Upload 2 files

app.py

@@ -0,0 +1,90 @@
+import time
+from io import BytesIO
+from langchain.llms import OpenAI
+from dotenv import load_dotenv
+import os
+import streamlit as st
+import pandas as pd
+
+# Set the page configuration here
+st.set_page_config(page_title="Insightly")
+
+def main():
+    load_dotenv()
+
+    # Load the OpenAI API key from the environment variable
+    api_key = os.getenv("OPENAI_API_KEY")
+    if api_key is None or api_key == "":
+        st.error("OPENAI_API_KEY is not set")
+        return
+
+    st.sidebar.image("https://i.ibb.co/bX6GdqG/insightly-wbg.png", use_column_width=True)
+    st.title("Chat with Columns 💬")
+
+    csv_files = st.file_uploader("Upload CSV files", type="csv", accept_multiple_files=True)
+    if csv_files:
+        llm = OpenAI(temperature=0)
+        user_input = st.text_input("Question here:")
+
+        # Read the CSV file and get the column names
+        for csv_file in csv_files:
+            try:
+                df = pd.read_csv(csv_file)
+            except pd.errors.EmptyDataError:
+                st.error(f"Empty CSV file uploaded: {csv_file.name}")
+                continue
+
+            if df.empty:
+                st.error(f"Empty CSV file uploaded: {csv_file.name}")
+                continue
+
+            column_names = df.columns.tolist()
+
+            # Dropdown to select the column for prompts
+            column_for_prompt = st.selectbox("Select the column for prompts:", [None] + column_names)
+
+            if column_for_prompt is not None:
+                # Create a list to store the responses and original rows for each CSV file
+                responses_list = []
+                original_rows_list = []
+
+                # Check if the specified column for prompts exists in the DataFrame
+                if column_for_prompt not in df.columns:
+                    st.error(f"The column '{column_for_prompt}' does not exist in the CSV file: {csv_file.name}")
+                    continue
+
+                # Perform any necessary data preprocessing or feature engineering here
+                # You can modify the code based on your specific requirements
+
+                # Example: Accessing columns from the DataFrame
+                column_data = df[column_for_prompt]
+
+                # Loop through each row in the specified column and pass the user input as prompt
+                for row_value in column_data:
+                    original_rows_list.append(row_value)
+                    # Example: Using the preprocessed data with the OpenAI API
+                    llm_response = llm.predict(row_value + " " + user_input)
+                    responses_list.append(llm_response)
+
+                    # Introduce a delay of 1 second between API calls to reduce the rate of requests
+                    time.sleep(1)
+
+                # Create a new DataFrame containing the original rows and responses
+                response_df = pd.DataFrame({
+                    "Original Rows": original_rows_list,
+                    "Responses": responses_list
+                })
+
+                # Offer the option to download the responses as a CSV file
+                if st.button("Download Responses as CSV"):
+                    with BytesIO() as output_file:
+                        response_df.to_csv(output_file, index=False)
+                        st.download_button(
+                            label="Download CSV",
+                            data=output_file.getvalue(),
+                            file_name="responses.csv",
+                            mime="text/csv",
+                        )
+
+if __name__ == "__main__":
+    main()

requirements.txt

@@ -0,0 +1,69 @@
+aiohttp==3.8.5
+aiosignal==1.3.1
+altair==5.0.1
+async-timeout==4.0.2
+attrs==23.1.0
+blinker==1.6.2
+cachetools==5.3.1
+certifi==2023.7.22
+charset-normalizer==3.2.0
+click==8.1.6
+dataclasses-json==0.5.13
+decorator==5.1.1
+frozenlist==1.4.0
+gitdb==4.0.10
+GitPython==3.1.32
+greenlet==2.0.2
+idna==3.4
+importlib-metadata==6.8.0
+Jinja2==3.1.2
+jsonschema==4.18.4
+jsonschema-specifications==2023.7.1
+langchain==0.0.240
+langsmith==0.0.14
+markdown-it-py==3.0.0
+MarkupSafe==2.1.3
+marshmallow==3.20.1
+mdurl==0.1.2
+multidict==6.0.4
+mypy-extensions==1.0.0
+numexpr==2.8.4
+numpy==1.25.1
+openai==0.27.8
+openapi-schema-pydantic==1.2.4
+packaging==23.1
+pandas==2.0.3
+Pillow==9.5.0
+protobuf==4.23.4
+pyarrow==12.0.1
+pydantic==1.10.11
+pydeck==0.8.0
+Pygments==2.15.1
+Pympler==1.0.1
+python-dateutil==2.8.2
+python-dotenv==1.0.0
+pytz==2023.3
+pytz-deprecation-shim==0.1.0.post0
+PyYAML==6.0.1
+referencing==0.30.0
+requests==2.31.0
+rich==13.4.2
+rpds-py==0.9.2
+six==1.16.0
+smmap==5.0.0
+SQLAlchemy==2.0.19
+streamlit==1.25.0
+tenacity==8.2.2
+toml==0.10.2
+toolz==0.12.0
+tornado==6.3.2
+tqdm==4.65.0
+typing-inspect==0.9.0
+typing_extensions==4.7.1
+tzdata==2023.3
+tzlocal==4.3.1
+urllib3==2.0.4
+validators==0.20.0
+watchdog==3.0.0
+yarl==1.9.2
+zipp==3.16.2