Log inSign up

Search

136 results found for “embeddings” (1263ms)

Code
127

jxnblk/blog-vt2/get-old-posts.ts
1 matches
    "slug": "val-vibes",
    "link": "/blog/val-vibes",
    "description": "How to build semantic search with embeddings for Val Town within Val Town it
    "pubDate": "Tue, 18 Jun 2024 00:00:00 GMT",
    "author": "JP Posma",
maxm/actuallyGoodEmojiSearch/main.tsx
2 matches
import { searchEmojis } from "https://esm.town/v/maxm/emojiVectorEmbeddings";
import { extractValInfo } from "https://esm.town/v/pomdtr/extractValInfo";
import { Hono } from "npm:hono@3.2.7";
      Use plain language to search for emojis. Get great results.
      <br />
      Built on Val Town with sqlite vector search and openai embeddings.
      <br />
      Fork the <a href="${htmlUrl}" target="_blank">source</a> and build your own!
stevekrouse/actuallyGoodEmojiSearch/main.tsx
2 matches
import { searchEmojis } from "https://esm.town/v/maxm/emojiVectorEmbeddings";
import { extractValInfo } from "https://esm.town/v/pomdtr/extractValInfo";
import { Hono } from "npm:hono@3.2.7";
      Use plain language to search for emojis. Get great results.
      <br />
      Built on Val Town with sqlite vector search and openai embeddings.
      <br />
      Fork the <a href="${htmlUrl}" target="_blank">source</a> and build your own!
stevekrouse/actuallyGoodEmojiSearch/README.md
1 matches
# Emoji Instant Search
Uses vector embeddings to get "vibes" search on emojis
maxm/emojisearch/index
7 matches
async function getEmbedding(emoji: string): Promise<number[]> {
  const result = await openai.embeddings.create({
    input: emoji,
    model: "text-embedding-3-small",
};
const embeddings: EmojiEmbedding[] = [];
// Calculate cosine similarity between two vectors
for (const emoji of emojisWithInfo) {
  embeddings.push({ emoji, embedding: await getEmbedding(emoji) });
}
function findNearestNeighbors(
  targetEmbedding: number[],
  allEmbeddings: EmojiEmbedding[],
  k: number = 50,
): { emoji: string; similarity: number }[] {
  return allEmbeddings
    .map(entry => ({
      emoji: entry.emoji,
}
const toSearch = embeddings.find((r) => (r.emoji === emojiToString(["🐻", emojis["🐻"]])))!;
console.log(findNearestNeighbors(toSearch.embedding, embeddings));
AIWB/memorySampleSummary/main.tsx
1 matches
// Generate embedding for a given text
async function generateEmbedding(text: string): Promise<number[]> {
  const response = await openai.embeddings.create({
    model: "text-embedding-ada-002",
    input: text,
goode_bye/ai/README.md
2 matches
```
async function calculateEmbeddings(text) {
    const url = `https://yawnxyz-ai.web.val.run/generate?embed=true&value=${encodeURIComponent(t
    
        return data;
    } catch (error) {
        console.error('Error calculating embeddings:', error);
        return null;
    }
wizos/ai/README.md
2 matches
```
async function calculateEmbeddings(text) {
    const url = `https://yawnxyz-ai.web.val.run/generate?embed=true&value=${encodeURIComponent(t
    
        return data;
    } catch (error) {
        console.error('Error calculating embeddings:', error);
        return null;
    }
tmcw/surprisingEmbeddings/index
11 matches
/** @jsxImportSource npm:hono@3/jsx */
import bots from "https://esm.town/v/tmcw/surprisingEmbeddings/bots"
import * as v from "jsr:@valibot/valibot"
import { Hono } from "npm:hono"
  <>
    <p>
      Embeddings. They're one of the parts of the LLM/AI wave that I sort of like.
    </p>
    <p>
    </p>
    <p>
      Embeddings are pretty cool when they work, because they sort of capture the idea of{" "}
      <a href="https://blog.val.town/blog/val-vibes/">'vibes', which makes them useful for searc
      Someone can search for 'lettuce' and get results for 'spinach' too because they're similar
    <p>
      This project is based on this{" "}
https://www.linkedin.com/pulse/insanity-relying-vector-embeddings-why-rag-fails-michael-wood-4ie
        blog post I read last year
      </a>{" "}
  if (inputResult.success) {
    const input = inputResult.output
    const embeddings = await client.embed({
      input,
      model: "voyage-3-lite",
      return {
        word,
        embedding: embeddings.data?.at(i)?.embedding,
      }
    })
      <html>
        <head>
          <title>Surprising embeddings</title>
          <link rel="stylesheet" href="https://unpkg.com/missing.css@1.1.3" />
            <header>
              <h3>
                Surprising embeddings
                <sub-title>
                  Using <a href="https://www.voyageai.com/">Voyage AI</a> voyage-3-lite model
              >
              </script>
t type="module" src="https://esm.town/v/tmcw/surprisingEmbeddings/visualization"></script>
            </div>
    <html>
      <head>
        <title>Surprising embeddings</title>
        <link rel="stylesheet" href="https://unpkg.com/missing.css@1.1.3" />
          <header>
            <h3>
              Surprising embeddings
              <sub-title>
                Using <a href="https://www.voyageai.com/">Voyage AI</a> voyage-3-lite model
tmcw/surprisingEmbeddings/embeddingGetter
2 matches
  const input = v.parse(inputSchema, ["dogs", "cats", "felines", "canines"])
  const embeddings = await client.embed({
    input,
    model: "voyage-3-lite",
    return {
      word,
      embedding: embeddings.data?.at(i)?.embedding,
    }
  })

Vals

7
View more
tmcw
surprisingEmbeddings
Visualizing embedding distances
maxm
emojiVectorEmbeddings
 
janpaul123
blogPostEmbeddingsDimensionalityReduction
 
janpaul123
compareEmbeddings
 
yawnxyz
embeddingsSearchExample
 

Users

No users found

Docs

2
View more
No docs found
…
7
Next