Duplicate from Insightly/CSV-Bot

Co-authored-by: Shreya Sivakumar <[email protected]>

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,13 @@
+---
+title: CSV Bot
+emoji: 🏃
+colorFrom: indigo
+colorTo: red
+sdk: streamlit
+sdk_version: 1.21.0
+app_file: app.py
+pinned: false
+duplicated_from: Insightly/CSV-Bot
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,86 @@
+from tempfile import NamedTemporaryFile
+from langchain.agents import create_csv_agent
+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("Data Analysis 📈")
+
+    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:")
+
+        # Iterate over each CSV file
+        for csv_file in csv_files:
+            with NamedTemporaryFile(delete=False) as f:
+                f.write(csv_file.getvalue())
+                f.flush()
+                df = pd.read_csv(f.name)
+
+                # 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_name"]
+
+                # Example: Applying transformations or calculations to the data
+                # transformed_data = column_data.apply(lambda x: x * 2)
+
+                # Example: Using the preprocessed data with the OpenAI API
+                # llm_response = llm.predict(transformed_data)
+
+                if user_input:
+                    # Pass the user input to the OpenAI agent for processing
+                    agent = create_csv_agent(llm, f.name, verbose=True)
+                    response = agent.run(user_input)
+
+                    st.write(f"CSV File: {csv_file.name}")
+                    st.write("Response:")
+                    st.write(response)
+
+# Add links to the sidebar with the same spacing properties
+
+    st.sidebar.markdown("<p class='sidebar-link'>📚  <a href='https://chandrakalagowda-demo2.hf.space/'>  PDF Bot </a></p>", unsafe_allow_html=True)
+    st.sidebar.markdown("<p class='sidebar-link'>🖼️  <a href='https://insightly-image-reader.hf.space'>  Image Reader</a></p>", unsafe_allow_html=True)
+    st.sidebar.markdown("<p class='sidebar-link'>📸  <a href='https://insightly-frame-capturer.hf.space/'>  Frame Capturer</a></p>", unsafe_allow_html=True)
+
+# Custom CSS to style the link and create vertical space
+    st.markdown(
+        """
+        <style>
+        .image-container {
+            margin-bottom: 60px;
+        }
+        .sidebar-link {
+            display: flex;
+            justify-content: left;
+            font-size: 28px;
+            margin-top: 20px;
+            margin-left: 10px;
+        }
+        .vertical-space {
+            height: 20px;
+        }
+        </style>
+        """,
+        unsafe_allow_html=True,
+    )
+
+if __name__ == "__main__":
+    main()

emb.py

@@ -0,0 +1,80 @@
+import openai
+
+# Set up the OpenAI API credentials
+openai.api_key = "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"
+
+# Code snippet
+code = """
+from tempfile import NamedTemporaryFile
+from langchain.agents import create_csv_agent
+from langchain.llms import OpenAI
+from dotenv import load_dotenv
+import os
+import streamlit as st
+import pandas as pd
+
+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.set_page_config(page_title="Insightly")
+    st.sidebar.image("/home/oem/Downloads/insightly_wbg.png", use_column_width=True)
+    st.header("Data Analysis 📈")
+
+    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:")
+
+        # Iterate over each CSV file
+        for csv_file in csv_files:
+            with NamedTemporaryFile(delete=False) as f:
+                f.write(csv_file.getvalue())
+                f.flush()
+                df = pd.read_csv(f.name)
+
+                # 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_name"]
+
+                # Example: Applying transformations or calculations to the data
+                # transformed_data = column_data.apply(lambda x: x * 2)
+
+                # Example: Using the preprocessed data with the OpenAI API
+                # llm_response = llm.predict(transformed_data)
+
+                if user_input:
+                    # Pass the user input to the OpenAI agent for processing
+                    agent = create_csv_agent(llm, f.name, verbose=True)
+                    response = agent.run(user_input)
+
+                    st.write(f"CSV File: {csv_file.name}")
+                    st.write("Response:")
+                    st.write(response)
+
+if __name__ == "__main__":
+    main()
+"""
+
+# Retrieve the embeddings
+response = openai.Completion.create(
+    model="gpt-3.5-turbo",
+    documents=[code],
+    num_completions=1,
+    return_prompt=True,
+    return_sequences=False,
+    expand_prompt=False
+)
+
+# Extract the embeddings from the response
+embeddings = response.choices[0].embedding
+
+# Print the embeddings
+print(embeddings)

requirements.txt

@@ -0,0 +1,77 @@
+aiohttp==3.8.4
+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==2023.5.7
+charset-normalizer==3.1.0
+click==8.1.3
+Cython==0.29.35
+dataclasses-json==0.5.8
+decorator==5.1.1
+filelock==3.12.2
+frozenlist==1.3.3
+fsspec==2023.6.0
+gitdb==4.0.10
+GitPython==3.1.31
+greenlet==2.0.2
+huggingface==0.0.1
+huggingface-hub==0.15.1
+idna==3.4
+importlib-metadata==6.7.0
+Jinja2==3.1.2
+jsonschema==4.17.3
+langchain==0.0.219
+langchainplus-sdk==0.0.17
+markdown-it-py==3.0.0
+MarkupSafe==2.1.3
+marshmallow==3.19.0
+marshmallow-enum==1.5.1
+mdurl==0.1.2
+multidict==6.0.4
+mypy-extensions==1.0.0
+numexpr==2.8.4
+numpy==1.25.0
+openai==0.27.8
+openapi-schema-pydantic==1.2.4
+packaging==23.1
+pandas==2.0.3
+Pillow==9.5.0
+protobuf==4.23.3
+pyarrow==12.0.1
+pydantic==1.10.9
+pydeck==0.8.1b0
+Pygments==2.15.1
+Pympler==1.0.1
+pyrsistent==0.19.3
+python-dateutil==2.8.2
+python-dotenv==1.0.0
+pytz==2023.3
+pytz-deprecation-shim==0.1.0.post0
+PyYAML==6.0
+regex==2023.6.3
+requests==2.31.0
+rich==13.4.2
+safetensors==0.3.1
+six==1.16.0
+smmap==5.0.0
+SQLAlchemy==2.0.17
+streamlit==1.24.0
+streamlit-chat==0.1.1
+tabulate==0.9.0
+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==4.6.3
+tzdata==2023.3
+tzlocal==4.3.1
+urllib3==2.0.3
+validators==0.20.0
+watchdog==3.0.0
+yarl==1.9.2
+zipp==3.15.0

setup.sh

@@ -0,0 +1,38 @@
+import streamlit as st
+
+def display_ui():
+    st.sidebar.image("/home/oem/Downloads/insightly_wbg.png", use_column_width=True)
+    st.header("Data Analysis 📈")
+
+    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:")
+
+        # Iterate over each CSV file
+        for csv_file in csv_files:
+            with NamedTemporaryFile(delete=False) as f:
+                f.write(csv_file.getvalue())
+                f.flush()
+                df = pd.read_csv(f.name)
+
+                # 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_name"]
+
+                # Example: Applying transformations or calculations to the data
+                # transformed_data = column_data.apply(lambda x: x * 2)
+
+                # Example: Using the preprocessed data with the OpenAI API
+                # llm_response = llm.predict(transformed_data)
+
+                if user_input:
+                    # Pass the user input to the OpenAI agent for processing
+                    agent = create_csv_agent(llm, f.name, verbose=True)
+                    response = agent.run(user_input)
+
+                    st.write(f"CSV File: {csv_file.name}")
+                    st.write("Response:")
+                    st.write(response)