Skip to content

Add support for Excel file upload in data-analysis-agent #300

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
23 changes: 20 additions & 3 deletions community/data-analysis-agent/data_analysis_agent.py
Original file line number Diff line number Diff line change
Expand Up @@ -19,15 +19,18 @@
from openai import OpenAI
import matplotlib.pyplot as plt
from typing import List, Dict, Any, Tuple
from dotenv import load_dotenv
load_dotenv()

# === Configuration ===
api_key = os.environ.get("NVIDIA_API_KEY")

client = OpenAI(
base_url="https://integrate.api.nvidia.com/v1",
api_key=api_key
)



# ------------------ QueryUnderstandingTool ---------------------------
def QueryUnderstandingTool(query: str) -> bool:
"""Return True if the query seems to request a visualisation based on keywords."""
Expand All @@ -39,6 +42,7 @@ def QueryUnderstandingTool(query: str) -> bool:

response = client.chat.completions.create(
model="nvidia/llama-3.1-nemotron-ultra-253b-v1",
#model="gpt-4o-mini",
messages=messages,
temperature=0.1,
max_tokens=5 # We only need a short response
Expand Down Expand Up @@ -95,6 +99,7 @@ def CodeGenerationAgent(query: str, df: pd.DataFrame):

response = client.chat.completions.create(
model="nvidia/llama-3.1-nemotron-ultra-253b-v1",
#model="gpt-4o-mini",
messages=messages,
temperature=0.2,
max_tokens=1024
Expand Down Expand Up @@ -160,6 +165,7 @@ def ReasoningAgent(query: str, result: Any):
# Streaming LLM call
response = client.chat.completions.create(
model="nvidia/llama-3.1-nemotron-ultra-253b-v1",
#model="gpt-4o-mini",
messages=[
{"role": "system", "content": "detailed thinking on. You are an insightful data analyst."},
{"role": "user", "content": prompt}
Expand Down Expand Up @@ -221,6 +227,7 @@ def DataInsightAgent(df: pd.DataFrame) -> str:
try:
response = client.chat.completions.create(
model="nvidia/llama-3.1-nemotron-ultra-253b-v1",
#model="gpt-4o-mini",
messages=[
{"role": "system", "content": "detailed thinking off. You are a data analyst providing brief, focused insights."},
{"role": "user", "content": prompt}
Expand Down Expand Up @@ -257,10 +264,20 @@ def main():
with left:
st.header("Data Analysis Agent")
st.markdown("<medium>Powered by <a href='https://build.nvidia.com/nvidia/llama-3_1-nemotron-ultra-253b-v1'>NVIDIA Llama-3.1-Nemotron-Ultra-253B-v1</a></medium>", unsafe_allow_html=True)
file = st.file_uploader("Choose CSV", type=["csv"])
#file = st.file_uploader("Choose CSV", type=["csv"])
file = st.file_uploader("Choose CSV or Excel", type=["csv", "xlsx"])

if file:
if ("df" not in st.session_state) or (st.session_state.get("current_file") != file.name):
st.session_state.df = pd.read_csv(file)
if file.name.endswith(".csv"):
st.session_state.df = pd.read_csv(file)
elif file.name.endswith(".xlsx"):
st.session_state.df = pd.read_excel(file)
else:
st.error("Unsupported file format.")
return


st.session_state.current_file = file.name
st.session_state.messages = []
with st.spinner("Generating dataset insights …"):
Expand Down
3 changes: 2 additions & 1 deletion community/data-analysis-agent/requirements.txt
Original file line number Diff line number Diff line change
Expand Up @@ -3,4 +3,5 @@ pandas>=2.2.0
matplotlib>=3.8.0
seaborn>=0.13.0
openai>=1.12.0
watchdog>=3.0.0
watchdog>=3.0.0
openpyxl>=3.1.0