Voyage AI

App · 4 actions

Create text, multimodal and contextual embeddings and rerank search results with Voyage AI's retrieval models.

Actions

ActionWhat it does
Create contextual embeddingsEmbed the chunks of one document so that each chunk's vector also reflects the rest of the document.
Create embeddingsTurn each text into a vector with a Voyage AI embedding model, ready to store in a vector database such as Pinecone and search by meaning.
Create multimodal embeddingTurn a text, an image, or the two together into one vector, so pictures and words can be searched in the same index.
Rerank documentsPut a list of documents in order of how well each answers a query, with a score for each.

Create contextual embeddings

Embed the chunks of one document so that each chunk's vector also reflects the rest of the document. Finds the right chunk more often than embedding the chunks one by one.

Inputs

Document chunkschunkslistRequired
The pieces of one document, in reading order, one entry each. Do not repeat text between pieces. With Input type set to Query, give a single entry.
Input typeinput_typetext
Optional. Use Document for text you will store and search through, and Query for the text a search starts from. Voyage AI adjusts the vector to match.One of: document (Document (text you will store and search through)), query (Query (the question you search with)), none (Not set). Default: document.
Vector sizeoutput_dimensiontext
Optional. How many numbers each vector holds. Smaller vectors are cheaper to store, larger ones slightly more exact. Leave empty for the model's own size (1,024) unless your vector database needs another. Only some models can change it.One of: 256, 512, 1024, 2048.

Outputs

countnumber
How many vectors came back
dimensionnumber
How many numbers each vector holds
embeddingslist
One vector per text, in the order you sent them
modeltext
The model Voyage AI used
total_tokensnumber
Tokens Voyage AI counted for this request, which is what it bills
Example output
{
  "count": 2,
  "dimension": 4,
  "embeddings": [
    {
      "embedding": [
        0.0132,
        -0.0267,
        0.0418,
        -0.0071
      ],
      "index": 0
    },
    {
      "embedding": [
        0.0132,
        -0.0267,
        0.0418,
        -0.0071
      ],
      "index": 1
    }
  ],
  "model": "voyage-context-3",
  "total_tokens": 24
}

Create embeddings

Turn each text into a vector with a Voyage AI embedding model, ready to store in a vector database such as Pinecone and search by meaning. Takes up to 1,000 texts per step.

Inputs

TextstextslistRequired
The texts to embed, one entry each, for example the chunks of a document or the rows of a table.
Modelmodeltext
Optional. Voyage 4 suits most uses; Large is the most accurate, Lite the fastest and cheapest. Code, Finance and Law models do better on those subjects.One of: voyage-4 (Voyage 4 (default, balanced)), voyage-4-large (Voyage 4 Large (best quality)), voyage-4-lite (Voyage 4 Lite (fastest and cheapest)), voyage-code-4 (Voyage Code 4 (source code)), voyage-finance-2 (Voyage Finance 2 (finance)), voyage-law-2 (Voyage Law 2 (legal)), voyage-3.5 (Voyage 3.5), voyage-3.5-lite (Voyage 3.5 Lite), voyage-3-large (Voyage 3 Large), voyage-code-3 (Voyage Code 3). Default: voyage-4.
Input typeinput_typetext
Optional. Use Document for text you will store and search through, and Query for the text a search starts from. Voyage AI adjusts the vector to match.One of: document (Document (text you will store and search through)), query (Query (the question you search with)), none (Not set). Default: document.
Vector sizeoutput_dimensiontext
Optional. How many numbers each vector holds. Smaller vectors are cheaper to store, larger ones slightly more exact. Leave empty for the model's own size (1,024) unless your vector database needs another. Only some models can change it.One of: 256, 512, 1024, 2048.
Shorten texts that are too longtruncationtrue/false
Optional. When on, a text longer than the model can read is cut to fit. When off, the step fails instead.Default: true.

Outputs

countnumber
How many vectors came back
dimensionnumber
How many numbers each vector holds
embeddingslist
One vector per text, in the order you sent them
modeltext
The model Voyage AI used
total_tokensnumber
Tokens Voyage AI counted for this request, which is what it bills
Example output
{
  "count": 2,
  "dimension": 4,
  "embeddings": [
    {
      "embedding": [
        0.0132,
        -0.0267,
        0.0418,
        -0.0071
      ],
      "index": 0
    },
    {
      "embedding": [
        0.0132,
        -0.0267,
        0.0418,
        -0.0071
      ],
      "index": 1
    }
  ],
  "model": "voyage-4",
  "total_tokens": 14
}

Create multimodal embedding

Turn a text, an image, or the two together into one vector, so pictures and words can be searched in the same index.

Inputs

Texttexttext
Optional. Words to embed. Give this, an image, or both.
Image URLimage_urltext
Optional. The web address of a PNG, JPEG, WebP or GIF image, for example 'https://example.com/photo.jpg'. The address must be public.
Modelmodeltext
Optional. Voyage Multimodal 3.5 is the newest.One of: voyage-multimodal-3.5 (Voyage Multimodal 3.5 (default)), voyage-multimodal-3 (Voyage Multimodal 3). Default: voyage-multimodal-3.5.
Input typeinput_typetext
Optional. Use Document for text you will store and search through, and Query for the text a search starts from. Voyage AI adjusts the vector to match.One of: document (Document (text you will store and search through)), query (Query (the question you search with)), none (Not set). Default: document.

Outputs

dimensionnumber
How many numbers the vector holds
embeddinglist
The vector: a list of numbers
image_pixelsnumber
Pixels counted for the image
modeltext
The model Voyage AI used
text_tokensnumber
Tokens counted for the text
total_tokensnumber
Tokens Voyage AI counted for this request, which is what it bills
Example output
{
  "dimension": 4,
  "embedding": [
    0.0132,
    -0.0267,
    0.0418,
    -0.0071
  ],
  "image_pixels": 17920,
  "model": "voyage-multimodal-3.5",
  "text_tokens": 4,
  "total_tokens": 36
}

Rerank documents

Put a list of documents in order of how well each answers a query, with a score for each. Use it to pick the best matches out of search or database results.

Inputs

QueryquerytextRequired
The question or search to rank the documents against.
DocumentsdocumentslistRequired
The texts to put in order, one entry each. Up to 1,000.
Modelmodeltext
Optional. The Lite models are faster and cheaper; the others rank more accurately.One of: rerank-2.5 (Rerank 2.5 (default)), rerank-2.5-lite (Rerank 2.5 Lite (faster)), rerank-3 (Rerank 3), rerank-3-lite (Rerank 3 Lite), rerank-2 (Rerank 2), rerank-2-lite (Rerank 2 Lite). Default: rerank-2.5.
Best matches to returntop_knumber
Optional. Return only this many documents, best first. Leave empty to get them all.At least 1.
Shorten texts that are too longtruncationtrue/false
Optional. When on, a text longer than the model can read is cut to fit. When off, the step fails instead.Default: true.

Outputs

countnumber
How many documents came back
modeltext
The model Voyage AI used
resultslist
Documents from most to least relevant
top_documenttext
The most relevant document, for convenience
total_tokensnumber
Tokens Voyage AI counted for this request, which is what it bills
Example output
{
  "count": 2,
  "model": "rerank-2.5",
  "results": [
    {
      "document": "Voyage AI makes embedding models for search.",
      "index": 1,
      "relevance_score": 0.8984375
    },
    {
      "document": "The weather is mild in spring.",
      "index": 0,
      "relevance_score": 0.1171875
    }
  ],
  "top_document": "Voyage AI makes embedding models for search.",
  "total_tokens": 31
}

On this page