Generative Language API Documentation

Welcome to the comprehensive documentation for the Generative Language API (version v1beta). This document provides detailed information, including descriptions and curl examples, for every available function.

API Base URL: https://generativelanguage.googleapis.com/

Resources

`batches`

The batches resource deals with long-running operations.

`batches.list`

Lists operations that match the specified filter in the request. If the server doesn't support this method, it returns UNIMPLEMENTED.

HTTP Request: GET https://generativelanguage.googleapis.com/v1beta/batches
Path Parameter:
- name: string (required). The name of the operation's parent resource. Must match the pattern ^batches$.
Query Parameters:
- filter: string. The standard list filter.
- pageSize: integer. The standard list page size.
- pageToken: string. The standard list page token.
Response Body: ListOperationsResponse

Example curl request:

curl "https://generativelanguage.googleapis.com/v1beta/batches?filter=done%3Dtrue&pageSize=10&key=[YOUR_API_KEY]"

`batches.get`

Gets the latest state of a long-running operation. Clients can use this method to poll the operation result at intervals as recommended by the API service.

HTTP Request: GET https://generativelanguage.googleapis.com/v1beta/batches/{batchesId}
Path Parameter:
- name: string (required). The name of the operation resource. Must match the pattern ^batches/[^/]+$.
Response Body: Operation

Example curl request:

curl "https://generativelanguage.googleapis.com/v1beta/batches/operation-12345?key=[YOUR_API_KEY]"

`batches.delete`

Deletes a long-running operation. This method indicates that the client is no longer interested in the operation result. It does not cancel the operation. If the server doesn't support this method, it returns google.rpc.Code.UNIMPLEMENTED.

HTTP Request: DELETE https://generativelanguage.googleapis.com/v1beta/batches/{batchesId}
Path Parameter:
- name: string (required). The name of the operation resource to be deleted. Must match the pattern ^batches/[^/]+$.
Response Body: Empty

Example curl request:

curl -X DELETE "https://generativelanguage.googleapis.com/v1beta/batches/operation-12345?key=[YOUR_API_KEY]"

`batches.cancel`

Starts asynchronous cancellation on a long-running operation. The server makes a best effort to cancel the operation, but success is not guaranteed. If the server doesn't support this method, it returns google.rpc.Code.UNIMPLEMENTED.

HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/batches/{batchesId}:cancel
Path Parameter:
- name: string (required). The name of the operation resource to be cancelled. Must match the pattern ^batches/[^/]+$.
Response Body: Empty

Example curl request:

curl -X POST "https://generativelanguage.googleapis.com/v1beta/batches/operation-12345:cancel?key=[YOUR_API_KEY]" \
  -H "Content-Type: application/json" \
  -d '{}'

`models`

The models resource provides access to the generative models.

`models.generateContent`

Generates a model response given an input GenerateContentRequest. Refer to the text generation guide for detailed usage information.

HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/{modelsId}:generateContent
Path Parameter:
- model: string (required). The name of the Model to use for generating the completion. Format: models/{model}.
Request Body: GenerateContentRequest
Response Body: GenerateContentResponse

Example curl request:

curl -X POST "https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-flash-001:generateContent?key=[YOUR_API_KEY]" \
  -H "Content-Type: application/json" \
  -d '{
        "contents": [{
          "parts":[{
            "text": "Explain why the sky is blue."
          }]
        }]
      }'

`models.generateAnswer`

Generates a grounded answer from the model given an input GenerateAnswerRequest.

HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/{modelsId}:generateAnswer
Path Parameter:
- model: string (required). The name of the Model to use for generating the grounded response. Format: models/{model}.
Request Body: GenerateAnswerRequest
Response Body: GenerateAnswerResponse

Example curl request:

curl -X POST "https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-flash-001:generateAnswer?key=[YOUR_API_KEY]" \
  -H "Content-Type: application/json" \
  -d '{
        "contents": [{"parts":[{"text": "What are the main ingredients in a margarita?"}]}],
        "answerStyle": "VERBOSE",
        "inlinePassages": {
          "passages": [{
            "id": "passage-1",
            "content": {
              "parts": [{
                "text": "A classic margarita cocktail is made with tequila, orange liqueur (like Cointreau or Triple Sec), and fresh lime juice. It is often served with a salted rim."
              }]
            }
          }]
        }
      }'

`models.streamGenerateContent`

Generates a streamed response from the model given an input GenerateContentRequest.

HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/{modelsId}:streamGenerateContent
Path Parameter:
- model: string (required). The name of the Model to use for generating the completion. Format: models/{model}.
Request Body: GenerateContentRequest
Response Body: A stream of GenerateContentResponse objects.

Example curl request:

curl -X POST "https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-flash-001:streamGenerateContent?key=[YOUR_API_KEY]" \
  -H "Content-Type: application/json" \
  -d '{
        "contents": [{
          "parts":[{
            "text": "Write a long, epic poem about a journey to the center of the Earth."
          }]
        }]
      }'

`models.embedContent`

Generates a text embedding vector from the input Content using the specified Gemini Embedding model.

HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/{modelsId}:embedContent
Path Parameter:
- model: string (required). The model's resource name. Format: models/{model}.
Request Body: EmbedContentRequest
Response Body: EmbedContentResponse

Example curl request:

curl -X POST "https://generativelanguage.googleapis.com/v1beta/models/embedding-001:embedContent?key=[YOUR_API_KEY]" \
  -H "Content-Type: application/json" \
  -d '{
        "content": {
          "parts": [{
            "text": "This is a sentence to be embedded."
          }]
        },
        "taskType": "RETRIEVAL_DOCUMENT"
      }'

`models.batchEmbedContents`

Generates multiple embedding vectors from the input Content which consists of a batch of strings represented as EmbedContentRequest objects.

HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/{modelsId}:batchEmbedContents
Path Parameter:
- model: string (required). The model's resource name. Format: models/{model}.
Request Body: BatchEmbedContentsRequest
Response Body: BatchEmbedContentsResponse

Example curl request:

curl -X POST "https://generativelanguage.googleapis.com/v1beta/models/embedding-001:batchEmbedContents?key=[YOUR_API_KEY]" \
  -H "Content-Type: application/json" \
  -d '{
        "requests": [
          {
            "model": "models/embedding-001",
            "content": {"parts": [{"text": "First document."}]},
            "taskType": "RETRIEVAL_DOCUMENT"
          },
          {
            "model": "models/embedding-001",
            "content": {"parts": [{"text": "Second document."}]},
            "taskType": "RETRIEVAL_DOCUMENT"
          }
        ]
      }'

`models.countTokens`

Runs a model's tokenizer on input Content and returns the token count. Refer to the tokens guide to learn more about tokens.

HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/{modelsId}:countTokens
Path Parameter:
- model: string (required). The model's resource name. Format: models/{model}.
Request Body: CountTokensRequest
Response Body: CountTokensResponse

Example curl request:

curl -X POST "https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-flash-001:countTokens?key=[YOUR_API_KEY]" \
  -H "Content-Type: application/json" \
  -d '{
        "contents": [{
          "parts":[{
            "text": "How many tokens are in this sentence?"
          }]
        }]
      }'

`models.get`

Gets information about a specific Model such as its version number, token limits, and other metadata.

HTTP Request: GET https://generativelanguage.googleapis.com/v1beta/models/{modelsId}
Path Parameter:
- name: string (required). The resource name of the model. Format: models/{model}.
Response Body: Model

Example curl request:

curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-flash-001?key=[YOUR_API_KEY]"

`models.list`

Lists the Models available through the Gemini API.

HTTP Request: GET https://generativelanguage.googleapis.com/v1beta/models
Query Parameters:
- pageSize: integer. The maximum number of Models to return (per page).
- pageToken: string. A page token, received from a previous ListModels call.
Response Body: ListModelsResponse

Example curl request:

curl "https://generativelanguage.googleapis.com/v1beta/models?pageSize=50&key=[YOUR_API_KEY]"

`models.generateText`

Generates a response from the model given an input message.

HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/{modelsId}:generateText
Path Parameter:
- model: string (required). The name of the Model or TunedModel to use. Example: models/text-bison-001.
Request Body: GenerateTextRequest
Response Body: GenerateTextResponse

Example curl request:

curl -X POST "https://generativelanguage.googleapis.com/v1beta/models/text-bison-001:generateText?key=[YOUR_API_KEY]" \
  -H "Content-Type: application/json" \
  -d '{
        "prompt": {
          "text": "Once upon a time"
        },
        "temperature": 0.7,
        "candidateCount": 1
      }'

`models.embedText`

Generates an embedding from the model given an input message.

HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/{modelsId}:embedText
Path Parameter:
- model: string (required). The model name to use. Example: models/embedding-gecko-001.
Request Body: EmbedTextRequest
Response Body: EmbedTextResponse

Example curl request:

curl -X POST "https://generativelanguage.googleapis.com/v1beta/models/embedding-gecko-001:embedText?key=[YOUR_API_KEY]" \
  -H "Content-Type: application/json" \
  -d '{
        "text": "Embed this sentence."
      }'

`models.batchEmbedText`

Generates multiple embeddings from the model given input text in a synchronous call.

HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/{modelsId}:batchEmbedText
Path Parameter:
- model: string (required). The name of the Model to use. Example: models/embedding-gecko-001.
Request Body: BatchEmbedTextRequest
Response Body: BatchEmbedTextResponse

Example curl request:

curl -X POST "https://generativelanguage.googleapis.com/v1beta/models/embedding-gecko-001:batchEmbedText?key=[YOUR_API_KEY]" \
  -H "Content-Type: application/json" \
  -d '{
        "texts": [
          "This is the first sentence.",
          "Here is a second one."
        ]
      }'

`models.countTextTokens`

Runs a model's tokenizer on a text and returns the token count.

HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/{modelsId}:countTextTokens
Path Parameter:
- model: string (required). The model's resource name.
Request Body: CountTextTokensRequest
Response Body: CountTextTokensResponse

Example curl request:

curl -X POST "https://generativelanguage.googleapis.com/v1beta/models/text-bison-001:countTextTokens?key=[YOUR_API_KEY]" \
  -H "Content-Type: application/json" \
  -d '{
        "prompt": {
          "text": "Count the tokens in this text."
        }
      }'

`tunedModels`

The tunedModels resource allows you to manage your fine-tuned models.

`tunedModels.create`

Creates a tuned model. Check intermediate tuning progress through the operations service.

HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/tunedModels
Query Parameter:
- tunedModelId: string. Optional. The unique id for the tuned model.
Request Body: TunedModel
Response Body: Operation

Example curl request:

curl -X POST "https://generativelanguage.googleapis.com/v1beta/tunedModels?key=[YOUR_API_KEY]" \
  -H "Content-Type: application/json" \
  -d '{
        "displayName": "My Sentence Translator",
        "baseModel": "models/gemini-1.5-flash-001",
        "tuningTask": {
          "trainingData": {
            "examples": {
              "examples": [
                {
                  "textInput": "The cat sat on the mat.",
                  "output": "Le chat était assis sur le tapis."
                },
                {
                  "textInput": "I love to read books.",
                  "output": "J'adore lire des livres."
                }
              ]
            }
          },
          "hyperparameters": {
            "epochCount": 5
          }
        }
      }'

`tunedModels.get`

Gets information about a specific TunedModel.

HTTP Request: GET https://generativelanguage.googleapis.com/v1beta/tunedModels/{tunedModelsId}
Path Parameter:
- name: string (required). The resource name of the model. Format: tunedModels/my-model-id.
Response Body: TunedModel

Example curl request:

curl "https://generativelanguage.googleapis.com/v1beta/tunedModels/sentence-translator-u3b7m?key=[YOUR_API_KEY]"

`tunedModels.list`

Lists created tuned models.

HTTP Request: GET https://generativelanguage.googleapis.com/v1beta/tunedModels
Query Parameters:
- pageSize: integer. The maximum number of TunedModels to return.
- pageToken: string. A page token from a previous call.
- filter: string. A filter to search over the tuned model's description and display name.
Response Body: ListTunedModelsResponse

Example curl request:

curl "https://generativelanguage.googleapis.com/v1beta/tunedModels?pageSize=10&filter=owner:me&key=[YOUR_API_KEY]"

`tunedModels.patch`

Updates a tuned model.

HTTP Request: PATCH https://generativelanguage.googleapis.com/v1beta/tunedModels/{tunedModelsId}
Path Parameter:
- name: string (required). The tuned model name. Example: tunedModels/sentence-translator-u3b7m.
Query Parameter:
- updateMask: string. The list of fields to update.
Request Body: TunedModel
Response Body: TunedModel

Example curl request:

curl -X PATCH "https://generativelanguage.googleapis.com/v1beta/tunedModels/sentence-translator-u3b7m?updateMask=displayName&key=[YOUR_API_KEY]" \
  -H "Content-Type: application/json" \
  -d '{
        "displayName": "My Awesome French Translator"
      }'

`tunedModels.delete`

Deletes a tuned model.

HTTP Request: DELETE https://generativelanguage.googleapis.com/v1beta/tunedModels/{tunedModelsId}
Path Parameter:
- name: string (required). The resource name of the model. Format: tunedModels/my-model-id.
Response Body: Empty

Example curl request:

curl -X DELETE "https://generativelanguage.googleapis.com/v1beta/tunedModels/sentence-translator-u3b7m?key=[YOUR_API_KEY]"

`tunedModels.transferOwnership`

Transfers ownership of the tuned model. This is the only way to change ownership of the tuned model. The current owner will be downgraded to writer role.

HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/tunedModels/{tunedModelsId}:transferOwnership
Path Parameter:
- name: string (required). The resource name of the tuned model to transfer ownership. Format: tunedModels/my-model-id.
Request Body: TransferOwnershipRequest
Response Body: TransferOwnershipResponse

Example curl request:

curl -X POST "https://generativelanguage.googleapis.com/v1beta/tunedModels/my-model-id:transferOwnership?key=[YOUR_API_KEY]" \
  -H "Content-Type: application/json" \
  -d '{
        "emailAddress": "[email protected]"
      }'

`tunedModels.generateContent`

Generates a model response from a tuned model given an input GenerateContentRequest.

HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/tunedModels/{tunedModelsId}:generateContent
Path Parameter:
- model: string (required). The name of the TunedModel to use. Format: tunedModels/{tuned_model_id}.
Request Body: GenerateContentRequest
Response Body: GenerateContentResponse

Example curl request:

curl -X POST "https://generativelanguage.googleapis.com/v1beta/tunedModels/sentence-translator-u3b7m:generateContent?key=[YOUR_API_KEY]" \
  -H "Content-Type: application/json" \
  -d '{
        "contents": [{
          "parts":[{
            "text": "The quick brown fox jumps over the lazy dog."
          }]
        }]
      }'

`files`

The files resource allows you to upload and manage files for use with the API.

`files.upload`

Creates a File. This is done by uploading the file content.

HTTP Request: POST https://generativelanguage.googleapis.com/upload/v1beta/files
Media Upload: This endpoint supports media uploads. You would typically use a client library to handle the multipart upload.
Request Body: CreateFileRequest
Response Body: CreateFileResponse

Example curl request (for a small file):

# This is a simplified example. For larger files, a resumable upload is recommended.
# The following assumes 'my-file.txt' and 'metadata.json' exist in the current directory.
# metadata.json content: { "file": { "displayName": "My Awesome File" } }

curl -X POST "https://generativelanguage.googleapis.com/upload/v1beta/files?key=[YOUR_API_KEY]" \
  -H "Content-Type: multipart/related; boundary=foo_bar_baz" \
  --data-binary @- <<EOF
--foo_bar_baz
Content-Type: application/json; charset=UTF-8

$(cat metadata.json)

--foo_bar_baz
Content-Type: text/plain

$(cat my-file.txt)
--foo_bar_baz--
EOF

`files.list`

Lists the metadata for Files owned by the requesting project.

HTTP Request: GET https://generativelanguage.googleapis.com/v1beta/files
Query Parameters:
- pageSize: integer. Maximum number of Files to return per page (max 100).
- pageToken: string. A page token from a previous ListFiles call.
Response Body: ListFilesResponse

Example curl request:

curl "https://generativelanguage.googleapis.com/v1beta/files?pageSize=10&key=[YOUR_API_KEY]"

`files.get`

Gets the metadata for the given File.

HTTP Request: GET https://generativelanguage.googleapis.com/v1beta/files/{filesId}
Path Parameter:
- name: string (required). The name of the File to get. Example: files/abc-123.
Response Body: File

Example curl request:

curl "https://generativelanguage.googleapis.com/v1beta/files/abc-123?key=[YOUR_API_KEY]"

`files.delete`

Deletes the File.

HTTP Request: DELETE https://generativelanguage.googleapis.com/v1beta/files/{filesId}
Path Parameter:
- name: string (required). The name of the File to delete. Example: files/abc-123.
Response Body: Empty

Example curl request:

curl -X DELETE "https://generativelanguage.googleapis.com/v1beta/files/abc-123?key=[YOUR_API_KEY]"

`corpora`

The corpora resource manages collections of documents for semantic search and retrieval. A project can have up to 5 corpora.

`corpora.create`

Creates an empty Corpus.

HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/corpora
Request Body: Corpus
Response Body: Corpus

Example curl request:

curl -X POST "https://generativelanguage.googleapis.com/v1beta/corpora?key=[YOUR_API_KEY]" \
  -H "Content-Type: application/json" \
  -d '{
        "displayName": "My Research Papers"
      }'

`corpora.get`

Gets information about a specific Corpus.

HTTP Request: GET https://generativelanguage.googleapis.com/v1beta/corpora/{corporaId}
Path Parameter:
- name: string (required). The name of the Corpus. Example: corpora/my-corpus-123.
Response Body: Corpus

Example curl request:

curl "https://generativelanguage.googleapis.com/v1beta/corpora/my-research-papers-123a456b789c?key=[YOUR_API_KEY]"

`corpora.patch`

Updates a Corpus. Currently, this only supports updating displayName.

HTTP Request: PATCH https://generativelanguage.googleapis.com/v1beta/corpora/{corporaId}
Path Parameter:
- name: string (required). The Corpus resource name.
Query Parameter:
- updateMask: string (required). The list of fields to update.
Request Body: Corpus
Response Body: Corpus

Example curl request:

curl -X PATCH "https://generativelanguage.googleapis.com/v1beta/corpora/my-research-papers-123a456b789c?updateMask=displayName&key=[YOUR_API_KEY]" \
  -H "Content-Type: application/json" \
  -d '{
        "displayName": "Updated Research Papers Collection"
      }'

`corpora.delete`

Deletes a Corpus.

HTTP Request: DELETE https://generativelanguage.googleapis.com/v1beta/corpora/{corporaId}
Path Parameter:
- name: string (required). The resource name of the Corpus.
Query Parameter:
- force: boolean. If set to true, any Documents and objects related to this Corpus will also be deleted.
Response Body: Empty

Example curl request:

curl -X DELETE "https://generativelanguage.googleapis.com/v1beta/corpora/my-research-papers-123a456b789c?force=true&key=[YOUR_API_KEY]"

`corpora.list`

Lists all Corpora owned by the user.

HTTP Request: GET https://generativelanguage.googleapis.com/v1beta/corpora
Query Parameters:
- pageSize: integer. The maximum number of Corpora to return (max 20).
- pageToken: string. A page token from a previous ListCorpora call.
Response Body: ListCorporaResponse

Example curl request:

curl "https://generativelanguage.googleapis.com/v1beta/corpora?pageSize=10&key=[YOUR_API_KEY]"

`corpora.query`

Performs semantic search over a Corpus.

HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/corpora/{corporaId}:query
Path Parameter:
- name: string (required). The name of the Corpus to query.
Request Body: QueryCorpusRequest
Response Body: QueryCorpusResponse

Example curl request:

curl -X POST "https://generativelanguage.googleapis.com/v1beta/corpora/my-research-papers-123a456b789c:query?key=[YOUR_API_KEY]" \
  -H "Content-Type: application/json" \
  -d '{
        "query": "What are the latest advancements in AI?",
        "resultsCount": 5
      }'

`corpora.documents`

The documents sub-resource manages documents within a corpus.

`corpora.documents.create`

Creates an empty Document.

HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/corpora/{corporaId}/documents
Path Parameter:
- parent: string (required). The name of the Corpus where this Document will be created.
Request Body: Document
Response Body: Document

Example curl request:

curl -X POST "https://generativelanguage.googleapis.com/v1beta/corpora/my-research-papers-123a456b789c/documents?key=[YOUR_API_KEY]" \
  -H "Content-Type: application/json" \
  -d '{
        "displayName": "Paper on Neural Networks"
      }'

`corpora.documents.get`

Gets information about a specific Document.

HTTP Request: GET https://generativelanguage.googleapis.com/v1beta/corpora/{corporaId}/documents/{documentsId}
Path Parameter:
- name: string (required). The name of the Document to retrieve.
Response Body: Document

Example curl request:

curl "https://generativelanguage.googleapis.com/v1beta/corpora/my-research-papers-123a456b789c/documents/paper-on-neural-networks-456b789c123d?key=[YOUR_API_KEY]"

`corpora.documents.patch`

Updates a Document.

HTTP Request: PATCH https://generativelanguage.googleapis.com/v1beta/corpora/{corporaId}/documents/{documentsId}
Path Parameter:
- name: string (required). The Document resource name.
Query Parameter:
- updateMask: string (required). The list of fields to update.
Request Body: Document
Response Body: Document

Example curl request:

curl -X PATCH "https://generativelanguage.googleapis.com/v1beta/corpora/my-research-papers-123a456b789c/documents/paper-on-neural-networks-456b789c123d?updateMask=displayName&key=[YOUR_API_KEY]" \
  -H "Content-Type: application/json" \
  -d '{
        "displayName": "2024 Paper on Advanced Neural Networks"
      }'

`corpora.documents.delete`

Deletes a Document.

HTTP Request: DELETE https://generativelanguage.googleapis.com/v1beta/corpora/{corporaId}/documents/{documentsId}
Path Parameter:
- name: string (required). The resource name of the Document.
Query Parameter:
- force: boolean. If true, deletes related Chunks as well.
Response Body: Empty

Example curl request:

curl -X DELETE "https://generativelanguage.googleapis.com/v1beta/corpora/my-research-papers-123a456b789c/documents/paper-on-neural-networks-456b789c123d?force=true&key=[YOUR_API_KEY]"

`corpora.documents.list`

Lists all Documents in a Corpus.

HTTP Request: GET https://generativelanguage.googleapis.com/v1beta/corpora/{corporaId}/documents
Path Parameter:
- parent: string (required). The name of the Corpus.
Query Parameters:
- pageSize: integer. The maximum number of Documents to return.
- pageToken: string. A page token from a previous call.
Response Body: ListDocumentsResponse

Example curl request:

curl "https://generativelanguage.googleapis.com/v1beta/corpora/my-research-papers-123a456b789c/documents?pageSize=10&key=[YOUR_API_KEY]"

`corpora.documents.query`

Performs semantic search over a Document.

HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/corpora/{corporaId}/documents/{documentsId}:query
Path Parameter:
- name: string (required). The name of the Document to query.
Request Body: QueryDocumentRequest
Response Body: QueryDocumentResponse

Example curl request:

curl -X POST "https://generativelanguage.googleapis.com/v1beta/corpora/my-research-papers-123a456b789c/documents/paper-on-neural-networks-456b789c123d:query?key=[YOUR_API_KEY]" \
  -H "Content-Type: application/json" \
  -d '{
        "query": "What is a convolutional layer?",
        "resultsCount": 3
      }'

`corpora.documents.chunks`

The chunks sub-resource manages chunks of text within a document.

`corpora.documents.chunks.create`

Creates a Chunk.

HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/corpora/{corporaId}/documents/{documentsId}/chunks
Path Parameter:
- parent: string (required). The name of the Document for the chunk.
Request Body: Chunk
Response Body: Chunk

Example curl request:

curl -X POST "https://generativelanguage.googleapis.com/v1beta/corpora/my-corpus-123/documents/the-doc-abc/chunks?key=[YOUR_API_KEY]" \
  -H "Content-Type: application/json" \
  -d '{
        "data": {
          "stringValue": "This is the first paragraph of the document, which will be stored as a chunk."
        }
      }'

`corpora.documents.chunks.batchCreate`

Batch create Chunks.

HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/corpora/{corporaId}/documents/{documentsId}/chunks:batchCreate
Path Parameter:
- parent: string (required). The parent Document.
Request Body: BatchCreateChunksRequest
Response Body: BatchCreateChunksResponse

Example curl request:

curl -X POST "https://generativelanguage.googleapis.com/v1beta/corpora/my-corpus-123/documents/the-doc-abc/chunks:batchCreate?key=[YOUR_API_KEY]" \
  -H "Content-Type: application/json" \
  -d '{
        "requests": [
          {
            "parent": "corpora/my-corpus-123/documents/the-doc-abc",
            "chunk": { "data": { "stringValue": "Chunk number one." } }
          },
          {
            "parent": "corpora/my-corpus-123/documents/the-doc-abc",
            "chunk": { "data": { "stringValue": "Chunk number two." } }
          }
        ]
      }'

`corpora.documents.chunks.get`

Gets information about a specific Chunk.

HTTP Request: GET https://generativelanguage.googleapis.com/v1beta/corpora/{corporaId}/documents/{documentsId}/chunks/{chunksId}
Path Parameter:
- name: string (required). The name of the Chunk.
Response Body: Chunk

Example curl request:

curl "https://generativelanguage.googleapis.com/v1beta/corpora/my-corpus-123/documents/the-doc-abc/chunks/some-chunk-id?key=[YOUR_API_KEY]"

`corpora.documents.chunks.patch`

Updates a Chunk.

HTTP Request: PATCH https://generativelanguage.googleapis.com/v1beta/corpora/{corporaId}/documents/{documentsId}/chunks/{chunksId}
Path Parameter:
- name: string (required). The Chunk resource name.
Query Parameter:
- updateMask: string (required). List of fields to update.
Request Body: Chunk
Response Body: Chunk

Example curl request:

curl -X PATCH "https://generativelanguage.googleapis.com/v1beta/corpora/my-corpus-123/documents/the-doc-abc/chunks/some-chunk-id?updateMask=data&key=[YOUR_API_KEY]" \
  -H "Content-Type: application/json" \
  -d '{
        "data": { "stringValue": "This is the updated content for the chunk." }
      }'

`corpora.documents.chunks.batchUpdate`

Batch update Chunks.

HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/corpora/{corporaId}/documents/{documentsId}/chunks:batchUpdate
Path Parameter:
- parent: string (required). The parent Document.
Request Body: BatchUpdateChunksRequest
Response Body: BatchUpdateChunksResponse

Example curl request:

curl -X POST "https://generativelanguage.googleapis.com/v1beta/corpora/my-corpus-123/documents/the-doc-abc/chunks:batchUpdate?key=[YOUR_API_KEY]" \
  -H "Content-Type: application/json" \
  -d '{
        "requests": [
          {
            "chunk": {
              "name": "corpora/my-corpus-123/documents/the-doc-abc/chunks/chunk-one-id",
              "data": { "stringValue": "Updated content for chunk one." }
            },
            "updateMask": "data"
          },
          {
            "chunk": {
              "name": "corpora/my-corpus-123/documents/the-doc-abc/chunks/chunk-two-id",
              "data": { "stringValue": "Updated content for chunk two." }
            },
            "updateMask": "data"
          }
        ]
      }'

`corpora.documents.chunks.delete`

Deletes a Chunk.

HTTP Request: DELETE https://generativelanguage.googleapis.com/v1beta/corpora/{corporaId}/documents/{documentsId}/chunks/{chunksId}
Path Parameter:
- name: string (required). The resource name of the Chunk.
Response Body: Empty

Example curl request:

curl -X DELETE "https://generativelanguage.googleapis.com/v1beta/corpora/my-corpus-123/documents/the-doc-abc/chunks/some-chunk-id?key=[YOUR_API_KEY]"

`corpora.documents.chunks.batchDelete`

Batch delete Chunks.

HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/corpora/{corporaId}/documents/{documentsId}/chunks:batchDelete
Path Parameter:
- parent: string (required). The parent Document.
Request Body: BatchDeleteChunksRequest
Response Body: Empty

Example curl request:

curl -X POST "https://generativelanguage.googleapis.com/v1beta/corpora/my-corpus-123/documents/the-doc-abc/chunks:batchDelete?key=[YOUR_API_KEY]" \
  -H "Content-Type: application/json" \
  -d '{
        "requests": [
          { "name": "corpora/my-corpus-123/documents/the-doc-abc/chunks/chunk-one-id" },
          { "name": "corpora/my-corpus-123/documents/the-doc-abc/chunks/chunk-two-id" }
        ]
      }'

`corpora.documents.chunks.list`

Lists all Chunks in a Document.

HTTP Request: GET https://generativelanguage.googleapis.com/v1beta/corpora/{corporaId}/documents/{documentsId}/chunks
Path Parameter:
- parent: string (required). The Document name.
Query Parameters:
- pageSize: integer. The maximum number of Chunks to return.
- pageToken: string. A page token from a previous call.
Response Body: ListChunksResponse

Example curl request:

curl "https://generativelanguage.googleapis.com/v1beta/corpora/my-corpus-123/documents/the-doc-abc/chunks?pageSize=50&key=[YOUR_API_KEY]"

0wwafa/genai_v1beta.md

Generative Language API Documentation

Resources

batches

batches.list

batches.get

batches.delete

batches.cancel

models

models.generateContent

models.generateAnswer

models.streamGenerateContent

models.embedContent

models.batchEmbedContents

models.countTokens

models.get

models.list

models.generateText

models.embedText

models.batchEmbedText

models.countTextTokens

tunedModels

tunedModels.create

tunedModels.get

tunedModels.list

tunedModels.patch

tunedModels.delete

tunedModels.transferOwnership

tunedModels.generateContent

files

files.upload

files.list

files.get

files.delete

corpora

corpora.create

corpora.get

corpora.patch

corpora.delete

corpora.list

corpora.query

corpora.documents

corpora.documents.create

corpora.documents.get

corpora.documents.patch

corpora.documents.delete

corpora.documents.list

corpora.documents.query

corpora.documents.chunks

corpora.documents.chunks.create

corpora.documents.chunks.batchCreate

corpora.documents.chunks.get

corpora.documents.chunks.patch

corpora.documents.chunks.batchUpdate

corpora.documents.chunks.delete

corpora.documents.chunks.batchDelete

corpora.documents.chunks.list

`batches`

`batches.list`

`batches.get`

`batches.delete`

`batches.cancel`

`models`

`models.generateContent`

`models.generateAnswer`

`models.streamGenerateContent`

`models.embedContent`

`models.batchEmbedContents`

`models.countTokens`

`models.get`

`models.list`

`models.generateText`

`models.embedText`

`models.batchEmbedText`

`models.countTextTokens`

`tunedModels`

`tunedModels.create`

`tunedModels.get`

`tunedModels.list`

`tunedModels.patch`

`tunedModels.delete`

`tunedModels.transferOwnership`

`tunedModels.generateContent`

`files`

`files.upload`

`files.list`

`files.get`

`files.delete`

`corpora`

`corpora.create`

`corpora.get`

`corpora.patch`

`corpora.delete`

`corpora.list`

`corpora.query`

`corpora.documents`

`corpora.documents.create`

`corpora.documents.get`

`corpora.documents.patch`

`corpora.documents.delete`

`corpora.documents.list`

`corpora.documents.query`

`corpora.documents.chunks`

`corpora.documents.chunks.create`

`corpora.documents.chunks.batchCreate`

`corpora.documents.chunks.get`

`corpora.documents.chunks.patch`

`corpora.documents.chunks.batchUpdate`

`corpora.documents.chunks.delete`

`corpora.documents.chunks.batchDelete`

`corpora.documents.chunks.list`