Search

    "slug": "val-vibes",
    "link": "/blog/val-vibes",
    "description": "How to build semantic search with embeddings for Val Town within Val Town itself",
    "pubDate": "Tue, 18 Jun 2024 00:00:00 GMT",
    "author": "JP Posma",

    "slug": "val-vibes",
    "link": "/blog/val-vibes",
    "description": "How to build semantic search with embeddings for Val Town within Val Town itself",
    "pubDate": "Tue, 18 Jun 2024 00:00:00 GMT",
    "author": "JP Posma",

    "slug": "val-vibes",
    "link": "/blog/val-vibes",
    "description": "How to build semantic search with embeddings for Val Town within Val Town itself",
    "pubDate": "Tue, 18 Jun 2024 00:00:00 GMT",
    "author": "JP Posma",

    "slug": "val-vibes",
    "link": "/blog/val-vibes",
    "description": "How to build semantic search with embeddings for Val Town within Val Town itself",
    "pubDate": "Tue, 18 Jun 2024 00:00:00 GMT",
    "author": "JP Posma",

  - `imageRecognition.labels`: Visual elements detected (people, objects, logos,
    etc.)
  - `vectors`: Text embeddings for semantic similarity (using Basilica method)
- **Content metadata fields** (may not yet be generally populated):
  - `description`: Manual content descriptions

  - `imageRecognition.labels`: Visual elements detected (people, objects, logos,
    etc.)
  - `vectors`: Text embeddings for semantic similarity (using Basilica method)
- **Content metadata fields** (may not yet be generally populated):
  - `description`: Manual content descriptions

  - `imageRecognition.labels`: Visual elements detected (people, objects, logos,
    etc.)
  - `vectors`: Text embeddings for semantic similarity (using Basilica method)
- **Content metadata fields** (may not yet be generally populated):
  - `description`: Manual content descriptions

    "slug": "val-vibes",
    "link": "/blog/val-vibes",
    "description": "How to build semantic search with embeddings for Val Town within Val Town itself",
    "pubDate": "Tue, 18 Jun 2024 00:00:00 GMT",
    "author": "JP Posma",

        contents: [query],
      });
      const values = result.embeddings[0].values;
      const queryResult = (await qdrant.search("wdl", {
        vector: values,

          return handleCompletions(await request.json(), apiKey)
            .catch(errHandler);
        case pathname.endsWith("/embeddings"):
          assert(request.method === "POST");
          return handleEmbeddings(await request.json(), apiKey)
            .catch(errHandler);
        case pathname.endsWith("/models"):
}
const DEFAULT_EMBEDDINGS_MODEL = "gemini-embedding-001";
async function handleEmbeddings (req, apiKey) {
  let modelFull, model;
  switch (true) {
      break;
    default:
      model = DEFAULT_EMBEDDINGS_MODEL;
  }
  modelFull = modelFull ?? "models/" + model;
  let { body } = response;
  if (response.ok) {
    const { embeddings } = JSON.parse(await response.text());
    body = JSON.stringify({
      object: "list",
      data: embeddings.map(({ values }, index) => ({
        object: "embedding",
        index,