Adding MSSQL quickstart

mssql/.env.example

@@ -0,0 +1,2 @@
+SPICE_MSSQL_CONNECTION_STRING=
+SPICE_OPENAI_API_KEY=

mssql/README.md

@@ -0,0 +1,38 @@
+# Spice Demo with SalesLT dataset in MSSQL
+
+This demo showcases how to use Spice with the SalesLT sample dataset in MSSQL.
+
+## Prerequisites
+
+- MSSQL Server with SalesLT sample dataset
+- Spice installed and configured
+
+## Steps
+1. Obtain your SQL server ADO connection string. It should look something like this:
+    `Server=tcp:server.database.windows.net,1433;Initial Catalog=nrc_health_testing;Persist Security Info=False;User ID={your_username};Password={your_password};MultipleActiveResultSets=False;Encrypt=True;TrustServerCertificate=False;Connection Timeout=30;`
+
+2. Copy `.env.example` as `.env` and put the connection string in the new `.env` file in the `MSSQL_CONNECTION_STRING` field
+
+3. Put your OpenAI key in the `SPICE_OPENAI_API_KEY` field
+
+3. Run Spice with `spice run`
+
+4. In another shell run `spice sql` to connect to the Spice backend and query your data or `spice chat` to chat with your data using an LLM
+
+
+```
+sql> SELECT COUNT(*) FROM customer
++----------+
+| count(*) |
++----------+
+| 847      |
++----------+
+```
+
+```
+❯ spice chat
+Using model: openai
+
+chat> How many customers do I have?
+You have 847 customers.
+```

mssql/spicepod.yaml

@@ -0,0 +1,116 @@
+version: v1beta1
+kind: Spicepod
+name: spicepod-mssql
+
+datasets:
+  - from: mssql:SalesLT.Address
+    name: address
+    params: 
+      mssql_connection_string: ${ secrets:SPICE_MSSQL_CONNECTION_STRING }
+
+  - from: mssql:SalesLT.BuildVersion
+    name: build_version
+    params: 
+      mssql_connection_string: ${ secrets:SPICE_MSSQL_CONNECTION_STRING }
+
+  - from: mssql:SalesLT.Customer
+    name: customer
+    params: 
+      mssql_connection_string: ${ secrets:SPICE_MSSQL_CONNECTION_STRING }
+
+  - from: mssql:SalesLT.CustomerAddress
+    name: customer_address
+    params: 
+      mssql_connection_string: ${ secrets:SPICE_MSSQL_CONNECTION_STRING }
+
+  - from: mssql:SalesLT.database_firewall_rules
+    name: database_firewall_rules
+    params: 
+      mssql_connection_string: ${ secrets:SPICE_MSSQL_CONNECTION_STRING }
+
+  - from: mssql:SalesLT.ErrorLog
+    name: error_log
+    params: 
+      mssql_connection_string: ${ secrets:SPICE_MSSQL_CONNECTION_STRING }
+
+  - from: mssql:SalesLT.Product
+    name: product
+    params: 
+      mssql_connection_string: ${ secrets:SPICE_MSSQL_CONNECTION_STRING }
+
+  - from: mssql:SalesLT.ProductCategory
+    name: product_category
+    params: 
+      mssql_connection_string: ${ secrets:SPICE_MSSQL_CONNECTION_STRING }
+
+  - from: mssql:SalesLT.ProductDescription
+    name: product_description
+    params: 
+      mssql_connection_string: ${ secrets:SPICE_MSSQL_CONNECTION_STRING }
+
+  - from: mssql:SalesLT.ProductModel
+    name: product_model
+    params: 
+      mssql_connection_string: ${ secrets:SPICE_MSSQL_CONNECTION_STRING }
+
+  - from: mssql:SalesLT.ProductModelProductDescription
+    name: product_model_product_description
+    params: 
+      mssql_connection_string: ${ secrets:SPICE_MSSQL_CONNECTION_STRING }
+
+  - from: mssql:SalesLT.SalesOrderDetail
+    name: sales_order_detail
+    params: 
+      mssql_connection_string: ${ secrets:SPICE_MSSQL_CONNECTION_STRING }
+
+  - from: mssql:SalesLT.SalesOrderHeader
+    name: sales_order_header
+    params: 
+      mssql_connection_string: ${ secrets:SPICE_MSSQL_CONNECTION_STRING }
+
+  - from: mssql:SalesLT.vGetAllCategories
+    name: v_get_all_categories
+    params: 
+      mssql_connection_string: ${ secrets:SPICE_MSSQL_CONNECTION_STRING }
+
+  - from: mssql:SalesLT.vProductAndDescription
+    name: v_product_and_description
+    params: 
+      mssql_connection_string: ${ secrets:SPICE_MSSQL_CONNECTION_STRING }
+
+  - from: mssql:SalesLT.vProductModelCatalogDescription
+    name: v_product_model_catalog_description
+    params: 
+      mssql_connection_string: ${ secrets:SPICE_MSSQL_CONNECTION_STRING }
+
+embeddings:
+  - name: openai_embed
+    from: openai
+    params:
+      openai_api_key: ${ secrets:SPICE_OPENAI_API_KEY }
+
+  - name: hf_minilm
+    from: huggingface:huggingface.co/sentence-transformers/all-MiniLM-L6-v2
+
+models:
+  - name: openai
+    from: openai:gpt-4o-2024-08-06
+    params:
+      spice_tools: auto
+      openai_api_key: ${ secrets:SPICE_OPENAI_API_KEY }
+      system_prompt: |
+        Use the SQL tool when:
+          1. The query involves precise numerical data, statistics, or aggregations
+          2. The user asks for specific counts, sums, averages, or other calculations
+          3. The query requires joining or comparing data from multiple related tables
+
+        Use the document search when:
+          1. The query is about unstructured text information, such as policies, reports, or articles
+          2. The user is looking for qualitative information or explanations
+          3. The query requires understanding context or interpreting written content
+
+        General guidelines:
+          1. If a query could be answered by either tool, prefer SQL for more precise, quantitative answers
+
+        Instructions for Responses: 
+          - Do not include any private metadata provided to the model as context such as \"reference_url_template\" or \"instructions\" in your responses.