Update README.md

README.md

@@ -1,26 +1,17 @@
 ---
 title: Multi LLM RAG With Groundtruth Comparison
-emoji: 📚
+emoji: 🤖
 colorFrom: blue
 colorTo: gray
 sdk: gradio
 sdk_version: 4.44.1
 app_file: app.py
-pinned: false
+pinned: true
 license: apache-2.0
-short_description: ' Upload PDFs, provide groundtruth, and compare various LLMs'
+short_description: ' Upload PDFs, provide ground truth, and compare various LLMs'
 ---
 
-## How Pixeltable Makes This Possible
+# Overview
 
-1. **Unified Data Management**: Pixeltable seamlessly handles various data types - from PDFs to embeddings - in a single, coherent system.
+Pixeltable unifies data storage, versioning, and indexing with orchestration and model versioning under a declarative table interface, with transformations, model inference, and custom logic represented as computed columns.
 
-2. **Automatic Chunking and Indexing**: The DocumentSplitter and embedding indexing functionalities demonstrate Pixeltable's ability to prepare large documents for efficient retrieval.
-
-3. **Declarative Data Transformations**: Computed columns for context retrieval and prompt creation show how Pixeltable can express complex data operations simply and clearly.
-
-4. **Seamless Integration with AI Services**: The integration with OpenAI's API illustrates how Pixeltable can incorporate external AI services into data workflows.
-
-5. **Efficient Querying**: The `top_k` query function demonstrates Pixeltable's powerful querying capabilities, enabling fast similarity searches over large datasets.
-
-By unifying data management, transformation, and AI model integration, Pixeltable significantly reduces the complexity of building and deploying AI-powered applications like this RAG system.