Duplicate from felix-weiland/dn

.gitattributes

@@ -0,0 +1,34 @@
+*.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
+*.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

README.md

@@ -0,0 +1,13 @@
+---
+title: Dn
+emoji: 📚
+colorFrom: red
+colorTo: green
+sdk: streamlit
+sdk_version: 1.21.0
+app_file: app.py
+pinned: false
+duplicated_from: felix-weiland/dn
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,165 @@
+from dataclasses import dataclass
+from typing import Literal
+import streamlit as st
+from langchain.chat_models import ChatOpenAI
+from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain.text_splitter import CharacterTextSplitter
+from langchain.vectorstores import Chroma
+from langchain.document_loaders.csv_loader import CSVLoader
+from langchain.callbacks import get_openai_callback
+from langchain.chains import ConversationChain
+from langchain.chains.conversation.memory import ConversationSummaryMemory
+from langchain.memory import ConversationBufferMemory
+from langchain.chains import ConversationalRetrievalChain
+import streamlit.components.v1 as components
+import os
+from langchain.chains import LLMChain
+from langchain.chains.question_answering import load_qa_chain
+from langchain.chains.conversational_retrieval.prompts import CONDENSE_QUESTION_PROMPT
+
+@dataclass
+class Message:
+    """Class for keeping track of a chat message."""
+    origin: Literal["human", "ai"]
+    message: str
+
+def load_css():
+    with open("static/styles.css", "r") as f:
+        css = f"<style>{f.read()}</style>"
+        st.markdown(css, unsafe_allow_html=True)
+
+@st.cache_resource()
+def load_index():
+    loader = CSVLoader(file_path='dagens_nyheter_new.csv')
+    doc = loader.load()
+    text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
+    docs = text_splitter.split_documents(doc)
+    embeddings = OpenAIEmbeddings()
+    docsearch = Chroma.from_documents(docs, embeddings)
+
+    return docsearch
+
+vectorstore = load_index()
+
+def initialize_session_state():
+    if "history" not in st.session_state:
+        st.session_state.history = []
+
+    if "token_count" not in st.session_state:
+        st.session_state.token_count = 0
+
+    if "conversation" not in st.session_state:
+
+        memory = ConversationSummaryMemory(
+            llm=ChatOpenAI(temperature=0, model='gpt-3.5-turbo-0613'), 
+            memory_key="chat_history",
+            return_messages=True
+        )
+
+        question_generator = LLMChain(
+            llm=ChatOpenAI(temperature=0, model="gpt-4"), 
+            prompt=CONDENSE_QUESTION_PROMPT
+        )
+        
+        doc_chain = load_qa_chain(
+            ChatOpenAI(temperature=0, model='gpt-3.5-turbo-16k'), 
+            chain_type="stuff"
+       )
+
+        st.session_state.conversation = ConversationalRetrievalChain(
+                retriever=vectorstore.as_retriever(search_kwargs=dict(k=50)),
+                question_generator=question_generator,
+                combine_docs_chain=doc_chain,
+                memory=memory
+        )
+
+def on_click_callback():
+
+    with get_openai_callback() as cb:
+        human_prompt = st.session_state.human_prompt
+        llm_response = st.session_state.conversation.run(
+            {"question": human_prompt}
+        )
+        st.session_state.history.append(
+            Message("human", human_prompt)
+        )
+        st.session_state.history.append(
+            Message("ai", llm_response)
+        )
+        st.session_state.token_count += cb.total_tokens
+        
+        # Reset the user input to empty string after sending the message
+        st.session_state.human_prompt = ""
+
+load_css()
+initialize_session_state()
+
+st.title("Dagens Nyheter Reviews")
+
+chat_placeholder = st.container()
+prompt_placeholder = st.form("chat-form")
+credit_card_placeholder = st.empty()
+
+with chat_placeholder:
+    for chat in st.session_state.history:
+        div = f"""
+<div class="chat-row 
+    {'' if chat.origin == 'ai' else 'row-reverse'}">
+    <img class="chat-icon" src="https://huggingface.co/spaces/felix-weiland/dn/resolve/main/static/{
+        'ai_icon.png' if chat.origin == 'ai' 
+                      else 'user_icon.png'}"
+         width=32 height=32>
+    <div class="chat-bubble
+    {'ai-bubble' if chat.origin == 'ai' else 'human-bubble'}">
+        &#8203;{chat.message}
+    </div>
+</div>
+        """
+        st.markdown(div, unsafe_allow_html=True)
+    
+    for _ in range(3):
+        st.markdown("")
+
+with prompt_placeholder:
+    st.markdown("**Chat**")
+    cols = st.columns((6, 1))
+    cols[0].text_input(
+        "Chat",
+        value="",
+        label_visibility="collapsed",
+        key="human_prompt",
+    )
+    cols[1].form_submit_button(
+        "Submit", 
+        type="primary", 
+        on_click=on_click_callback, 
+    )
+
+
+credit_card_placeholder.caption(f"""
+Used {st.session_state.token_count} tokens \n
+Debug Langchain conversation: 
+{st.session_state.conversation.memory.buffer}
+""")
+
+components.html("""
+<script>
+const streamlitDoc = window.parent.document;
+const buttons = Array.from(
+    streamlitDoc.querySelectorAll('.stButton > button')
+);
+const submitButton = buttons.find(
+    el => el.innerText === 'Submit'
+);
+streamlitDoc.addEventListener('keydown', function(e) {
+    switch (e.key) {
+        case 'Enter':
+            submitButton.click();
+            break;
+    }
+});
+</script>
+""", 
+    height=0,
+    width=0,
+)

requirements.txt

@@ -0,0 +1,7 @@
+altair==4.2.0
+chromadb==0.3.22
+langchain==0.0.198
+langchainplus-sdk==0.0.9
+openai==0.27.2
+pandas==2.0.2
+tiktoken==0.3.1

static/styles.css

@@ -0,0 +1,32 @@
+.chat-row {
+    display: flex;
+    margin: 5px;
+    width: 100%;
+}
+
+.row-reverse {
+    flex-direction: row-reverse;
+}
+
+.chat-bubble {
+    font-family: "Source Sans Pro", sans-serif, "Segoe UI", "Roboto", sans-serif;
+    border: 1px solid transparent;
+    padding: 5px 10px;
+    margin: 0px 7px;
+    max-width: 70%;
+}
+
+.ai-bubble {
+    background: rgb(240, 242, 246);
+    border-radius: 10px;
+}
+
+.human-bubble {
+    background:  rgb(0, 106, 255); 
+    color: white;
+    border-radius: 20px;
+}
+
+.chat-icon {
+    border-radius: 5px;
+}