DOCSP 43493 VSCode Copilot /query functionality

snooty.toml

@@ -10,7 +10,8 @@ toc_landing_pages = [
     "/playgrounds",
     "/crud-ops",
     "/playground-databases",
-    "/require-playgrounds"
+    "/require-playgrounds",
+    "/copilot"
 ]
 
 [constants]
@@ -40,6 +41,7 @@ cifs = ":abbr:`CIFS (Common Internet File System)`"
 cps = ":abbr:`CPS (Cloud Provider Snapshots)`"
 cmk = ":abbr:`CMK (customer master key)`"
 compass = "MongoDB Compass"
+copilot = "MongoDB Github Copilot Participant"
 data-lakes = "Data Lakes"
 data-lake = "Data Lake"
 datadog = "`Datadog <https://www.datadoghq.com/>`__"

source/ai-data-usage.txt

@@ -0,0 +1,35 @@
+.. vscode-ai-data-usage:
+
+=============================
+AI and Data Usage Information
+=============================
+
+.. contents:: On this page
+   :local:
+   :backlinks: none
+   :depth: 1
+
+The MongoDB Github Copilot Participant is powered by Generative AI (Gen
+AI), and may give inaccurate responses. See our `Generative AI FAQ
+<https://dochub.mongodb.org/core/faq-ai-features>`__ for more
+information about Gen AI in MongoDB products.
+
+Third Party Providers
+---------------------
+
+The MongoDB Github Copilot Participant is powered by `Github Copilot <https://github.com/features/copilot>`__.
+
+How Your Data is Used
+---------------------
+
+When you use the MongoDB Github Copilot Participant, the following
+information is sent to MongoDB's backend and/or the third party AI
+provider: 
+
+- The full text of your natural language prompt.
+- The schema of the collection you are using, 
+  including database name, collection name, field names, and types. 
+
+The information that is sent will not be shared with any other third 
+parties or stored by the AI provider. We do not send database 
+connection strings, credentials, or rows/documents from your databases. 

source/copilot-query.txt

@@ -0,0 +1,141 @@
+.. _vsce-copilot-query:
+
+==============
+/query Command
+==============
+
+.. default-domain:: mongodb
+
+.. contents:: On this page
+   :local:
+   :backlinks: none
+   :depth: 1
+   :class: singlecol
+
+The ``/query`` command assists in generating queries from a natural
+language against a connected MongoDB cluster. The |copilot| provides
+underlying schema information of the relevant collections to Github
+Copilot to generate a response. If you do not specify a collection in
+your prompt, the chat prompts you to select a relevant collection. 
+
+When the LLM generates a query, you can open the query in a playground
+file or run the query directly in your collection. 
+
+Examples
+~~~~~~~~
+
+Generate a Query
+````````````````
+
+Consider the ``users`` collection in the `Mflix Sample Database
+<https://www.mongodb.com/docs/atlas/sample-data/sample-mflix/#sample_mflix.users>`__.
+Each document in the collection has the following structure:
+
+.. code-block:: javascript
+   :copyable: false
+
+   {
+      _id: {
+         "$oid": "59b99db4cfa9a34dcd7885b6"
+      },
+      name: "Kayden Washington",
+      email: "[email protected]",
+      password: "11222021"
+   }
+
+Once you connect to the deployment that contains the ``users``
+collection, you can ask the Github Copilot chat to generate a query that
+finds the document in the ``users`` collection that has the ``name``
+value of ``Kayden Washington``. 
+
+.. code-block:: javascript
+   :copyable: false
+
+   @MongoDB /query In the sample_mflix database, find a document in the
+   users collection with the name of Kayden Washington.
+
+The Github Copilot Chat uses the |copilot| to
+generate the following query using knowledge of your database schema:
+
+.. code-block:: javascript
+
+   use(`sample_mflix`);
+   db.getCollection('users').findOne({ name: 'Kayden Washington' });
+
+Once the |copilot| generates the query, you can choose to run the query
+directly or open the query in a playground. 
+
+.. figure:: /images/copilot-query.png
+   :figwidth: 700px
+   :alt: Screenshot of copilot generating a query
+
+Build an Aggregation Pipeline
+`````````````````````````````
+
+You can also use the |copilot| to build aggregation pipelines. Consider
+the ``users`` collection in the `Mflix Sample Database
+<https://www.mongodb.com/docs/atlas/sample-data/sample-mflix/#sample_mflix.users>`__.
+Each document in the collection has the following structure:
+
+.. code-block:: javascript
+   :copyable: false
+
+   {
+      _id: {
+         "$oid": "59b99db4cfa9a34dcd7885b6"
+      },
+      name: "Kayden Washington",
+      email: "[email protected]",
+      password: "11222021"
+   }
+
+Once you connect to the deployment that contains the ``users``
+collection, you can ask the Github Copilot chat to generate an aggregation pipeline. 
+
+.. code-block:: javascript
+   :copyable: false
+
+   @MongoDB /query Generate an aggregation pipeline on the users 
+   collection that first sorts documents alphabetically by name and then 
+   removes the password field from each document. 
+
+The |copilot| generates the following aggregation pipeline:
+
+.. code-block:: javascript
+
+   use('sample_mflix');
+   db.getCollection('users').aggregate([
+      { $sort: { name: 1 } },
+      { $project: { password: 0 } }
+   ]);
+
+Once the |copilot| generates the query, you can choose to run the pipeline
+directly or open the pipeline in a playground.   
+
+.. figure:: /images/copilot-agg-pipeline.png
+   :figwidth: 700px
+   :alt: Screenshot of copilot generating an aggregation pipeline
+
+You can also iteratively build on your aggregation pipeline:
+
+.. code-block:: javascript
+   :copyable: false
+
+   @MongoDB /query Add a stage to my pipeline that adds a username field 
+   to each document containing the user's email without the 
+   email domain. 
+
+The |copilot| returns the following aggregation pipeline:
+
+.. code-block:: javascript
+
+   use('sample_mflix');
+   db.getCollection('users').aggregate([
+      { $sort: { name: 1 } },
+      { $project: { password: 0 } },
+      { $addFields: { username: { $arrayElemAt: [{ $split: ["$email", "@"] }, 0] } } }
+   ]);
+
+.. figure:: /images/copilot-agg-pipeline2.png
+   :figwidth: 700px
+   :alt: Screenshot of copilot iteratively building on an aggregation pipeline

source/copilot.txt

@@ -0,0 +1,41 @@
+.. _vsce-copilot:
+
+==================================
+|copilot|
+==================================
+
+.. default-domain:: mongodb
+
+.. contents:: On this page
+   :local:
+   :backlinks: none
+   :depth: 1
+   :class: singlecol
+
+|vsce-full| includes the |copilot| to assist in using `Github Copilot
+<https://github.com/features/copilot>`__ with your MongoDB deployments.
+Through Github Copilot's chat feature, users with |vsce| can interact
+with their MongoDB clusters and generate code with MongoDB
+domain-specific knowledge on top of Github Copilot's LLM. The |copilot
+can also answer questions about your database collection schema and
+provide links to specific MongoDB documentation.  
+
+The |copilot| includes MongoDB-specific
+commands to assist in interacting with your deployment.
+
+Commands
+--------
+
+/query
+~~~~~~
+
+The ``/query`` command assists in generating queries from a natural
+language against a connected MongoDB cluster.
+
+.. toctree::
+   :titlesonly:
+
+   /query </copilot-query>
+   AI & Data Usage </ai-data-usage>
+
+

source/index.txt

@@ -56,6 +56,7 @@ Get Started
    /connect
    /databases-collections
    /playgrounds
+   /copilot
    /create-cluster-terraform
    /reference
    Changelog <https://github.com/mongodb-js/vscode/releases>