Create app.py

v.0.1
- add chat with chosen LLM Model,
- add Conversation History,
- add Dataset uploader

app.py

@@ -0,0 +1,78 @@
+import streamlit as st
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
+from langchain import HuggingFacePipeline
+from langchain_core.prompts import ChatPromptTemplate, HumanMessagePromptTemplate, SystemMessage
+from langchain_core.messages import SystemMessage
+import nltk
+import json
+import pandas as pd
+
+# Download nltk stopwords
+nltk.download('stopwords')
+
+# Function to load the conversation history
+def load_conversation_history(file):
+    with open(file, 'r') as f:
+        return json.load(f)
+
+# Function to save the conversation history
+def save_conversation_history(history, file):
+    with open(file, 'w') as f:
+        json.dump(history, f)
+
+# Initialize conversation history
+conversation_history = []
+if st.session_state.get('conversation_history'):
+    conversation_history = st.session_state.conversation_history
+
+# Title
+st.title('Culture AI v.0.1')
+
+# Model selection
+model_name = st.selectbox('Choose a model:', [
+    'mistralai/Mistral-7B-Instruct-v0.1',
+    'meta-llama/Meta-Llama-3–8B',
+    'microsoft/Phi-3-mini-4k-instruct',
+    'microsoft/phi-1_5',
+    'speakleash/Bielik-11B-v2.3-Instruct'
+    # Add more models as needed
+])
+
+# Upload dataset
+dataset_file = st.file_uploader('Upload your dataset (CSV format)', type='csv')
+if dataset_file:
+    df = pd.read_csv(dataset_file)
+
+# Initialize tokenizer and model
+tokenizer = AutoTokenizer.from_pretrained(model_name, use_fast=True)
+model = AutoModelForCausalLM.from_pretrained(model_name)
+pipe = pipeline("text-generation", model=model, tokenizer=tokenizer, return_full_text=True)
+llm = HuggingFacePipeline(pipeline=pipe)
+
+# Chat interface
+st.write('## Chat')
+topic = st.text_input('Enter a topic for the conversation:', 'Machine Learning')
+prompt = ChatPromptTemplate.from_messages([
+    SystemMessage(content=f"Write a response related to the input topic in one paragraph"),
+    HumanMessagePromptTemplate.from_template("```{topic}```"),
+])
+
+chain = prompt | llm
+
+if st.button('Generate Response'):
+    output = chain.invoke({"topic": topic})
+    st.write(output.content)
+    conversation_history.append({"user": topic, "assistant": output.content})
+
+# Save conversation history
+if st.button('Save Conversation History'):
+    save_conversation_history(conversation_history, 'conversation_history.json')
+    st.success('Conversation history saved!')
+
+# Display conversation history
+st.write('## Conversation History')
+st.write(conversation_history)
+
+# Update session state for conversation history
+st.session_state.conversation_history = conversation_history