Spaces:
Running
Running
File size: 4,158 Bytes
1d1e331 996504b 1d1e331 996504b 1d1e331 996504b 1d1e331 996504b 1d1e331 996504b 1d1e331 996504b 1d1e331 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 |
import os
import streamlit as st
import pandas as pd
import openai
import torch
import matplotlib.pyplot as plt
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
from dotenv import load_dotenv
import anthropic
import ast
import re
from langchain.agents import AgentType, initialize_agent
from langchain.tools import Tool
from langchain.chat_models import ChatOpenAI
from langchain.memory import ConversationBufferMemory
# Load environment variables
load_dotenv()
os.environ["OPENAI_API_KEY"] = os.getenv("OPENAI_API_KEY")
os.environ["ANTHROPIC_API_KEY"] = os.getenv("ANTHROPIC_API_KEY")
# UI Styling
st.markdown(
"""
<style>
.stButton button {
background-color: #1F6FEB;
color: white;
border-radius: 8px;
border: none;
padding: 10px 20px;
font-weight: bold;
}
.stButton button:hover {
background-color: #1A4FC5;
}
.stTextInput > div > input {
border: 1px solid #30363D;
background-color: #161B22;
color: #C9D1D9;
border-radius: 6px;
padding: 10px;
}
.stFileUploader > div {
border: 2px dashed #30363D;
background-color: #161B22;
color: #C9D1D9;
border-radius: 6px;
padding: 10px;
}
.response-box {
background-color: #161B22;
padding: 10px;
border-radius: 6px;
margin-bottom: 10px;
color: #FFFFFF;
}
</style>
""",
unsafe_allow_html=True
)
st.title("Excel Q&A Chatbot 📊")
# Initialize LangChain Agent with Multi-step Reasoning and Memory
def execute_query(query):
memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)
tool = Tool(
name="Pandas Query Executor",
func=lambda q: eval(q, {"df": df, "pd": pd}),
description="Executes Pandas-based queries on uploaded data"
)
agent = initialize_agent(
tools=[tool],
llm=ChatOpenAI(model_name="gpt-3.5-turbo", temperature=0),
agent=AgentType.CONVERSATIONAL_REACT_DESCRIPTION,
memory=memory,
verbose=True
)
return agent.run(query)
# Model Selection
model_choice = st.selectbox("Select LLM Model", ["OpenAI GPT-3.5", "Claude 3 Haiku", "Mistral-7B"])
# File Upload with validation
uploaded_file = st.file_uploader("Upload a file", type=["csv", "xlsx", "xls", "json", "tsv"])
if uploaded_file is not None:
file_extension = uploaded_file.name.split(".")[-1].lower()
try:
if file_extension == "csv":
df = pd.read_csv(uploaded_file)
elif file_extension in ["xlsx", "xls"]:
df = pd.read_excel(uploaded_file, engine="openpyxl")
elif file_extension == "json":
df = pd.read_json(uploaded_file)
elif file_extension == "tsv":
df = pd.read_csv(uploaded_file, sep="\t")
else:
st.error("Unsupported file format. Please upload a CSV, Excel, JSON, or TSV file.")
st.stop()
st.write("### Preview of Data:")
st.write(df.head())
# Extract metadata
column_names = df.columns.tolist()
data_types = df.dtypes.apply(lambda x: x.name).to_dict()
missing_values = df.isnull().sum().to_dict()
# Display metadata
st.write("### Column Details:")
st.write(pd.DataFrame({"Column": column_names, "Type": data_types.values(), "Missing Values": missing_values.values()}))
except Exception as e:
st.error(f"Error loading file: {str(e)}")
st.stop()
# User Query
query = st.text_input("Ask a question about this data:")
if st.button("Submit Query"):
if query:
try:
exec_result = execute_query(query)
st.write("### Result:")
st.write(exec_result)
except Exception as e:
st.error(f"Error executing query: {str(e)}")
# Memory for context retention
if "query_history" not in st.session_state:
st.session_state.query_history = []
st.session_state.query_history.append(query)
|