Log inSign up

Search

115 code results for “embeddings”
Back to all results

Code
115

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"
    <p>
      Embeddings. They're one of the parts of the LLM/AI wave that I sort of like.
    </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
      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
    const input = inputResult.output
    const embeddings = await client.embed({
      input,
        word,
        embedding: embeddings.data?.at(i)?.embedding,
      }
        <head>
          <title>Surprising embeddings</title>
          <link rel="stylesheet" href="https://unpkg.com/missing.css@1.1.3" />
              <h3>
                Surprising embeddings
                <sub-title>
              </script>
t type="module" src="https://esm.town/v/tmcw/surprisingEmbeddings/visualization"></script>
            </div>
      <head>
        <title>Surprising embeddings</title>
        <link rel="stylesheet" href="https://unpkg.com/missing.css@1.1.3" />
            <h3>
              Surprising embeddings
              <sub-title>
tmcw/surprisingEmbeddings/visualization
0 matches
tmcw/surprisingEmbeddings/embeddingGetter
2 matches
  const embeddings = await client.embed({
    input,
      word,
      embedding: embeddings.data?.at(i)?.embedding,
    }
yawnxyz/SidebarToArchive/main.tsx
4 matches
      try {
        // let embeddings = await modelProvider.gen({
        //   embed: true, 
        // });
        // console.log(`Adding link ${counter}:`, link.title, link.url, embeddings);
        console.log(`Adding link ${counter}:`, link.title, link.url);
          data: JSON.stringify(link),
          // embeddings: embeddings.embedding.join(','),
        });
janpaul123/semanticSearchBlobs/main.tsx
13 matches
export default async function semanticSearchPublicVals(query) {
  const allValsBlobEmbeddingsMeta = (await blob.getJSON(`allValsBlob${dimensions}EmbeddingsMeta`
 allBatchDataIndexes = _.uniq(Object.values(allValsBlobEmbeddingsMeta).map((item: any) => item.b
  const embeddingsBatches = [];
  const allBatchDataIndexesPromises = [];
  for (const batchDataIndex of allBatchDataIndexes) {
    const embeddingsBatchBlobName = `allValsBlob${dimensions}EmbeddingsData_${batchDataIndex}`;
    const promise = blob.get(embeddingsBatchBlobName).then((response) => response.arrayBuffer())
    promise.then((data) => {
      embeddingsBatches[batchDataIndex as any] = data;
      console.log(`Loaded ${embeddingsBatchBlobName} (${data.byteLength} bytes)`);
    });
  const openai = new OpenAI();
  const queryEmbedding = (await openai.embeddings.create({
    model: "text-embedding-3-small",
  const res = [];
  for (const id in allValsBlobEmbeddingsMeta) {
    const meta = allValsBlobEmbeddingsMeta[id];
    const embedding = new Float32Array(
      embeddingsBatches[meta.batchDataIndex],
      dimensions * 4 * meta.valIndex,
janpaul123/semanticSearchTurso/main.tsx
6 matches
  const sqlite = createClient({
    url: "libsql://valsembeddings-jpvaltown.turso.io",
    authToken: Deno.env.get("TURSO_AUTH_TOKEN_VALSEMBEDDINGS"),
  });
  const embedding = await openai.embeddings.create({
    model: "text-embedding-3-small",
      sql:
"WITH matches AS (SELECT rowid, distance FROM vss_vals_embeddings WHERE vss_search(embedding, :e
      args: { embeddingBinary },
janpaul123/semanticSearchBlobs/README.md
6 matches
ob storage](https://docs.val.town/std/blob/) to search embeddings of all vals, by downloading th
t metadata from blob storage: `allValsBlob${dimensions}EmbeddingsMeta` (currently `allValsBlob15
  - The blobs have been generated by [janpaul123/indexValsBlobs](https://www.val.town/v/janpaul1
- Get all blobs with embeddings pointed to by the metadata, e.g. `allValsBlob1536EmbeddingsData_
- Call OpenAI to generate an embedding for the search query.
- Go through all embeddings and compute cosine similarity with the embedding for the search quer
- Return list sorted by similarity.
janpaul123/semanticSearchTurso/README.md
3 matches
Uses [Turso](https://turso.tech/) to search embeddings of all vals, using the [sqlite-vss](https
- Call OpenAI to generate an embedding for the search query.
- Query the `vss_vals_embeddings` table in Turso using `vss_search`.
  - The `vss_vals_embeddings` table has been generated by [janpaul123/indexValsTurso](https://ww
  - This table is incomplete due to a [bug in Turso](https://discord.com/channels/93307116268095
wilt/createQdrantCollection/main.tsx
1 matches
 * Create a new Qdrant collection in an existing cluster with the given name
 * Uses recommended values for OpenAPI embeddings
 */
q8kamikaze/plotmock/jinatest.ts
1 matches
  try {
    const r = await fetch("https://embeddings-dashboard-api.jina.ai/api/v1/api_key/user?api_key=
      { signal: AbortSignal.timeout(20000) });
ziggyware/free-ai/router-discover.ts
1 matches
    const rx = new RegExp(p.prefer, "i");
    // never "discover" non-chat endpoints: guard/moderation, ASR, TTS, embeddings, rerankers
    const JUNK = /guard|safeguard|moderat|whisper|tts|speech|embed|rerank|playai|vision-only|ocr
q8kamikaze/plotmock/jembed.ts
2 matches
export async function embed(texts: string[], task: "retrieval.passage" | "retrieval.query") {
  const r = await fetch("https://api.jina.ai/v1/embeddings", {
    method: "POST",
    headers: { "content-type": "application/json", authorization: "Bearer " + KEY() },
    body: JSON.stringify({ model: "jina-embeddings-v3", task, dimensions: DIM, input: texts }),
    signal: AbortSignal.timeout(50000),
ziggyware/free-ai/router-discover.ts
1 matches
    const rx = new RegExp(p.prefer, "i");
    // never "discover" non-chat endpoints: guard/moderation, ASR, TTS, embeddings, rerankers
    const JUNK = /guard|safeguard|moderat|whisper|tts|speech|embed|rerank|playai|vision-only|ocr
cleitoncosta/grimorio-evidence-memory/seed_manual_depth_canaries.ts
1 matches
['MDC-001','historical_breadth',{historical_master_reaches_numbered_section:193,rule:'final manu
['MDC-002','ai_retrieval',{historical_topics:['embeddings','vector search','RAG','advanced RAG',
['MDC-003','security',{historical_topics:['least privilege','defense in depth','deny by default'
cleitoncosta/grimorio-evidence-memory/seed_manual_requirements.ts
1 matches
const req = [
ep learning"],["M004","Sistemas de IA","Redes neurais, embeddings, transformers e attention"],["
];
2
…