==1.3.1
+SQLAlchemy==2.0.31
+starlette==0.37.2
+sympy==1.13.1
+tenacity==8.5.0
+tiktoken==0.7.0
+tokenizers==0.19.1
+tomlkit==0.12.0
+tqdm==4.66.4
+typer==0.12.3
+typing-inspect==0.9.0
+typing_extensions==4.12.2
+tzdata==2024.1
+urllib3==2.2.2
+uvicorn==0.30.3
+uvloop==0.19.0
+watchfiles==0.22.0
+websocket-client==1.8.0
+websockets==11.0.3
+wrapt==1.16.0
+yarl==1.9.4
+zipp==3.19.2