adding retail vertex-ai demo to labs repo (#7)

* adding retail vertex-ai demo to labs repo * removed unecessary files * resetting homecraft folder * removing unnecessary files * polished folder * adding homecraft info in commong readme --------- Co-authored-by: Valerio Arvizzigno <valerio@ComputeiValerio.station>

Author: valerioarvizzigno

example-apps/README.md

@@ -13,6 +13,7 @@ Use these apps as a starting point for your own projects.
 - [OpenAI embeddings](./OpenAI-embeddings/README.md). Use OpenAI embeddings at index time and in Elastic kNN queries. Available in [JavaScript](./OpenAI-embeddings/OpenAI-JS/README.md) and [Python](./OpenAI-embeddings/OpenAI-Py/README.md) versions.
 - [Workplace search](./Workplace-Search/README.md). Build a semantic search experience for organizational/workplace data.
 - [relevance-workbench](./relevance-workbench/README.md). A Python application that allows you to compare results ranking between the **Elastic Learned Sparse Encoder** model and BM25.
+- [Homecraft Vertex](./homecraft_vertex/README.md). A Python application designed for Retail industry simulating an e-commerce search bar. It integrates with Google's VertexAI and PALM2 model, BigQuery Datasets and Elastic Vector Search to answer questions around previous orders, suggested products available and company information.
 
 
 > ℹ️ **Note**:

example-apps/homecraft_vertex/Additional sources/helpful_elastic_api_calls

@@ -0,0 +1,86 @@
+POST search-homecraft-ikea/_mapping
+{
+ "properties": {
+ "title-vector": {
+ "type": "dense_vector",
+ "dims": 768,
+ "index": true,
+ "similarity": "dot_product"
+ }
+ }
+}
+
+
+POST home-depot-product-catalog-vector/_mapping
+{
+ "properties": {
+ "title-vector": {
+ "type": "dense_vector",
+ "dims": 768,
+ "index": true,
+ "similarity": "dot_product"
+ }
+ }
+}
+
+POST _reindex
+{
+ "source": {
+ "index": "home-depot-product-catalog"
+ },
+ "dest": {
+ "index": "home-depot-product-catalog-vector",
+ "pipeline": "ml-inference-title-vector"
+ }
+}
+
+
+POST /home-depot-product-catalog-vector/_delete_by_query
+{
+ "query": {
+ "match_all": {}
+ }
+}
+
+DELETE /home-depot-product-catalog-vector
+
+PUT /home-depot-product-catalog-vector 
+
+
+# Elasticsearch query (BM25) and kNN configuration for hybrid search
+
+GET home-depot-product-catalog-vector/_search
+{
+ "query" : {
+ "bool": {
+ "must": [{
+ "match": {
+ "title": {
+ "query": "list the 3 top paint primers in the product catalog, specify also product price and product key features",
+ "boost": 1
+ }
+ }
+ }],
+ "filter": [{
+ "exists": {
+ "field": "title-vector"
+ }
+ }]
+ }
+ },
+
+ "knn" : {
+ "field": "title-vector",
+ "k": 1,
+ "num_candidates": 20,
+ "query_vector_builder": {
+ "text_embedding": {
+ "model_id": "sentence-transformers__all-distilroberta-v1",
+ "model_text": "list the 3 top paint primers in the product catalog, specify also product price and product key features."
+ }
+ },
+ "boost": 24
+ }
+
+} 
+