Added sample colab code to README

README.md

@@ -11,7 +11,7 @@ license: mit
 pipeline_tag: feature-extraction
 ---
 
-# VectorPath SearchMap: Conversational Search Embedding Model
+# VectorPath SearchMap: Conversational E-commerce Search Embedding Model
 
 ## Model Description
 
@@ -25,6 +25,10 @@ SearchMap is a specialized embedding model designed to change search by making i
 - Efficient 1024-dimensional embeddings (configurable up to 8192)
 - Specialized for product and hotel search scenarios
 
+## Quick Start
+
+Try out the model in our interactive [Colab Demo](https://colab.research.google.com/drive/1wUQlWgL5R65orhw6MFChxitabqTKIGRu?usp=sharing)!
+
 ## Model Details
 
 - Base Model: Stella Embed 400M v5
@@ -35,17 +39,16 @@ SearchMap is a specialized embedding model designed to change search by making i
 
 ## Usage
 
-### Using FlagEmbedding (Recommended)
+### Using Sentence Transformers
 
 ```python
-from FlagEmbedding import FlagModel
+# Install required packages
+!pip install -U torch==2.5.1 transformers==4.44.2 sentence-transformers==2.7.0 xformers==0.0.28.post3
+
+from sentence_transformers import SentenceTransformer
 
 # Initialize the model
-model = FlagModel(
-    'vectorpath/searchmap-v1',
-    query_instruction_for_retrieval="Generate a representation for this search query that can be used to retrieve related ecommerce products:",
-    use_fp16=True
-)
+model = SentenceTransformer('vectopath/SearchMap_Preview', trust_remote_code=True)
 
 # Encode queries
 query = "A treat my dog and I can eat together"
@@ -67,13 +70,13 @@ embedding_dimension = 1024  # or your chosen dimension
 index = faiss.IndexFlatL2(embedding_dimension)
 
 # Add product embeddings
-product_embeddings = model.encode(product_descriptions)
+product_embeddings = model.encode(product_descriptions, show_progress_bar=True)
 index.add(np.array(product_embeddings).astype('float32'))
 
 # Search
-query_embedding = model.encode(query)
+query_embedding = model.encode([query])
 distances, indices = index.search(
-    np.array([query_embedding]).astype('float32'), 
+    np.array(query_embedding).astype('float32'), 
     k=10
 )
 ```
@@ -103,7 +106,7 @@ The model excels at understanding natural language queries like:
 ## Training Details
 
 The model was trained using:
-- Supervised learning with FlagEmbedding
+- Supervised learning with Sentence Transformers
 - 100,000+ product dataset across 32 categories
 - AI-generated conversational search queries
 - Positive and negative product examples for contrast learning
@@ -135,6 +138,7 @@ If you use this model in your research, please cite:
 
 - Discord Community: [Join our Discord](https://discord.gg/9XTrys4f)
 - GitHub Issues: Report bugs and feature requests
+- Interactive Demo: [Try it on Colab](https://colab.research.google.com/drive/1wUQlWgL5R65orhw6MFChxitabqTKIGRu?usp=sharing)
 
 ## License