changing to add basic contextual options before analyzing data

app.py

@@ -1,68 +1,31 @@
-# Bring in deps
 import streamlit as st 
-from langchain.llms import LlamaCpp
-from langchain.embeddings import LlamaCppEmbeddings
-from langchain.prompts import PromptTemplate
-from langchain.chains import LLMChain
-from langchain.document_loaders import CSVLoader  # Import CSVLoader
-from langchain.text_splitter import CharacterTextSplitter
-from langchain.vectorstores import Chroma
+from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
 import pandas as pd
 
-# Customize the layout
-st.set_page_config(page_title="DOCAI", page_icon="🤖", layout="wide", )     
-st.markdown(f"""
-            <style>
-            .stApp {{background-image: url("https://images.unsplash.com/photo-1509537257950-20f875b03669?ixlib=rb-4.0.3&ixid=M3wxMjA3fDB8MHxwaG90by1wYWdlfHx8fGVufDB8fHx8fA%3D%3D&auto=format&fit=crop&w=1469&q=80"); 
-                     background-attachment: fixed;
-                     background-size: cover}}
-         </style>
-         """, unsafe_allow_html=True)
-
-# function for writing uploaded file in temp
-def write_csv_file(content, file_path):
-    try:
-        with open(file_path, 'w') as file:
-            file.write(content)
-        return True
-    except Exception as e:
-        print(f"Error occurred while writing the file: {e}")
-        return False
-
-# set prompt template
-prompt_template = """Use the following pieces of context to answer the question at the end. If you don't know the answer, just say that you don't know, don't try to make up an answer.
-
-{context}
-
-Question: {question}
-Answer:"""
-prompt = PromptTemplate(template=prompt_template, input_variables=["context", "question"])
-
-# initialize the LLM & Embeddings
-llm = LlamaCpp(model_path="./models/llama-7b.ggmlv3.q4_0.bin")
-embeddings = LlamaCppEmbeddings(model_path="models/llama-7b.ggmlv3.q4_0.bin")
-llm_chain = LLMChain(llm=llm, prompt=prompt)
+# Initialize the LLM from HuggingFace
+tokenizer = AutoTokenizer.from_pretrained("upstage/SOLAR-0-70b-16bit")
+model = AutoModelForCausalLM.from_pretrained("upstage/SOLAR-0-70b-16bit")
+pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
 
 st.title("📄 Document Conversation 🤖")
-uploaded_file = st.file_uploader("Upload a CSV file", type="csv")  # Change type to csv
+uploaded_file = st.file_uploader("Upload a CSV file", type="csv")
 
 if uploaded_file is not None:
-    content = uploaded_file.read().decode('utf-8')
-    file_path = "temp/file.csv"
-    write_csv_file(content, file_path)   
-    
-    loader = CSVLoader(file_path)  # Use CSVLoader
-    docs = loader.load()    
-    text_splitter = CharacterTextSplitter(chunk_size=100, chunk_overlap=0)
-    texts = text_splitter.split_documents(docs)
-    db = Chroma.from_documents(texts, embeddings)    
-    st.success("File Loaded Successfully!!")
+    df = pd.read_csv(uploaded_file)
+    st.write(f"Loaded CSV with {df.shape[0]} rows and {df.shape[1]} columns.")
+    st.write("Columns:", df.columns.tolist())
     
-    # Query through LLM    
-    question = st.text_input("Ask something from the file", placeholder="Find something similar to: ....this.... in the text?", disabled=not uploaded_file,)    
-    if question:
-        similar_doc = db.similarity_search(question, k=1)
-        context = similar_doc[0].page_content
-        query_llm = LLMChain(llm=llm, prompt=prompt)
-        response = query_llm.run({"context": context, "question": question})        
-        st.write(response)
+    # Allow user to select columns to focus on
+    selected_columns = st.multiselect("Select columns to focus on:", df.columns.tolist())
+    if selected_columns:
+        st.write(df[selected_columns].head())  # Display first few rows of selected columns
+        
+        # Generate a textual representation of the selected data
+        context = f"The selected data has columns: {', '.join(selected_columns)}. Here are the first few entries: {df[selected_columns].head().to_string(index=False)}"
+        
+        # Query through LLM    
+        question = st.text_input("Ask something about the selected data", placeholder="What is the average of ...?")    
+        if question:
+            full_query = context + " " + question
+            response = pipe(full_query, max_length=250, do_sample=True, top_k=50)
+            st.write(response[0]['generated_text'])