aamanlamba commited on
Commit
cd3cd19
Β·
1 Parent(s): f12921d

update README and app.py for MCP 1st Birthday submission details and features

Browse files
Files changed (2) hide show
  1. README.md +7 -2
  2. app.py +22 -2
README.md CHANGED
@@ -9,12 +9,16 @@ app_file: app.py
9
  pinned: false
10
  license: mit
11
  short_description: An agent that extracts data lineage, pipeline dependencies
 
 
12
  ---
13
 
14
- # Lineage Graph Accelerator πŸ”₯
15
 
16
  A Gradio-based agent that extracts, summarizes, and visualizes data lineage from multiple metadata sources (BigQuery, dbt, Airflow, APIs, and more). Designed as a small, extendable framework of sub-agents that parse metadata, infer relationships, and render clear graph visualizations for exploration and debugging.
17
 
 
 
18
  ## Architecture
19
 
20
  This project is organized as a collection of lightweight sub-agents (workers): a metadata parser, a graph visualizer, and optional integration adapters (BigQuery, URL fetcher, dbt, Airflow). The UI (Gradio) orchestrates these components and displays results as Mermaid diagrams.
@@ -53,7 +57,8 @@ flowchart TD
53
  - Mermaid for graph visualizations (client-side)
54
  - Langsmith's Agent Builder (used to design and orchestrate the agent/sub-agent structure)
55
 
56
- This project was prepared as a submission for the MCP 1st Birthday celebration. See the Hugging Face MCP-1st-Birthday activity for context: https://huggingface.co/organizations/MCP-1st-Birthday/activity/all
 
57
 
58
  ## Quickstart (local)
59
 
 
9
  pinned: false
10
  license: mit
11
  short_description: An agent that extracts data lineage, pipeline dependencies
12
+ tags:
13
+ - MCP-1st-Birthday
14
  ---
15
 
16
+ # Lineage Graph Accelerator πŸ”₯ #MCP-1st-Birthday
17
 
18
  A Gradio-based agent that extracts, summarizes, and visualizes data lineage from multiple metadata sources (BigQuery, dbt, Airflow, APIs, and more). Designed as a small, extendable framework of sub-agents that parse metadata, infer relationships, and render clear graph visualizations for exploration and debugging.
19
 
20
+ **Prepared as a submission for the MCP 1st Birthday celebration** β€” see [Hugging Face MCP-1st-Birthday activity](https://huggingface.co/organizations/MCP-1st-Birthday/activity/all).
21
+
22
  ## Architecture
23
 
24
  This project is organized as a collection of lightweight sub-agents (workers): a metadata parser, a graph visualizer, and optional integration adapters (BigQuery, URL fetcher, dbt, Airflow). The UI (Gradio) orchestrates these components and displays results as Mermaid diagrams.
 
57
  - Mermaid for graph visualizations (client-side)
58
  - Langsmith's Agent Builder (used to design and orchestrate the agent/sub-agent structure)
59
 
60
+ This project was prepared as a submission for the [MCP 1st Birthday celebration](https://huggingface.co/organizations/MCP-1st-Birthday/activity/all).
61
+
62
 
63
  ## Quickstart (local)
64
 
app.py CHANGED
@@ -108,16 +108,36 @@ def extract_lineage_from_url(
108
  # Create Gradio interface
109
  with gr.Blocks(title="Lineage Graph Extractor", theme=gr.themes.Soft()) as demo:
110
  gr.Markdown("""
111
- # πŸ” Lineage Graph Extractor
112
 
113
  Extract and visualize data lineage from various metadata sources including BigQuery, dbt, Airflow,
114
  APIs, and more. This tool helps you understand complex data relationships through clear graph visualizations.
115
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
116
  ## Supported Sources
117
- - **Text/File Metadata**: Paste metadata directly
118
  - **BigQuery**: Query table metadata and relationships
119
  - **URLs/APIs**: Fetch metadata from web endpoints
120
  - **dbt, Airflow, Snowflake**: Through MCP integration (when configured)
 
 
121
  """)
122
  # Load Mermaid.js once (hidden). We set startOnLoad=false and will initialize
123
  # individual diagrams after inserting them into the DOM.
 
108
  # Create Gradio interface
109
  with gr.Blocks(title="Lineage Graph Extractor", theme=gr.themes.Soft()) as demo:
110
  gr.Markdown("""
111
+ # πŸ” Lineage Graph Extractor #MCP-1st-Birthday
112
 
113
  Extract and visualize data lineage from various metadata sources including BigQuery, dbt, Airflow,
114
  APIs, and more. This tool helps you understand complex data relationships through clear graph visualizations.
115
 
116
+ ## About
117
+
118
+ This project was prepared as a submission for the **MCP 1st Birthday celebration**. It demonstrates
119
+ how modular agent-based architecture (built with **Langsmith's Agent Builder**) can be used to extract
120
+ and visualize complex data relationships.
121
+
122
+ ### Features
123
+ - πŸ”— Multi-source metadata ingestion (Text, BigQuery, URLs/APIs)
124
+ - πŸ€– AI-assisted metadata parsing and relationship extraction (pluggable agent backend)
125
+ - πŸ“Š Mermaid and DOT visualization support (rendered dynamically in the UI)
126
+ - 🧩 Lightweight, modular code designed for easy extension and testing
127
+
128
+ ### Built With
129
+ - **Gradio** β€” Interactive web UI
130
+ - **Mermaid** β€” Graph visualization (client-side rendering)
131
+ - **Langsmith's Agent Builder** β€” Agent orchestration and sub-agent design
132
+ - **Python** β€” Core application logic
133
+
134
  ## Supported Sources
135
+ - **Text/File Metadata**: Paste metadata directly (JSON, YAML, SQL, etc.)
136
  - **BigQuery**: Query table metadata and relationships
137
  - **URLs/APIs**: Fetch metadata from web endpoints
138
  - **dbt, Airflow, Snowflake**: Through MCP integration (when configured)
139
+
140
+ Learn more: [MCP 1st Birthday](https://huggingface.co/organizations/MCP-1st-Birthday/activity/all)
141
  """)
142
  # Load Mermaid.js once (hidden). We set startOnLoad=false and will initialize
143
  # individual diagrams after inserting them into the DOM.