Upload 7 files

.gitattributes

@@ -1,35 +1,35 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz 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
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

.streamlit/config.toml

@@ -0,0 +1,3 @@
+[server]
+enableXsrfProtection = false
+enableCORS = true

Dockerfile

@@ -1,20 +1,21 @@
-FROM python:3.13.5-slim
-
-WORKDIR /app
-
-RUN apt-get update && apt-get install -y \
-    build-essential \
-    curl \
-    git \
-    && rm -rf /var/lib/apt/lists/*
-
-COPY requirements.txt ./
-COPY src/ ./src/
-
-RUN pip3 install -r requirements.txt
-
-EXPOSE 8501
-
-HEALTHCHECK CMD curl --fail http://localhost:8501/_stcore/health
-
-ENTRYPOINT ["streamlit", "run", "src/streamlit_app.py", "--server.port=8501", "--server.address=0.0.0.0"]
+FROM python:3.11-slim
+
+WORKDIR /app
+
+RUN apt-get update && apt-get install -y \
+    build-essential \
+    curl \
+    git \
+    && rm -rf /var/lib/apt/lists/*
+
+COPY requirements.txt ./
+COPY src/ ./src/
+COPY .streamlit/config.toml .streamlit/config.toml
+
+RUN pip3 install -r requirements.txt
+
+EXPOSE 8501
+
+HEALTHCHECK CMD curl --fail http://localhost:8501/_stcore/health
+
+ENTRYPOINT ["streamlit", "run", "src/streamlit_app.py", "--server.port=8501", "--server.address=0.0.0.0", "--server.enableXsrfProtection=false", "--server.enableCORS=true"]

README.md

@@ -1,20 +1,19 @@
----
-title: Machine Learning Assignment 8
-emoji: 🚀
-colorFrom: red
-colorTo: red
-sdk: docker
-app_port: 8501
-tags:
-- streamlit
-pinned: false
-short_description: Streamlit template space
-license: apache-2.0
----
-
-# Welcome to Streamlit!
-
-Edit `/src/streamlit_app.py` to customize this app to your heart's desire. :heart:
-
-If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
-forums](https://discuss.streamlit.io).
+---
+title: Test Llama
+emoji: 🚀
+colorFrom: red
+colorTo: red
+sdk: docker
+app_port: 8501
+tags:
+- streamlit
+pinned: false
+short_description: Streamlit template space
+---
+
+# Welcome to Streamlit!
+
+Edit `/src/streamlit_app.py` to customize this app to your heart's desire. :heart:
+
+If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
+forums](https://discuss.streamlit.io).

requirements.txt

@@ -1,3 +1,15 @@
-altair
-pandas
-streamlit
+langchain>=0.1.20,<0.2
+langchain-community>=0.0.38,<0.1
+langchain-text-splitters
+langchain-groq>=0.1.5
+PyPDF2==3.0.1
+faiss-cpu==1.7.4
+pypdf==4.2.0
+chromadb==0.4.24
+tiktoken==0.7.0
+streamlit==1.33.0
+streamlit-extras==0.4.2
+InstructorEmbedding==1.0.1
+sentence-transformers==2.5.1
+huggingface-hub==0.22.2
+python-dotenv==1.0.1

src/htmlTemplates.py

@@ -0,0 +1,44 @@
+css = '''
+<style>
+.chat-message {
+    padding: 1.5rem; border-radius: 0.5rem; margin-bottom: 1rem; display: flex
+}
+.chat-message.user {
+    background-color: #2b313e
+}
+.chat-message.bot {
+    background-color: #475063
+}
+.chat-message .avatar {
+  width: 20%;
+}
+.chat-message .avatar img {
+  max-width: 78px;
+  max-height: 78px;
+  border-radius: 50%;
+  object-fit: cover;
+}
+.chat-message .message {
+  width: 80%;
+  padding: 0 1.5rem;
+  color: #fff;
+}
+'''
+
+bot_template = '''
+<div class="chat-message bot">
+    <div class="avatar">
+        <img src="https://i.ibb.co/cN0nmSj/Screenshot-2023-05-28-at-02-37-21.png" style="max-height: 78px; max-width: 78px; border-radius: 50%; object-fit: cover;">
+    </div>
+    <div class="message">{{MSG}}</div>
+</div>
+'''
+
+user_template = '''
+<div class="chat-message user">
+    <div class="avatar">
+        <img src="https://i.ibb.co/rdZC7LZ/Photo-logo-1.png">
+    </div>    
+    <div class="message">{{MSG}}</div>
+</div>
+'''

src/streamlit_app.py

@@ -1,40 +1,214 @@
-import altair as alt
-import numpy as np
-import pandas as pd
-import streamlit as st
-
-"""
-# Welcome to Streamlit!
-
-Edit `/streamlit_app.py` to customize this app to your heart's desire :heart:.
-If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
-forums](https://discuss.streamlit.io).
-
-In the meantime, below is an example of what you can do with just a few lines of code:
-"""
-
-num_points = st.slider("Number of points in spiral", 1, 10000, 1100)
-num_turns = st.slider("Number of turns in spiral", 1, 300, 31)
-
-indices = np.linspace(0, 1, num_points)
-theta = 2 * np.pi * num_turns * indices
-radius = indices
-
-x = radius * np.cos(theta)
-y = radius * np.sin(theta)
-
-df = pd.DataFrame({
-    "x": x,
-    "y": y,
-    "idx": indices,
-    "rand": np.random.randn(num_points),
-})
-
-st.altair_chart(alt.Chart(df, height=700, width=700)
-    .mark_point(filled=True)
-    .encode(
-        x=alt.X("x", axis=None),
-        y=alt.Y("y", axis=None),
-        color=alt.Color("idx", legend=None, scale=alt.Scale()),
-        size=alt.Size("rand", legend=None, scale=alt.Scale(range=[1, 150])),
-    ))
+import streamlit as st
+from dotenv import load_dotenv
+# from langchain.text_splitter import CharacterTextSplitter, RecursiveCharacterTextSplitter
+# from langchain.vectorstores import FAISS
+# from langchain.embeddings import HuggingFaceEmbeddings  # General embeddings from HuggingFace models.
+from langchain.memory import ConversationBufferMemory
+from langchain.chains import ConversationalRetrievalChain
+from htmlTemplates import css, bot_template, user_template
+# from langchain.llms import LlamaCpp  # For loading transformer models.
+# from langchain.document_loaders import PyPDFLoader, TextLoader, JSONLoader, CSVLoader
+# 텍스트 스플리터
+from langchain_text_splitters import CharacterTextSplitter, RecursiveCharacterTextSplitter
+
+# 벡터스토어/임베딩/LLM
+from langchain_community.vectorstores import FAISS
+from langchain_community.embeddings import HuggingFaceEmbeddings
+
+# 로더들 (pebblo/pwd 끌려오지 않게 서브모듈로)
+from langchain_community.document_loaders.pdf import PyPDFLoader
+from langchain_community.document_loaders.text import TextLoader
+from langchain_community.document_loaders.csv_loader import CSVLoader
+from langchain_community.document_loaders.json_loader import JSONLoader
+import tempfile # 임시 파일을 생성하기 위한 라이브러리입니다.
+import os
+import json
+from langchain.docstore.document import Document
+from langchain_groq import ChatGroq
+
+# PDF 문서로부터 텍스트를 추출하는 함수입니다.
+def get_pdf_text(pdf_docs):
+    temp_dir = tempfile.TemporaryDirectory() # 임시 디렉토리를 생성합니다.
+    temp_filepath = os.path.join(temp_dir.name, pdf_docs.name) # 임시 파일 경로를 생성합니다.
+    with open(temp_filepath, "wb") as f:  # 임시 파일을 바이너리 쓰기 모드로 엽니다.
+        f.write(pdf_docs.getvalue()) # PDF 문서의 내용을 임시 파일에 씁니다.
+    pdf_loader = PyPDFLoader(temp_filepath) # PyPDFLoader를 사용해 PDF를 로드합니다.
+    pdf_doc = pdf_loader.load() # 텍스트를 추출합니다.
+    return pdf_doc # 추출한 텍스트를 반환합니다.
+
+
+def get_text_file(docs):
+    #################### 내용을 추가할 부분
+    return text_doc
+
+
+def get_csv_file(docs):
+    #################### 내용을 추가할 부분
+    return csv_doc
+
+# def get_json_file(docs):
+#     temp_dir = tempfile.TemporaryDirectory()
+#     temp_filepath = os.path.join(temp_dir.name, docs.name)
+#     with open(temp_filepath, "wb") as f:
+#         f.write(docs.getvalue())
+#     json_loader = JSONLoader(temp_filepath,
+#                                  jq_schema='.scans[].relationships',
+#                                  text_content=False)
+#
+#     json_doc = json_loader.load()
+#     # print('json_doc = ',json_doc)
+#     return json_doc
+
+def get_json_file(file) -> list[Document]:
+    # Streamlit UploadedFile -> str
+    raw = file.getvalue().decode("utf-8", errors="ignore")
+    data = json.loads(raw)
+
+    docs = []
+
+    # 예전 jq 경로가 '.scans[].relationships'였다면, 동일한 의미로 파싱:
+    # 존재하면 그것만 뽑고, 없으면 통으로 문서화
+    def add_doc(x):
+        docs.append(Document(page_content=json.dumps(x, ensure_ascii=False)))
+
+    if isinstance(data, dict) and "scans" in data and isinstance(data["scans"], list):
+        for s in data["scans"]:
+            rels = s.get("relationships", [])
+            if isinstance(rels, list) and rels:
+                for r in rels:
+                    add_doc(r)
+        if not docs:  # 그래도 못 뽑았으면 전체를 하나로
+            add_doc(data)
+    elif isinstance(data, list):
+        for item in data:
+            add_doc(item)
+    else:
+        add_doc(data)
+
+    return docs
+
+# 문서들을 처리하여 텍스트 청크로 나누는 함수입니다.
+def get_text_chunks(documents):
+    text_splitter = RecursiveCharacterTextSplitter(
+        chunk_size=1000,  # 청크의 크기를 지정합니다.
+        chunk_overlap=200,  # 청크 사이의 중복을 지정합니다.
+        length_function=len  # 텍스트의 길이를 측정하는 함수를 지정합니다.
+    )
+
+    documents = text_splitter.split_documents(documents)  # 문서들을 청크로 나눕니다.
+    return documents  # 나눈 청크를 반환합니다.
+
+
+# 텍스트 청크들로부터 벡터 스토어를 생성하는 함수입니다.
+def get_vectorstore(text_chunks):
+    # 원하는 임베딩 모델을 로드합니다.
+    embeddings = HuggingFaceEmbeddings(model_name='sentence-transformers/all-MiniLM-L12-v2',
+                                       model_kwargs={'device': 'cpu'})  # 임베딩 모델을 설정합니다.
+    vectorstore = FAISS.from_documents(text_chunks, embeddings)  # FAISS 벡터 스토어를 생성합니다.
+    return vectorstore  # 생성된 벡터 스토어를 반환합니다.
+
+
+def get_conversation_chain(vectorstore):
+    # Groq LLM
+    llm = ChatGroq(
+        groq_api_key=os.environ.get("GROQ_API_KEY"),
+        model_name="llama-3.1-8b-instant",
+        temperature=0.75,      # 필요에 맞게 튜닝
+        max_tokens=512        # 컨텍스트 초과 방지용 (필요시 조정)
+    )
+
+    memory = ConversationBufferMemory(
+        memory_key="chat_history",
+        return_messages=True
+    )
+    retriever = vectorstore.as_retriever(search_kwargs={"k": 3})
+
+    conversation_chain = ConversationalRetrievalChain.from_llm(
+        llm=llm,
+        retriever=retriever,
+        memory=memory,
+    )
+    return conversation_chain
+
+# 사용자 입력을 처리하는 함수입니다.
+def handle_userinput(user_question):
+    print('user_question =>  ', user_question)
+    # 대화 체인을 사용하여 사용자 질문에 대한 응답을 생성합니다.
+    response = st.session_state.conversation({'question': user_question})
+    # 대화 기록을 저장합니다.
+    st.session_state.chat_history = response['chat_history']
+
+    for i, message in enumerate(st.session_state.chat_history):
+        if i % 2 == 0:
+            st.write(user_template.replace(
+                "{{MSG}}", message.content), unsafe_allow_html=True)
+        else:
+            st.write(bot_template.replace(
+                "{{MSG}}", message.content), unsafe_allow_html=True)
+
+
+def main():
+    load_dotenv()
+    st.set_page_config(page_title="Basic_RAG_AI_Chatbot_with_Llama",
+                       page_icon=":books:")
+    st.write(css, unsafe_allow_html=True)
+
+    if "conversation" not in st.session_state:
+        st.session_state.conversation = None
+    if "chat_history" not in st.session_state:
+        st.session_state.chat_history = None
+
+    st.header("Basic_RAG_AI_Chatbot_with_Llama3 :books:")
+    user_question = st.text_input("Ask a question about your documents:")
+    if user_question:
+        handle_userinput(user_question)
+
+    with st.sidebar:
+        st.subheader("Your documents")
+        docs = st.file_uploader(
+            "Upload your Files here and click on 'Process'", accept_multiple_files=True)
+        if st.button("Process[PDF]"):
+            with st.spinner("Processing"):
+                # get pdf text
+                doc_list = []
+                for file in docs:
+                    print('file - type : ', file.type)
+                    if file.type in ['application/octet-stream', 'application/pdf']:
+                        # file is .pdf
+                        doc_list.extend(get_pdf_text(file))
+                    else:
+                        st.error("PDF 파일이 아닙니다.")
+                if not doc_list:
+                    st.error("처리 가능한 문서를 찾지 못했습니다.")
+                    st.stop()
+
+                text_chunks = get_text_chunks(doc_list)
+                vectorstore = get_vectorstore(text_chunks)
+                st.session_state.conversation = get_conversation_chain(vectorstore)
+
+        ################## TXT, CSV 버튼 구현
+        # TXT 버튼 구현 참고 : if file.type == 'text/plain':
+        # CSV 버튼 구현 참고 : if file.type == 'text/csv':
+
+        if st.button("Process[JSON]"):
+            with st.spinner("Processing"):
+                # get txt text
+                doc_list = []
+                for file in docs:
+                    print('file - type : ', file.type)
+                    if file.type == 'application/json':
+                        # file is .json
+                        doc_list.extend(get_json_file(file))
+                    else:
+                        st.error("JSON 파일이 아닙니다.")
+                if not doc_list:
+                    st.error("처리 가능한 문서를 찾지 못했습니다.")
+                    st.stop()
+
+                text_chunks = get_text_chunks(doc_list)
+                vectorstore = get_vectorstore(text_chunks)
+                st.session_state.conversation = get_conversation_chain(vectorstore)
+
+
+if __name__ == '__main__':
+    main()