enhance Spider benchmarking

.gitignore

@@ -167,3 +167,9 @@ cython_debug/
 # Spider data: https://drive.google.com/file/d/1403EGqzIDoHMdQF4c9Bkyl7dZLZ5Wt6J/view
 /text_2_sql/test-suite-sql-eval/
 /text_2_sql/spider_data/
+
+# Generated samples data
+/text_2_sql/data_dictionary/generated_samples/
+
+# Data Dictionary environment file
+/text_2_sql/data_dictionary/.env

pyproject.toml

@@ -4,6 +4,9 @@ version = "0.1.0"
 description = "This repo accelerates development of RAG applications with rich data sources including SQL Warehouses and documents analysed with Azure Document Intelligence."
 readme = "README.md"
 requires-python = ">=3.11"
+dependencies = [
+    "text-2-sql-core[sqlite]",
+]
 
 [dependency-groups]
 dev = [
@@ -20,7 +23,7 @@ dev = [
 members = ["text_2_sql/text_2_sql_core", "text_2_sql/autogen", "deploy_ai_search_indexes", "image_processing"]
 
 [tool.uv.sources]
-text_2_sql_core = { workspace = true }
 autogen_text_2_sql = { workspace = true }
 deploy_ai_search_indexes = { workspace = true }
 image_processing = { workspace = true }
+text-2-sql-core = { workspace = true }

text_2_sql/autogen/.env.example

@@ -0,0 +1,59 @@
+# OpenAI Configuration (Common for all environments)
+OpenAI__CompletionDeployment=gpt-4o-mini
+OpenAI__MiniCompletionDeployment=gpt-4o-mini
+OpenAI__GroupChatModel=4o-mini
+OpenAI__EmbeddingModel=text-embedding-ada-002
+OpenAI__Endpoint=your_openai_endpoint
+OpenAI__ApiKey=your_api_key
+OpenAI__ApiVersion=2024-08-01-preview
+
+# Authentication (Common for all environments)
+IdentityType=key
+
+### ENVIRONMENT-SPECIFIC SETTINGS ###
+# Uncomment only one section at a time
+
+## Spider Evaluation Baseline Settings (using tables.json) ##
+#Text2Sql__DatabaseEngine=SQLite
+#Text2Sql__UseQueryCache=False
+#Text2Sql__PreRunQueryCache=False
+#Text2Sql__UseColumnValueStore=False
+#Text2Sql__UseAISearch=False
+#Text2Sql__DatabaseName=
+#Text2Sql__DatabaseConnectionString=
+
+## Spider Evaluation with Enhanced Schema Settings ##
+Text2Sql__DatabaseEngine=SQLite
+Text2Sql__UseQueryCache=False
+Text2Sql__PreRunQueryCache=False
+Text2Sql__UseColumnValueStore=True
+Text2Sql__UseAISearch=True
+Text2Sql__DatabaseName=
+Text2Sql__DatabaseConnectionString=
+AIService__AzureSearchOptions__Endpoint=your_search_endpoint
+AIService__AzureSearchOptions__Key=your_search_key
+AIService__AzureSearchOptions__Text2SqlSchemaStore__Index=text-2-sql-schema-store-index-spider-test
+AIService__AzureSearchOptions__Text2SqlSchemaStore__SemanticConfig=text-2-sql-schema-store-semantic-config-spider-test
+AIService__AzureSearchOptions__Text2SqlQueryCache__Index=text-2-sql-query-cache-index-spider-test
+AIService__AzureSearchOptions__Text2SqlQueryCache__SemanticConfig=text-2-sql-query-cache-semantic-config-spider-test
+AIService__AzureSearchOptions__Text2SqlColumnValueStore__Index=text-2-sql-column-value-store-index-spider-test
+AIService__AzureSearchOptions__Text2SqlSchemaCache__Index=text-2-sql-schema-cache-index-spider-test
+
+## Production Settings (Commented Out) ##
+#Text2Sql__DatabaseEngine=TSQL
+#Text2Sql__UseQueryCache=True
+#Text2Sql__PreRunQueryCache=True
+#Text2Sql__UseColumnValueStore=True
+#Text2Sql__UseAISearch=True
+#Text2Sql__DatabaseName=SalesLT
+#Text2Sql__DatabaseConnectionString=your_database_connection_string
+#AIService__AzureSearchOptions__Endpoint=your_search_endpoint
+#AIService__AzureSearchOptions__Key=your_search_key
+#AIService__AzureSearchOptions__RagDocuments__Index=
+#AIService__AzureSearchOptions__RagDocuments__SemanticConfig=
+#AIService__AzureSearchOptions__Text2SqlSchemaStore__Index=text-2-sql-schema-store-index
+#AIService__AzureSearchOptions__Text2SqlSchemaStore__SemanticConfig=text-2-sql-schema-store-semantic-config
+#AIService__AzureSearchOptions__Text2SqlQueryCache__Index=text-2-sql-query-cache-index
+#AIService__AzureSearchOptions__Text2SqlQueryCache__SemanticConfig=text-2-sql-query-cache-semantic-config
+#AIService__AzureSearchOptions__Text2SqlColumnValueStore__Index=text-2-sql-column-value-store-index
+#AIService__AzureSearchOptions__Text2SqlSchemaCache__Index=text-2-sql-schema-cache-index

text_2_sql/autogen/Iteration 5 - Agentic Vector Based Text2SQL.ipynb

@@ -118,7 +118,7 @@
   ],
   "metadata": {
     "kernelspec": {
-      "display_name": "Python 3",
+      "display_name": ".venv",
       "language": "python",
       "name": "python3"
     },