ujwal55 commited on
Commit
e3305b3
Β·
1 Parent(s): 078f4bf

Update ReadMe with new description

Browse files
Files changed (1) hide show
  1. README.md +88 -0
README.md CHANGED
@@ -11,3 +11,91 @@ short_description: Helps users break down high-level tasks into sub-steps
11
  ---
12
 
13
  Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  ---
12
 
13
  Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
14
+
15
+ # πŸ“‹ Rule-Based Task Planner
16
+
17
+ A simple rule-based AI agent that helps users break down high-level tasks into actionable substeps. Built with Python and Gradio, this project demonstrates a basic agentic AI workflow using hard-coded logic β€” no machine learning involved.
18
+
19
+ ---
20
+
21
+ ## πŸš€ Demo
22
+
23
+ πŸ‘‰ [Launch the app on Hugging Face Spaces](https://huggingface.co/spaces/ujwal55/Rule-Based_Task_Planner)
24
+
25
+ ---
26
+
27
+ ## 🧠 What It Does
28
+
29
+ Enter a task like:
30
+
31
+ - `Plan a study session`
32
+ - `Plan a workout`
33
+ - `Plan a trip`
34
+ - `Plan a presentation`
35
+
36
+ And the app will return a predefined list of sub-tasks.
37
+
38
+ Example:
39
+
40
+ > **Input:** `Plan a study session`
41
+ > **Output:**
42
+ > 1. Choose a topic to study
43
+ > 2. Gather necessary materials (books, notes, etc.)
44
+ > 3. Allocate a time slot for the session
45
+ > 4. Set specific goals
46
+ > 5. Review notes and summarize key points
47
+
48
+ ---
49
+
50
+ ## πŸ›  Tech Stack
51
+
52
+ - **Python**
53
+ - **Gradio** – For building a lightweight UI
54
+ - **Rule Engine** – Dictionary-based mapping of tasks to steps
55
+
56
+ ---
57
+
58
+ ## 🧩 Agentic AI Concept
59
+
60
+ Although there's no ML model here, this project mimics agentic behavior using a **hard-coded rule-based planner**:
61
+ - Maps user intent to structured outputs
62
+ - Provides a decision-like structure via a rule engine
63
+
64
+ This is ideal for beginners looking to build agentic systems without needing a large language model.
65
+
66
+ ---
67
+
68
+ ## πŸ“ File Structure
69
+ app.py # Main app with Gradio interface
70
+ task_plannings.py # It consist rule_engine description
71
+ README.md
72
+ requirements.txt # gradio
73
+
74
+ ---
75
+
76
+ ## πŸ§ͺ Run Locally
77
+
78
+ 1. Clone the repo:
79
+ ```bash
80
+ git clone https://huggingface.co/spaces/ujwal55/Rule-Based_Task_Planner
81
+ cd Rule-Based_Task_Planner
82
+ ```
83
+
84
+ 2. Install dependencies:
85
+ pip install -r requirements.txt
86
+
87
+ 3. Run the app:
88
+ python app.py
89
+
90
+ πŸ’‘ Ideas to Extend
91
+ - Add a dropdown to choose common tasks
92
+ - Allow user-defined tasks with a fallback plan
93
+ - Use a small local LLM for few-shot task breakdowns
94
+
95
+ ---
96
+
97
+ πŸ‘¨β€πŸ’» Built by @ujwal55
98
+
99
+ Let me know if you want a more advanced version with a chatbot-style interface or LLM integration later.
100
+
101
+ ---