chore(examples): tighten up the openai chat example a bit (#519)

Use atypical (for this repo) 2-space indent to help avoid fighting 80-columns reflow, for use in a blog post where appearance matters a little bit more.
elastic · Jan 10, 2025 · 6b0bfda · 6b0bfda
1 parent a82250e
commit 6b0bfda
Show file tree

Hide file tree

Showing 4 changed files with 61 additions and 51 deletions.
diff --git a/examples/openai/.editorconfig b/examples/openai/.editorconfig
@@ -0,0 +1,4 @@
+# Use 2-space indent for these examples to help tighten them
+# up in a blog post. Typically this repo is using 4-space.
+[*.js]
+indent_size = 2
diff --git a/examples/openai/.prettierrc b/examples/openai/.prettierrc
@@ -0,0 +1,10 @@
+{
+  "printWidth": 80,
+  "useTabs": false,
+  "semi": true,
+  "trailingComma": "es5",
+
+  "bracketSpacing": false,
+  "singleQuote": true,
+  "tabWidth": 2
+}
diff --git a/examples/openai/chat.js b/examples/openai/chat.js
@@ -22,21 +22,17 @@ const {OpenAI} = require('openai');
 let chatModel = process.env.CHAT_MODEL ?? 'gpt-4o-mini';
 
 async function main() {
-    const client = new OpenAI();
-
-    const messages = [
-        {
-            role: 'user',
-            content:
-                'Answer in up to 3 words: Which ocean contains Bouvet Island?',
-        },
-    ];
-
-    const chatCompletion = await client.chat.completions.create({
-        model: chatModel,
-        messages: messages,
-    });
-    console.log(chatCompletion.choices[0].message.content);
+  const client = new OpenAI();
+  const completion = await client.chat.completions.create({
+    model: chatModel,
+    messages: [
+      {
+        role: 'user',
+        content: 'Answer in up to 3 words: Which ocean contains Bouvet Island?',
+      },
+    ],
+  });
+  console.log(completion.choices[0].message.content);
 }
 
 main();
diff --git a/examples/openai/embeddings.js b/examples/openai/embeddings.js
@@ -23,51 +23,51 @@ const {dot, norm} = require('mathjs');
 let embeddingsModel = process.env.EMBEDDINGS_MODEL ?? 'text-embedding-3-small';
 
 async function main() {
-    const client = new OpenAI();
+  const client = new OpenAI();
 
-    const products = [
-        "Search: Ingest your data, and explore Elastic's machine learning and retrieval augmented generation (RAG) capabilities.",
-        'Observability: Unify your logs, metrics, traces, and profiling at scale in a single platform.',
-        'Security: Protect, investigate, and respond to cyber threats with AI-driven security analytics.',
-        'Elasticsearch: Distributed, RESTful search and analytics.',
-        'Kibana: Visualize your data. Navigate the Stack.',
-        'Beats: Collect, parse, and ship in a lightweight fashion.',
-        'Connectors: Connect popular databases, file systems, collaboration tools, and more.',
-        'Logstash: Ingest, transform, enrich, and output.',
-    ];
+  const products = [
+    "Search: Ingest your data, and explore Elastic's machine learning and retrieval augmented generation (RAG) capabilities.",
+    'Observability: Unify your logs, metrics, traces, and profiling at scale in a single platform.',
+    'Security: Protect, investigate, and respond to cyber threats with AI-driven security analytics.',
+    'Elasticsearch: Distributed, RESTful search and analytics.',
+    'Kibana: Visualize your data. Navigate the Stack.',
+    'Beats: Collect, parse, and ship in a lightweight fashion.',
+    'Connectors: Connect popular databases, file systems, collaboration tools, and more.',
+    'Logstash: Ingest, transform, enrich, and output.',
+  ];
 
-    // Generate embeddings for each product. Keep them in an array instead of a vector DB.
-    const productEmbeddings = [];
-    for (const product of products) {
-        productEmbeddings.push(await createEmbedding(client, product));
-    }
+  // Generate embeddings for each product. Keep them in an array instead of a vector DB.
+  const productEmbeddings = [];
+  for (const product of products) {
+    productEmbeddings.push(await createEmbedding(client, product));
+  }
 
-    const queryEmbedding = await createEmbedding(
-        client,
-        'What can help me connect to a database?'
-    );
+  const queryEmbedding = await createEmbedding(
+    client,
+    'What can help me connect to a database?'
+  );
 
-    // Calculate cosine similarity between the query and document embeddings
-    const similarities = productEmbeddings.map((productEmbedding) => {
-        return (
-            dot(queryEmbedding, productEmbedding) /
-            (norm(queryEmbedding) * norm(productEmbedding))
-        );
-    });
+  // Calculate cosine similarity between the query and document embeddings
+  const similarities = productEmbeddings.map((productEmbedding) => {
+    return (
+      dot(queryEmbedding, productEmbedding) /
+      (norm(queryEmbedding) * norm(productEmbedding))
+    );
+  });
 
-    // Get the index of the most similar document
-    const mostSimilarIndex = similarities.indexOf(Math.max(...similarities));
+  // Get the index of the most similar document
+  const mostSimilarIndex = similarities.indexOf(Math.max(...similarities));
 
-    console.log(products[mostSimilarIndex]);
+  console.log(products[mostSimilarIndex]);
 }
 
 async function createEmbedding(client, text) {
-    const response = await client.embeddings.create({
-        input: [text],
-        model: embeddingsModel,
-        encoding_format: 'float',
-    });
-    return response.data[0].embedding;
+  const response = await client.embeddings.create({
+    input: [text],
+    model: embeddingsModel,
+    encoding_format: 'float',
+  });
+  return response.data[0].embedding;
 }
 
 main();