NaderAfshar commited on
Commit
3ba38b1
Β·
1 Parent(s): 83d7c0c

Updated the README file

Browse files
Files changed (1) hide show
  1. README.md +88 -0
README.md CHANGED
@@ -12,3 +12,91 @@ short_description: A sample Agentic Data Analyst
12
  ---
13
 
14
  Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
12
  ---
13
 
14
  Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
15
+
16
+ # πŸ“Š CSV Agent with Cohere LLM and Langchain
17
+
18
+ This application is developed as a demonstration of an Agentic system that acts as
19
+ a Data Analyst. A csv file can be loaded and analyzed by asking questions. Charts can also
20
+ be requested and should be displayed by the agent.
21
+
22
+ The underlying LLM is a **Cohere Command-R** model, specifically **command-r-plus-08-2024**. The
23
+ Agent also makes use of the LangChain framework.
24
+
25
+
26
+ ## 🎯 Key Features
27
+
28
+ - **Dynamic CSV Upload:** Upload your CSV file effortlessly for instant analysis.
29
+ - **Natural Language Queries:** Ask questions in plain English, and the agent responds with data insights.
30
+ - **Chart Generation:** Visualize your data with auto-generated charts based on your queries.
31
+ - **Interactive Interface:** User-friendly interface built with Gradio for easy interaction.
32
+ - **Agent Reset:** Quickly reset the agent to upload new datasets without refreshing the page.
33
+
34
+ ## πŸ—‚οΈ Installation
35
+
36
+ 1. Clone the repository:
37
+ ```bash
38
+ git clone https://huggingface.co/spaces/nader01/csv-agent
39
+ cd csv-agent
40
+ ```
41
+
42
+ 2. Create a virtual environment and activate it:
43
+ ```bash
44
+ python -m venv .venv
45
+ source .venv/bin/activate # On Windows: .venv\Scripts\activate
46
+ ```
47
+
48
+ 3. Install dependencies:
49
+ ```bash
50
+ pip install -r requirements.txt
51
+ ```
52
+
53
+ 4. Set up your `.env` file with the Cohere API key:
54
+ ```bash
55
+ COHERE_API_KEY=your_cohere_api_key
56
+ ```
57
+
58
+ 5. Run the application:
59
+ ```bash
60
+ python csv_agent_with_chart.py
61
+ ```
62
+
63
+ ## 🌐 How to Use
64
+
65
+ 1. **Upload a CSV File:**
66
+ - Click on the **Upload CSV** button.
67
+ - Select your CSV file to load the data.
68
+ - View a preview of your data.
69
+
70
+ 2. **Ask a Question:**
71
+ - Enter your question in the **Ask a Question** box.
72
+ - Click **Submit Question** to receive a detailed answer.
73
+
74
+ 3. **View Charts:**
75
+ - If the response includes a chart, it will be displayed below the response box.
76
+
77
+ 4. **Reset Agent:**
78
+ - Click **Reset Agent** to clear data and upload a new CSV file without refreshing the page.
79
+
80
+ ## 🎨 User Interface Design
81
+
82
+ - **Input & Output Boxes:** Light blue background with bold, dark blue labels for easy readability.
83
+ - **Interactive Elements:** Buttons with responsive feedback for better user experience.
84
+
85
+ ![UI Screenshot](ui_screenshot.jpg)
86
+
87
+ ## 🧠 Powered By
88
+
89
+ - **Cohere AI:** For natural language processing and data analysis.
90
+ - **Gradio:** For building the interactive user interface.
91
+ - **Pandas:** For efficient data handling.
92
+
93
+
94
+ ## πŸ“œ License
95
+
96
+ This project is licensed under the MIT License. See the [LICENSE](LICENSE) file for details.
97
+
98
+ ---
99
+
100
+ Enjoy exploring your data with this **CSV Agent**! πŸš€
101
+
102
+