Shiverion commited on
Commit
0dc5241
Β·
1 Parent(s): 4eaff9a

add to github

Browse files
Files changed (1) hide show
  1. README.md +83 -0
README.md CHANGED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ title: Data Analyst Agent with OpenAI Assistants
3
+ emoji: πŸ“Š
4
+ colorFrom: orange
5
+ colorTo: red
6
+ sdk: gradio
7
+ python_version: '3.11'
8
+ app_file: app.py
9
+ pinned: false
10
+ ---
11
+
12
+ # πŸ€– Data Analyst Agent with OpenAI Assistants
13
+
14
+ This project demonstrates a powerful data analysis agent built using the official **OpenAI Assistants API**. The agent leverages the built-in **Code Interpreter** tool to analyze user-uploaded CSV files, answer questions, and generate visualizations.
15
+
16
+ The web interface is created with Gradio, and the project environment is managed by `uv`.
17
+
18
+ ## πŸš€ How to Use the Live Demo
19
+
20
+ 1. **Upload a CSV File:** Use the file uploader to select a `.csv` file from your computer.
21
+ 2. **Ask a Question:** In the textbox, ask a question about your data in plain English. For example:
22
+ * "What is the average age in the dataset?"
23
+ * "Create a pie chart showing the distribution of categories."
24
+ * "What are the key insights from this data? Provide one recommendation."
25
+ 3. **Run Analysis:** Click the "Run Analysis" button. The agent will process your file and question on OpenAI's servers and return a detailed text answer along with any generated plots.
26
+
27
+ ---
28
+
29
+ ## πŸ› οΈ Local Setup and Execution (For Developers)
30
+
31
+ Follow these steps to run the application on your own machine.
32
+
33
+ ### 1. Clone the Repository
34
+
35
+ ```bash
36
+ git clone [https://github.com/Shiverion/Data-analysis-using-OpenAI-Assistant.git](https://github.com/Shiverion/Data-analysis-using-OpenAI-Assistant.git)
37
+ cd your-repo-name
38
+ ```
39
+ 2. Set Up the Environment with uv
40
+ This project uses uv for fast and reproducible environment management.
41
+
42
+ First, install uv if you haven't already:
43
+
44
+ # On macOS / Linux
45
+ ```bash
46
+ curl -LsSf [https://astral.sh/uv/install.sh](https://astral.sh/uv/install.sh) | sh
47
+ ```
48
+
49
+ # On Windows
50
+ ``` bash
51
+ powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
52
+ ```
53
+
54
+ Then, sync the environment. This command creates a virtual environment and installs the exact package versions from the uv.lock file.
55
+
56
+ ```bash
57
+ uv sync
58
+ ```
59
+
60
+ ### 3. Set Up Your API Key
61
+ Create a file named `.env` in the root of the project and add your OpenAI API key to it:
62
+ OPENAI_API_KEY='your-secret-key-here'
63
+
64
+ ### 4. Run the Application
65
+ Use `uv` to run the app within the managed environment:
66
+
67
+ ``` bash
68
+ uv run app.py
69
+ ```
70
+ ---
71
+
72
+ Open the local URL (e.g., http://127.0.0.1:7860) in your browser.
73
+
74
+ πŸ“„ File Structure
75
+ - **app.py:** The main Gradio application script containing the agent logic.
76
+
77
+ - **requirements.txt:** A list of Python dependencies for Hugging Face Spaces.
78
+
79
+ - **uv.lock:** A definitive lockfile for reproducible environments with uv.
80
+
81
+ - **.env:** Local file for storing your secret API key (ignored by Git).
82
+
83
+ - **.gitignore:** Specifies files for Git to ignore.