openai-data - Pinkfish - AI Agents & Workflows for Getting Work Done

Server path: /openai-data | Type: Application | PCID required: Yes

Tools

Tool	Description
`openai_data_add_upload_part`	Adds a Part to an Upload object. A Part represents a chunk of bytes from the file you are trying to upload. Each Part can be at most 64 MB, and you can add Parts until you hit the Upload maximum of 8 GB. It is possible to add multiple Parts in parallel. You can decide the intended order of the Parts when you complete the Upload.
`openai_data_cancel_batch`	Cancels an in-progress batch. The batch will be in status `cancelling` for up to 10 minutes, before changing to `cancelled`, where it will have partial results (if any) available in the output file.
`openai_data_cancel_eval_run`	Cancel an ongoing evaluation run.
`openai_data_cancel_fine_tuning_job`	Immediately cancel a fine-tune job.
`openai_data_cancel_upload`	Cancels the Upload. No Parts may be added after an Upload is cancelled.
`openai_data_cancel_vector_store_file_batch`	Cancel a vector store file batch. This attempts to cancel the processing of files in this batch as soon as possible.
`openai_data_complete_upload`	Completes the Upload. Within the returned Upload object, there is a nested File object that is ready to use in the rest of the platform. You can specify the order of the Parts by passing in an ordered list of the Part IDs. The number of bytes uploaded upon completion must match the number of bytes initially specified when creating the Upload object. No Parts may be added after an Upload is completed.
`openai_data_create_batch`	Creates and executes a batch from an uploaded file of requests
`openai_data_create_eval`	Create the structure of an evaluation that can be used to test a model’s performance. An evaluation is a set of testing criteria and a datasource. After creating an evaluation, you can run it on different models and model parameters. We support several types of graders and datasources. For more information, see the Evals guide.
`openai_data_create_eval_run`	Create a new evaluation run. This is the endpoint that will kick off grading.
`openai_data_create_file`	Upload a file that can be used across various endpoints. Individual files can be up to 512 MB, and the size of all files uploaded by one organization can be up to 100 GB. The Assistants API supports files up to 2 million tokens and of specific file types. See the Assistants Tools guide for details. The Fine-tuning API only supports `.jsonl` files. The input also has certain required formats for fine-tuning chat or completions models. The Batch API only supports `.jsonl` files up to 200 MB in size. The input also has a specific required format. Please contact us if you need to increase these storage limits.
`openai_data_create_fine_tuning_checkpoint_permission`	NOTE: Calling this endpoint requires an admin API key. This enables organization owners to share fine-tuned models with other projects in their organization.
`openai_data_create_fine_tuning_job`	Creates a fine-tuning job which begins the process of creating a new model from a given dataset. Response includes details of the enqueued job including job status and the name of the fine-tuned models once complete. Learn more about fine-tuning
`openai_data_create_upload`	Creates an intermediate Upload object that you can add Parts to. Currently, an Upload can accept at most 8 GB in total and expires after an hour after you create it. Once you complete the Upload, we will create a File object that contains all the parts you uploaded. This File is usable in the rest of our platform as a regular File object. For certain `purpose` values, the correct `mime_type` must be specified. Please refer to documentation for the supported MIME types for your use case. For guidance on the proper filename extensions for each purpose, please follow the documentation on creating a File.
`openai_data_create_vector_store`	Create a vector store.
`openai_data_create_vector_store_file`	Create a vector store file by attaching a File to a vector store.
`openai_data_create_vector_store_file_batch`	Create a vector store file batch.
`openai_data_delete_eval`	Delete an evaluation.
`openai_data_delete_eval_run`	Delete an eval run.
`openai_data_delete_file`	Delete a file.
`openai_data_delete_fine_tuning_checkpoint_permission`	NOTE: This endpoint requires an admin API key. Organization owners can use this endpoint to delete a permission for a fine-tuned model checkpoint.
`openai_data_delete_vector_store`	Delete a vector store.
`openai_data_delete_vector_store_file`	Delete a vector store file. This will remove the file from the vector store but the file itself will not be deleted. To delete the file, use the delete file endpoint.
`openai_data_download_file`	Returns the contents of the specified file.
`openai_data_get_eval`	Get an evaluation by ID.
`openai_data_get_eval_run`	Get an evaluation run by ID.
`openai_data_get_eval_run_output_item`	Get an evaluation run output item by ID.
`openai_data_get_eval_run_output_items`	Get a list of output items for an evaluation run.
`openai_data_get_eval_runs`	Get a list of runs for an evaluation.
`openai_data_get_vector_store`	Retrieves a vector store.
`openai_data_get_vector_store_file`	Retrieves a vector store file.
`openai_data_get_vector_store_file_batch`	Retrieves a vector store file batch.
`openai_data_list_batches`	List your organization’s batches.
`openai_data_list_evals`	List evaluations for a project.
`openai_data_list_files`	Returns a list of files.
`openai_data_list_files_in_vector_store_batch`	Returns a list of vector store files in a batch.
`openai_data_list_fine_tuning_checkpoint_permissions`	NOTE: This endpoint requires an admin API key. Organization owners can use this endpoint to view all permissions for a fine-tuned model checkpoint.
`openai_data_list_fine_tuning_events`	Get status updates for a fine-tuning job.
`openai_data_list_fine_tuning_job_checkpoints`	List checkpoints for a fine-tuning job.
`openai_data_list_paginated_fine_tuning_jobs`	List your organization’s fine-tuning jobs
`openai_data_list_vector_store_files`	Returns a list of vector store files.
`openai_data_list_vector_stores`	Returns a list of vector stores.
`openai_data_modify_vector_store`	Modifies a vector store.
`openai_data_retrieve_batch`	Retrieves a batch.
`openai_data_retrieve_file`	Returns information about a specific file.
`openai_data_retrieve_fine_tuning_job`	Get info about a fine-tuning job. Learn more about fine-tuning
`openai_data_retrieve_vector_store_file_content`	Retrieve the parsed contents of a vector store file.
`openai_data_search_vector_store`	Search a vector store for relevant chunks based on a query and file attributes filter.
`openai_data_update_eval`	Update certain properties of an evaluation.
`openai_data_update_vector_store_file_attributes`	Update attributes on a vector store file.

openai_data_add_upload_part

Adds a Part to an Upload object. A Part represents a chunk of bytes from the file you are trying to upload. Each Part can be at most 64 MB, and you can add Parts until you hit the Upload maximum of 8 GB. It is possible to add multiple Parts in parallel. You can decide the intended order of the Parts when you complete the Upload. Parameters:

Parameter	Type	Required	Default	Description
`upload_id`	string	Yes	—	The ID of the Upload.
`data`	string	Yes	—	The chunk of bytes for this Part.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "upload_id": {
      "type": "string",
      "description": "The ID of the Upload."
    },
    "data": {
      "type": "string",
      "description": "The chunk of bytes for this Part."
    }
  },
  "required": [
    "PCID",
    "upload_id",
    "data"
  ]
}

openai_data_cancel_batch

Cancels an in-progress batch. The batch will be in status cancelling for up to 10 minutes, before changing to cancelled, where it will have partial results (if any) available in the output file. Parameters:

Parameter	Type	Required	Default	Description
`batch_id`	string	Yes	—	The ID of the batch to cancel.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "batch_id": {
      "type": "string",
      "description": "The ID of the batch to cancel."
    }
  },
  "required": [
    "PCID",
    "batch_id"
  ]
}

openai_data_cancel_eval_run

Cancel an ongoing evaluation run. Parameters:

Parameter	Type	Required	Default	Description
`eval_id`	string	Yes	—	The ID of the evaluation whose run you want to cancel.
`run_id`	string	Yes	—	The ID of the run to cancel.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "eval_id": {
      "type": "string",
      "description": "The ID of the evaluation whose run you want to cancel."
    },
    "run_id": {
      "type": "string",
      "description": "The ID of the run to cancel."
    }
  },
  "required": [
    "PCID",
    "eval_id",
    "run_id"
  ]
}

openai_data_cancel_fine_tuning_job

Immediately cancel a fine-tune job. Parameters:

Parameter	Type	Required	Default	Description
`fine_tuning_job_id`	string	Yes	—	The ID of the fine-tuning job to cancel.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "fine_tuning_job_id": {
      "type": "string",
      "description": "The ID of the fine-tuning job to cancel."
    }
  },
  "required": [
    "PCID",
    "fine_tuning_job_id"
  ]
}

openai_data_cancel_upload

Cancels the Upload. No Parts may be added after an Upload is cancelled. Parameters:

Parameter	Type	Required	Default	Description
`upload_id`	string	Yes	—	The ID of the Upload.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "upload_id": {
      "type": "string",
      "description": "The ID of the Upload."
    }
  },
  "required": [
    "PCID",
    "upload_id"
  ]
}

openai_data_cancel_vector_store_file_batch

Cancel a vector store file batch. This attempts to cancel the processing of files in this batch as soon as possible. Parameters:

Parameter	Type	Required	Default	Description
`vector_store_id`	string	Yes	—	The ID of the vector store that the file batch belongs to.
`batch_id`	string	Yes	—	The ID of the file batch to cancel.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "vector_store_id": {
      "type": "string",
      "description": "The ID of the vector store that the file batch belongs to."
    },
    "batch_id": {
      "type": "string",
      "description": "The ID of the file batch to cancel."
    }
  },
  "required": [
    "PCID",
    "vector_store_id",
    "batch_id"
  ]
}

openai_data_complete_upload

Completes the Upload. Within the returned Upload object, there is a nested File object that is ready to use in the rest of the platform. You can specify the order of the Parts by passing in an ordered list of the Part IDs. The number of bytes uploaded upon completion must match the number of bytes initially specified when creating the Upload object. No Parts may be added after an Upload is completed. Parameters:

Parameter	Type	Required	Default	Description
`upload_id`	string	Yes	—	The ID of the Upload.
`md5`	string	No	—	The optional md5 checksum for the file contents to verify if the bytes uploaded matches what you expect.
`part_ids`	string[]	Yes	—	The ordered list of Part IDs.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "upload_id": {
      "type": "string",
      "description": "The ID of the Upload."
    },
    "md5": {
      "type": "string",
      "description": "The optional md5 checksum for the file contents to verify if the bytes uploaded matches what you expect."
    },
    "part_ids": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "The ordered list of Part IDs."
    }
  },
  "required": [
    "PCID",
    "upload_id",
    "part_ids"
  ]
}

openai_data_create_batch

Creates and executes a batch from an uploaded file of requests Parameters:

Parameter	Type	Required	Default	Description
`completion_window`	string	Yes	—	The time frame within which the batch should be processed. Currently only `24h` is supported.
`endpoint`	string	Yes	—	The endpoint to be used for all requests in the batch. Currently `/v1/responses`, `/v1/chat/completions`, `/v1/embeddings`, and `/v1/completions` are supported. Note that `/v1/embeddings` batches are also restricted to a maximum of 50,000 embedding inputs across all requests in the batch.
`input_file_id`	string	Yes	—	The ID of an uploaded file that contains requests for the new batch. See upload file for how to upload a file. Your input file must be formatted as a JSONL file, and must be uploaded with the purpose `batch`. The file can contain up to 50,000 requests, and can be up to 200 MB in size.
`metadata`	object	No	—	Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "completion_window": {
      "type": "string",
      "description": "The time frame within which the batch should be processed. Currently only `24h` is supported.",
      "enum": [
        "24h"
      ]
    },
    "endpoint": {
      "type": "string",
      "description": "The endpoint to be used for all requests in the batch. Currently `/v1/responses`, `/v1/chat/completions`, `/v1/embeddings`, and `/v1/completions` are supported. Note that `/v1/embeddings` batches are also restricted to a maximum of 50,000 embedding inputs across all requests in the batch.",
      "enum": [
        "/v1/responses",
        "/v1/chat/completions",
        "/v1/embeddings",
        "/v1/completions"
      ]
    },
    "input_file_id": {
      "type": "string",
      "description": "The ID of an uploaded file that contains requests for the new batch.  See [upload file](/docs/api-reference/files/create) for how to upload a file.  Your input file must be formatted as a [JSONL file](/docs/api-reference/batch/request-input), and must be uploaded with the purpose `batch`. The file can contain up to 50,000 requests, and can be up to 200 MB in size."
    },
    "metadata": {
      "type": "object",
      "description": "Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.   Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters."
    }
  },
  "required": [
    "PCID",
    "completion_window",
    "endpoint",
    "input_file_id"
  ]
}

openai_data_create_eval

Create the structure of an evaluation that can be used to test a model’s performance. An evaluation is a set of testing criteria and a datasource. After creating an evaluation, you can run it on different models and model parameters. We support several types of graders and datasources. For more information, see the Evals guide. Parameters:

Parameter	Type	Required	Default	Description
`data_source_config`	object	Yes	—	The configuration for the data source used for the evaluation runs.
`metadata`	object	No	—	Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
`name`	string	No	—	The name of the evaluation.
`testing_criteria`	any[]	Yes	—	A list of graders for all eval runs in this group.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "data_source_config": {
      "type": "object",
      "description": "The configuration for the data source used for the evaluation runs."
    },
    "metadata": {
      "type": "object",
      "description": "Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.   Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters."
    },
    "name": {
      "type": "string",
      "description": "The name of the evaluation."
    },
    "testing_criteria": {
      "type": "array",
      "description": "A list of graders for all eval runs in this group."
    }
  },
  "required": [
    "PCID",
    "data_source_config",
    "testing_criteria"
  ]
}

openai_data_create_eval_run

Create a new evaluation run. This is the endpoint that will kick off grading. Parameters:

Parameter	Type	Required	Default	Description
`eval_id`	string	Yes	—	The ID of the evaluation to create a run for.
`data_source`	object	Yes	—	Details about the run’s data source.
`metadata`	object	No	—	Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
`name`	string	No	—	The name of the run.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "eval_id": {
      "type": "string",
      "description": "The ID of the evaluation to create a run for."
    },
    "data_source": {
      "type": "object",
      "description": "Details about the run's data source."
    },
    "metadata": {
      "type": "object",
      "description": "Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.   Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters."
    },
    "name": {
      "type": "string",
      "description": "The name of the run."
    }
  },
  "required": [
    "PCID",
    "eval_id",
    "data_source"
  ]
}

openai_data_create_file

Upload a file that can be used across various endpoints. Individual files can be up to 512 MB, and the size of all files uploaded by one organization can be up to 100 GB. The Assistants API supports files up to 2 million tokens and of specific file types. See the Assistants Tools guide for details. The Fine-tuning API only supports .jsonl files. The input also has certain required formats for fine-tuning chat or completions models. The Batch API only supports .jsonl files up to 200 MB in size. The input also has a specific required format. Please contact us if you need to increase these storage limits. Parameters:

Parameter	Type	Required	Default	Description
`file`	string	Yes	—	The File object (not file name) to be uploaded.
`purpose`	string	Yes	—	The intended purpose of the uploaded file. One of: - `assistants`: Used in the Assistants API - `batch`: Used in the Batch API - `fine-tune`: Used for fine-tuning - `vision`: Images used for vision fine-tuning - `user_data`: Flexible file type for any purpose - `evals`: Used for eval data sets

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "file": {
      "type": "string",
      "description": "The File object (not file name) to be uploaded."
    },
    "purpose": {
      "type": "string",
      "description": "The intended purpose of the uploaded file. One of: - `assistants`: Used in the Assistants API - `batch`: Used in the Batch API - `fine-tune`: Used for fine-tuning - `vision`: Images used for vision fine-tuning - `user_data`: Flexible file type for any purpose - `evals`: Used for eval data sets",
      "enum": [
        "assistants",
        "batch",
        "fine-tune",
        "vision",
        "user_data",
        "evals"
      ]
    }
  },
  "required": [
    "PCID",
    "file",
    "purpose"
  ]
}

openai_data_create_fine_tuning_checkpoint_permission

NOTE: Calling this endpoint requires an admin API key. This enables organization owners to share fine-tuned models with other projects in their organization. Parameters:

Parameter	Type	Required	Default	Description
`fine_tuned_model_checkpoint`	string	Yes	—	The ID of the fine-tuned model checkpoint to create a permission for.
`project_ids`	string[]	Yes	—	The project identifiers to grant access to.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "fine_tuned_model_checkpoint": {
      "type": "string",
      "description": "The ID of the fine-tuned model checkpoint to create a permission for."
    },
    "project_ids": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "The project identifiers to grant access to."
    }
  },
  "required": [
    "PCID",
    "fine_tuned_model_checkpoint",
    "project_ids"
  ]
}

openai_data_create_fine_tuning_job

Creates a fine-tuning job which begins the process of creating a new model from a given dataset. Response includes details of the enqueued job including job status and the name of the fine-tuned models once complete. Learn more about fine-tuning Parameters:

Parameter	Type	Required	Default	Description
`hyperparameters`	object	No	—	The hyperparameters used for the fine-tuning job. This value is now deprecated in favor of `method`, and should be passed in under the `method` parameter.
`integrations`	object[]	No	—	A list of integrations to enable for your fine-tuning job.
`metadata`	object	No	—	Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
`method`	object	No	—	The method used for fine-tuning.
`model`	object	Yes	—	The name of the model to fine-tune. You can select one of the supported models.
`seed`	integer	null	No	—	The seed controls the reproducibility of the job. Passing in the same seed and job parameters should produce the same results, but may differ in rare cases. If a seed is not specified, one will be generated for you.
`suffix`	string	null	No	—	A string of up to 64 characters that will be added to your fine-tuned model name. For example, a `suffix` of “custom-model-name” would produce a model name like `ft:gpt-4o-mini:openai:custom-model-name:7p4lURel`.
`training_file`	string	Yes	—	The ID of an uploaded file that contains training data. See upload file for how to upload a file. Your dataset must be formatted as a JSONL file. Additionally, you must upload your file with the purpose `fine-tune`. The contents of the file should differ depending on if the model uses the chat, completions format, or if the fine-tuning method uses the preference format. See the fine-tuning guide for more details.
`validation_file`	string	null	No	—	The ID of an uploaded file that contains validation data. If you provide this file, the data is used to generate validation metrics periodically during fine-tuning. These metrics can be viewed in the fine-tuning results file. The same data should not be present in both train and validation files. Your dataset must be formatted as a JSONL file. You must upload your file with the purpose `fine-tune`. See the fine-tuning guide for more details.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "hyperparameters": {
      "type": "object",
      "description": "The hyperparameters used for the fine-tuning job. This value is now deprecated in favor of `method`, and should be passed in under the `method` parameter.",
      "properties": {
        "batch_size": {
          "description": "Number of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance."
        },
        "learning_rate_multiplier": {
          "description": "Scaling factor for the learning rate. A smaller learning rate may be useful to avoid overfitting."
        },
        "n_epochs": {
          "description": "The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset."
        }
      }
    },
    "integrations": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "type": {
            "type": "string",
            "enum": [
              "wandb"
            ],
            "description": "The type of integration to enable. Currently, only \"wandb\" (Weights and Biases) is supported."
          },
          "wandb": {
            "type": "object",
            "description": "The settings for your integration with Weights and Biases. This payload specifies the project that metrics will be sent to. Optionally, you can set an explicit display name for your run, add tags to your run, and set a default entity (team, username, etc) to be associated with your run."
          }
        },
        "required": [
          "type",
          "wandb"
        ]
      },
      "description": "A list of integrations to enable for your fine-tuning job."
    },
    "metadata": {
      "type": "object",
      "description": "Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.   Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters."
    },
    "method": {
      "type": "object",
      "description": "The method used for fine-tuning.",
      "properties": {
        "type": {
          "type": "string",
          "description": "The type of method. Is either `supervised` or `dpo`.",
          "enum": [
            "supervised",
            "dpo"
          ]
        },
        "supervised": {
          "type": "object",
          "description": "Configuration for the supervised fine-tuning method."
        },
        "dpo": {
          "type": "object",
          "description": "Configuration for the DPO fine-tuning method."
        }
      }
    },
    "model": {
      "description": "The name of the model to fine-tune. You can select one of the [supported models](/docs/guides/fine-tuning#which-models-can-be-fine-tuned)."
    },
    "seed": {
      "type": [
        "integer",
        "null"
      ],
      "description": "The seed controls the reproducibility of the job. Passing in the same seed and job parameters should produce the same results, but may differ in rare cases. If a seed is not specified, one will be generated for you."
    },
    "suffix": {
      "type": [
        "string",
        "null"
      ],
      "description": "A string of up to 64 characters that will be added to your fine-tuned model name.  For example, a `suffix` of \"custom-model-name\" would produce a model name like `ft:gpt-4o-mini:openai:custom-model-name:7p4lURel`."
    },
    "training_file": {
      "type": "string",
      "description": "The ID of an uploaded file that contains training data.  See [upload file](/docs/api-reference/files/create) for how to upload a file.  Your dataset must be formatted as a JSONL file. Additionally, you must upload your file with the purpose `fine-tune`.  The contents of the file should differ depending on if the model uses the [chat](/docs/api-reference/fine-tuning/chat-input), [completions](/docs/api-reference/fine-tuning/completions-input) format, or if the fine-tuning method uses the [preference](/docs/api-reference/fine-tuning/preference-input) format.  See the [fine-tuning guide](/docs/guides/fine-tuning) for more details."
    },
    "validation_file": {
      "type": [
        "string",
        "null"
      ],
      "description": "The ID of an uploaded file that contains validation data.  If you provide this file, the data is used to generate validation metrics periodically during fine-tuning. These metrics can be viewed in the fine-tuning results file. The same data should not be present in both train and validation files.  Your dataset must be formatted as a JSONL file. You must upload your file with the purpose `fine-tune`.  See the [fine-tuning guide](/docs/guides/fine-tuning) for more details."
    }
  },
  "required": [
    "PCID",
    "model",
    "training_file"
  ]
}

openai_data_create_upload

Creates an intermediate Upload object that you can add Parts to. Currently, an Upload can accept at most 8 GB in total and expires after an hour after you create it. Once you complete the Upload, we will create a File object that contains all the parts you uploaded. This File is usable in the rest of our platform as a regular File object. For certain purpose values, the correct mime_type must be specified. Please refer to documentation for the supported MIME types for your use case. For guidance on the proper filename extensions for each purpose, please follow the documentation on creating a File. Parameters:

Parameter	Type	Required	Default	Description
`bytes`	integer	Yes	—	The number of bytes in the file you are uploading.
`filename`	string	Yes	—	The name of the file to upload.
`mime_type`	string	Yes	—	The MIME type of the file. This must fall within the supported MIME types for your file purpose. See the supported MIME types for assistants and vision.
`purpose`	string	Yes	—	The intended purpose of the uploaded file. See the documentation on File purposes.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "bytes": {
      "type": "integer",
      "description": "The number of bytes in the file you are uploading."
    },
    "filename": {
      "type": "string",
      "description": "The name of the file to upload."
    },
    "mime_type": {
      "type": "string",
      "description": "The MIME type of the file.  This must fall within the supported MIME types for your file purpose. See the supported MIME types for assistants and vision."
    },
    "purpose": {
      "type": "string",
      "description": "The intended purpose of the uploaded file.  See the [documentation on File purposes](/docs/api-reference/files/create#files-create-purpose).",
      "enum": [
        "assistants",
        "batch",
        "fine-tune",
        "vision"
      ]
    }
  },
  "required": [
    "PCID",
    "bytes",
    "filename",
    "mime_type",
    "purpose"
  ]
}

openai_data_create_vector_store

Create a vector store. Parameters:

Parameter	Type	Required	Default	Description
`chunking_strategy`	object	No	—	The chunking strategy used to chunk the file(s). If not set, will use the `auto` strategy. Only applicable if `file_ids` is non-empty.
`expires_after`	object	No	—	The expiration policy for a vector store.
`file_ids`	string[]	No	—	A list of File IDs that the vector store should use. Useful for tools like `file_search` that can access files.
`metadata`	object	No	—	Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
`name`	string	No	—	The name of the vector store.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "chunking_strategy": {
      "type": "object",
      "description": "The chunking strategy used to chunk the file(s). If not set, will use the `auto` strategy. Only applicable if `file_ids` is non-empty."
    },
    "expires_after": {
      "type": "object",
      "description": "The expiration policy for a vector store.",
      "properties": {
        "anchor": {
          "type": "string",
          "description": "Anchor timestamp after which the expiration policy applies. Supported anchors: `last_active_at`.",
          "enum": [
            "last_active_at"
          ]
        },
        "days": {
          "type": "integer",
          "description": "The number of days after the anchor time that the vector store will expire."
        }
      },
      "required": [
        "anchor",
        "days"
      ]
    },
    "file_ids": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "A list of [File](/docs/api-reference/files) IDs that the vector store should use. Useful for tools like `file_search` that can access files."
    },
    "metadata": {
      "type": "object",
      "description": "Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.   Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters."
    },
    "name": {
      "type": "string",
      "description": "The name of the vector store."
    }
  },
  "required": [
    "PCID"
  ]
}

openai_data_create_vector_store_file

Create a vector store file by attaching a File to a vector store. Parameters:

Parameter	Type	Required	Default	Description
`vector_store_id`	string	Yes	—	The ID of the vector store for which to create a File.
`attributes`	object	No	—	Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.
`chunking_strategy`	object	No	—	The chunking strategy used to chunk the file(s). If not set, will use the `auto` strategy.
`file_id`	string	Yes	—	A File ID that the vector store should use. Useful for tools like `file_search` that can access files.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "vector_store_id": {
      "type": "string",
      "description": "The ID of the vector store for which to create a File."
    },
    "attributes": {
      "type": "object",
      "description": "Set of 16 key-value pairs that can be attached to an object. This can be  useful for storing additional information about the object in a structured  format, and querying for objects via API or the dashboard. Keys are strings  with a maximum length of 64 characters. Values are strings with a maximum  length of 512 characters, booleans, or numbers."
    },
    "chunking_strategy": {
      "type": "object",
      "description": "The chunking strategy used to chunk the file(s). If not set, will use the `auto` strategy."
    },
    "file_id": {
      "type": "string",
      "description": "A [File](/docs/api-reference/files) ID that the vector store should use. Useful for tools like `file_search` that can access files."
    }
  },
  "required": [
    "PCID",
    "vector_store_id",
    "file_id"
  ]
}

openai_data_create_vector_store_file_batch

Create a vector store file batch. Parameters:

Parameter	Type	Required	Default	Description
`vector_store_id`	string	Yes	—	The ID of the vector store for which to create a File Batch.
`attributes`	object	No	—	Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.
`chunking_strategy`	object	No	—	The chunking strategy used to chunk the file(s). If not set, will use the `auto` strategy.
`file_ids`	string[]	Yes	—	A list of File IDs that the vector store should use. Useful for tools like `file_search` that can access files.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "vector_store_id": {
      "type": "string",
      "description": "The ID of the vector store for which to create a File Batch."
    },
    "attributes": {
      "type": "object",
      "description": "Set of 16 key-value pairs that can be attached to an object. This can be  useful for storing additional information about the object in a structured  format, and querying for objects via API or the dashboard. Keys are strings  with a maximum length of 64 characters. Values are strings with a maximum  length of 512 characters, booleans, or numbers."
    },
    "chunking_strategy": {
      "type": "object",
      "description": "The chunking strategy used to chunk the file(s). If not set, will use the `auto` strategy."
    },
    "file_ids": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "A list of [File](/docs/api-reference/files) IDs that the vector store should use. Useful for tools like `file_search` that can access files."
    }
  },
  "required": [
    "PCID",
    "vector_store_id",
    "file_ids"
  ]
}

openai_data_delete_eval

Delete an evaluation. Parameters:

Parameter	Type	Required	Default	Description
`eval_id`	string	Yes	—	The ID of the evaluation to delete.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "eval_id": {
      "type": "string",
      "description": "The ID of the evaluation to delete."
    }
  },
  "required": [
    "PCID",
    "eval_id"
  ]
}

openai_data_delete_eval_run

Delete an eval run. Parameters:

Parameter	Type	Required	Default	Description
`eval_id`	string	Yes	—	The ID of the evaluation to delete the run from.
`run_id`	string	Yes	—	The ID of the run to delete.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "eval_id": {
      "type": "string",
      "description": "The ID of the evaluation to delete the run from."
    },
    "run_id": {
      "type": "string",
      "description": "The ID of the run to delete."
    }
  },
  "required": [
    "PCID",
    "eval_id",
    "run_id"
  ]
}

openai_data_delete_file

Delete a file. Parameters:

Parameter	Type	Required	Default	Description
`file_id`	string	Yes	—	The ID of the file to use for this request.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "file_id": {
      "type": "string",
      "description": "The ID of the file to use for this request."
    }
  },
  "required": [
    "PCID",
    "file_id"
  ]
}

openai_data_delete_fine_tuning_checkpoint_permission

NOTE: This endpoint requires an admin API key. Organization owners can use this endpoint to delete a permission for a fine-tuned model checkpoint. Parameters:

Parameter	Type	Required	Default	Description
`fine_tuned_model_checkpoint`	string	Yes	—	The ID of the fine-tuned model checkpoint to delete a permission for.
`permission_id`	string	Yes	—	The ID of the fine-tuned model checkpoint permission to delete.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "fine_tuned_model_checkpoint": {
      "type": "string",
      "description": "The ID of the fine-tuned model checkpoint to delete a permission for."
    },
    "permission_id": {
      "type": "string",
      "description": "The ID of the fine-tuned model checkpoint permission to delete."
    }
  },
  "required": [
    "PCID",
    "fine_tuned_model_checkpoint",
    "permission_id"
  ]
}

openai_data_delete_vector_store

Delete a vector store. Parameters:

Parameter	Type	Required	Default	Description
`vector_store_id`	string	Yes	—	The ID of the vector store to delete.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "vector_store_id": {
      "type": "string",
      "description": "The ID of the vector store to delete."
    }
  },
  "required": [
    "PCID",
    "vector_store_id"
  ]
}

openai_data_delete_vector_store_file

Delete a vector store file. This will remove the file from the vector store but the file itself will not be deleted. To delete the file, use the delete file endpoint. Parameters:

Parameter	Type	Required	Default	Description
`vector_store_id`	string	Yes	—	The ID of the vector store that the file belongs to.
`file_id`	string	Yes	—	The ID of the file to delete.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "vector_store_id": {
      "type": "string",
      "description": "The ID of the vector store that the file belongs to."
    },
    "file_id": {
      "type": "string",
      "description": "The ID of the file to delete."
    }
  },
  "required": [
    "PCID",
    "vector_store_id",
    "file_id"
  ]
}

openai_data_download_file

Returns the contents of the specified file. Parameters:

Parameter	Type	Required	Default	Description
`file_id`	string	Yes	—	The ID of the file to use for this request.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "file_id": {
      "type": "string",
      "description": "The ID of the file to use for this request."
    }
  },
  "required": [
    "PCID",
    "file_id"
  ]
}

openai_data_get_eval

Get an evaluation by ID. Parameters:

Parameter	Type	Required	Default	Description
`eval_id`	string	Yes	—	The ID of the evaluation to retrieve.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "eval_id": {
      "type": "string",
      "description": "The ID of the evaluation to retrieve."
    }
  },
  "required": [
    "PCID",
    "eval_id"
  ]
}

openai_data_get_eval_run

Get an evaluation run by ID. Parameters:

Parameter	Type	Required	Default	Description
`eval_id`	string	Yes	—	The ID of the evaluation to retrieve runs for.
`run_id`	string	Yes	—	The ID of the run to retrieve.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "eval_id": {
      "type": "string",
      "description": "The ID of the evaluation to retrieve runs for."
    },
    "run_id": {
      "type": "string",
      "description": "The ID of the run to retrieve."
    }
  },
  "required": [
    "PCID",
    "eval_id",
    "run_id"
  ]
}

openai_data_get_eval_run_output_item

Get an evaluation run output item by ID. Parameters:

Parameter	Type	Required	Default	Description
`eval_id`	string	Yes	—	The ID of the evaluation to retrieve runs for.
`run_id`	string	Yes	—	The ID of the run to retrieve.
`output_item_id`	string	Yes	—	The ID of the output item to retrieve.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "eval_id": {
      "type": "string",
      "description": "The ID of the evaluation to retrieve runs for."
    },
    "run_id": {
      "type": "string",
      "description": "The ID of the run to retrieve."
    },
    "output_item_id": {
      "type": "string",
      "description": "The ID of the output item to retrieve."
    }
  },
  "required": [
    "PCID",
    "eval_id",
    "run_id",
    "output_item_id"
  ]
}

openai_data_get_eval_run_output_items

Get a list of output items for an evaluation run. Parameters:

Parameter	Type	Required	Default	Description
`eval_id`	string	Yes	—	The ID of the evaluation to retrieve runs for.
`run_id`	string	Yes	—	The ID of the run to retrieve output items for.
`after`	string	No	—	Identifier for the last output item from the previous pagination request.
`limit`	integer	No	—	Number of output items to retrieve.
`status`	string	No	—	Filter output items by status. Use `failed` to filter by failed output items or `pass` to filter by passed output items.
`order`	string	No	—	Sort order for output items by timestamp. Use `asc` for ascending order or `desc` for descending order. Defaults to `asc`.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "eval_id": {
      "type": "string",
      "description": "The ID of the evaluation to retrieve runs for."
    },
    "run_id": {
      "type": "string",
      "description": "The ID of the run to retrieve output items for."
    },
    "after": {
      "type": "string",
      "description": "Identifier for the last output item from the previous pagination request."
    },
    "limit": {
      "type": "integer",
      "description": "Number of output items to retrieve."
    },
    "status": {
      "type": "string",
      "description": "Filter output items by status. Use `failed` to filter by failed output items or `pass` to filter by passed output items.",
      "enum": [
        "fail",
        "pass"
      ]
    },
    "order": {
      "type": "string",
      "description": "Sort order for output items by timestamp. Use `asc` for ascending order or `desc` for descending order. Defaults to `asc`.",
      "enum": [
        "asc",
        "desc"
      ]
    }
  },
  "required": [
    "PCID",
    "eval_id",
    "run_id"
  ]
}

openai_data_get_eval_runs

Get a list of runs for an evaluation. Parameters:

Parameter	Type	Required	Default	Description
`eval_id`	string	Yes	—	The ID of the evaluation to retrieve runs for.
`after`	string	No	—	Identifier for the last run from the previous pagination request.
`limit`	integer	No	—	Number of runs to retrieve.
`order`	string	No	—	Sort order for runs by timestamp. Use `asc` for ascending order or `desc` for descending order. Defaults to `asc`.
`status`	string	No	—	Filter runs by status. One of `queued` \| `in_progress` \| `failed` \| `completed` \| `canceled`.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "eval_id": {
      "type": "string",
      "description": "The ID of the evaluation to retrieve runs for."
    },
    "after": {
      "type": "string",
      "description": "Identifier for the last run from the previous pagination request."
    },
    "limit": {
      "type": "integer",
      "description": "Number of runs to retrieve."
    },
    "order": {
      "type": "string",
      "description": "Sort order for runs by timestamp. Use `asc` for ascending order or `desc` for descending order. Defaults to `asc`.",
      "enum": [
        "asc",
        "desc"
      ]
    },
    "status": {
      "type": "string",
      "description": "Filter runs by status. One of `queued` | `in_progress` | `failed` | `completed` | `canceled`.",
      "enum": [
        "queued",
        "in_progress",
        "completed",
        "canceled",
        "failed"
      ]
    }
  },
  "required": [
    "PCID",
    "eval_id"
  ]
}

openai_data_get_vector_store

Retrieves a vector store. Parameters:

Parameter	Type	Required	Default	Description
`vector_store_id`	string	Yes	—	The ID of the vector store to retrieve.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "vector_store_id": {
      "type": "string",
      "description": "The ID of the vector store to retrieve."
    }
  },
  "required": [
    "PCID",
    "vector_store_id"
  ]
}

openai_data_get_vector_store_file

Retrieves a vector store file. Parameters:

Parameter	Type	Required	Default	Description
`vector_store_id`	string	Yes	—	The ID of the vector store that the file belongs to.
`file_id`	string	Yes	—	The ID of the file being retrieved.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "vector_store_id": {
      "type": "string",
      "description": "The ID of the vector store that the file belongs to."
    },
    "file_id": {
      "type": "string",
      "description": "The ID of the file being retrieved."
    }
  },
  "required": [
    "PCID",
    "vector_store_id",
    "file_id"
  ]
}

openai_data_get_vector_store_file_batch

Retrieves a vector store file batch. Parameters:

Parameter	Type	Required	Default	Description
`vector_store_id`	string	Yes	—	The ID of the vector store that the file batch belongs to.
`batch_id`	string	Yes	—	The ID of the file batch being retrieved.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "vector_store_id": {
      "type": "string",
      "description": "The ID of the vector store that the file batch belongs to."
    },
    "batch_id": {
      "type": "string",
      "description": "The ID of the file batch being retrieved."
    }
  },
  "required": [
    "PCID",
    "vector_store_id",
    "batch_id"
  ]
}

openai_data_list_batches

List your organization’s batches. Parameters:

Parameter	Type	Required	Default	Description
`after`	string	No	—	A cursor for use in pagination. `after` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.
`limit`	integer	No	—	A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "after": {
      "type": "string",
      "description": "A cursor for use in pagination. `after` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list."
    },
    "limit": {
      "type": "integer",
      "description": "A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20."
    }
  },
  "required": [
    "PCID"
  ]
}

openai_data_list_evals

List evaluations for a project. Parameters:

Parameter	Type	Required	Default	Description
`after`	string	No	—	Identifier for the last eval from the previous pagination request.
`limit`	integer	No	—	Number of evals to retrieve.
`order`	string	No	—	Sort order for evals by timestamp. Use `asc` for ascending order or `desc` for descending order.
`order_by`	string	No	—	Evals can be ordered by creation time or last updated time. Use `created_at` for creation time or `updated_at` for last updated time.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "after": {
      "type": "string",
      "description": "Identifier for the last eval from the previous pagination request."
    },
    "limit": {
      "type": "integer",
      "description": "Number of evals to retrieve."
    },
    "order": {
      "type": "string",
      "description": "Sort order for evals by timestamp. Use `asc` for ascending order or `desc` for descending order.",
      "enum": [
        "asc",
        "desc"
      ]
    },
    "order_by": {
      "type": "string",
      "description": "Evals can be ordered by creation time or last updated time. Use `created_at` for creation time or `updated_at` for last updated time.",
      "enum": [
        "created_at",
        "updated_at"
      ]
    }
  },
  "required": [
    "PCID"
  ]
}

openai_data_list_files

Returns a list of files. Parameters:

Parameter	Type	Required	Default	Description
`purpose`	string	No	—	Only return files with the given purpose.
`limit`	integer	No	—	A limit on the number of objects to be returned. Limit can range between 1 and 10,000, and the default is 10,000.
`order`	string	No	—	Sort order by the `created_at` timestamp of the objects. `asc` for ascending order and `desc` for descending order.
`after`	string	No	—	A cursor for use in pagination. `after` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "purpose": {
      "type": "string",
      "description": "Only return files with the given purpose."
    },
    "limit": {
      "type": "integer",
      "description": "A limit on the number of objects to be returned. Limit can range between 1 and 10,000, and the default is 10,000."
    },
    "order": {
      "type": "string",
      "description": "Sort order by the `created_at` timestamp of the objects. `asc` for ascending order and `desc` for descending order.",
      "enum": [
        "asc",
        "desc"
      ]
    },
    "after": {
      "type": "string",
      "description": "A cursor for use in pagination. `after` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list."
    }
  },
  "required": [
    "PCID"
  ]
}

openai_data_list_files_in_vector_store_batch

Returns a list of vector store files in a batch. Parameters:

Parameter	Type	Required	Default	Description
`vector_store_id`	string	Yes	—	The ID of the vector store that the files belong to.
`batch_id`	string	Yes	—	The ID of the file batch that the files belong to.
`limit`	integer	No	—	A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.
`order`	string	No	—	Sort order by the `created_at` timestamp of the objects. `asc` for ascending order and `desc` for descending order.
`after`	string	No	—	A cursor for use in pagination. `after` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.
`before`	string	No	—	A cursor for use in pagination. `before` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, starting with obj_foo, your subsequent call can include before=obj_foo in order to fetch the previous page of the list.
`filter`	string	No	—	Filter by file status. One of `in_progress`, `completed`, `failed`, `cancelled`.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "vector_store_id": {
      "type": "string",
      "description": "The ID of the vector store that the files belong to."
    },
    "batch_id": {
      "type": "string",
      "description": "The ID of the file batch that the files belong to."
    },
    "limit": {
      "type": "integer",
      "description": "A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20."
    },
    "order": {
      "type": "string",
      "description": "Sort order by the `created_at` timestamp of the objects. `asc` for ascending order and `desc` for descending order.",
      "enum": [
        "asc",
        "desc"
      ]
    },
    "after": {
      "type": "string",
      "description": "A cursor for use in pagination. `after` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list."
    },
    "before": {
      "type": "string",
      "description": "A cursor for use in pagination. `before` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, starting with obj_foo, your subsequent call can include before=obj_foo in order to fetch the previous page of the list."
    },
    "filter": {
      "type": "string",
      "description": "Filter by file status. One of `in_progress`, `completed`, `failed`, `cancelled`.",
      "enum": [
        "in_progress",
        "completed",
        "failed",
        "cancelled"
      ]
    }
  },
  "required": [
    "PCID",
    "vector_store_id",
    "batch_id"
  ]
}

openai_data_list_fine_tuning_checkpoint_permissions

NOTE: This endpoint requires an admin API key. Organization owners can use this endpoint to view all permissions for a fine-tuned model checkpoint. Parameters:

Parameter	Type	Required	Default	Description
`fine_tuned_model_checkpoint`	string	Yes	—	The ID of the fine-tuned model checkpoint to get permissions for.
`project_id`	string	No	—	The ID of the project to get permissions for.
`after`	string	No	—	Identifier for the last permission ID from the previous pagination request.
`limit`	integer	No	—	Number of permissions to retrieve.
`order`	string	No	—	The order in which to retrieve permissions.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "fine_tuned_model_checkpoint": {
      "type": "string",
      "description": "The ID of the fine-tuned model checkpoint to get permissions for."
    },
    "project_id": {
      "type": "string",
      "description": "The ID of the project to get permissions for."
    },
    "after": {
      "type": "string",
      "description": "Identifier for the last permission ID from the previous pagination request."
    },
    "limit": {
      "type": "integer",
      "description": "Number of permissions to retrieve."
    },
    "order": {
      "type": "string",
      "description": "The order in which to retrieve permissions.",
      "enum": [
        "ascending",
        "descending"
      ]
    }
  },
  "required": [
    "PCID",
    "fine_tuned_model_checkpoint"
  ]
}

openai_data_list_fine_tuning_events

Get status updates for a fine-tuning job. Parameters:

Parameter	Type	Required	Default	Description
`fine_tuning_job_id`	string	Yes	—	The ID of the fine-tuning job to get events for.
`after`	string	No	—	Identifier for the last event from the previous pagination request.
`limit`	integer	No	—	Number of events to retrieve.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "fine_tuning_job_id": {
      "type": "string",
      "description": "The ID of the fine-tuning job to get events for."
    },
    "after": {
      "type": "string",
      "description": "Identifier for the last event from the previous pagination request."
    },
    "limit": {
      "type": "integer",
      "description": "Number of events to retrieve."
    }
  },
  "required": [
    "PCID",
    "fine_tuning_job_id"
  ]
}

openai_data_list_fine_tuning_job_checkpoints

List checkpoints for a fine-tuning job. Parameters:

Parameter	Type	Required	Default	Description
`fine_tuning_job_id`	string	Yes	—	The ID of the fine-tuning job to get checkpoints for.
`after`	string	No	—	Identifier for the last checkpoint ID from the previous pagination request.
`limit`	integer	No	—	Number of checkpoints to retrieve.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "fine_tuning_job_id": {
      "type": "string",
      "description": "The ID of the fine-tuning job to get checkpoints for."
    },
    "after": {
      "type": "string",
      "description": "Identifier for the last checkpoint ID from the previous pagination request."
    },
    "limit": {
      "type": "integer",
      "description": "Number of checkpoints to retrieve."
    }
  },
  "required": [
    "PCID",
    "fine_tuning_job_id"
  ]
}

openai_data_list_paginated_fine_tuning_jobs

List your organization’s fine-tuning jobs Parameters:

Parameter	Type	Required	Default	Description
`after`	string	No	—	Identifier for the last job from the previous pagination request.
`limit`	integer	No	—	Number of fine-tuning jobs to retrieve.
`metadata`	object	No	—	Optional metadata filter. To filter, use the syntax `metadata[k]=v`. Alternatively, set `metadata=null` to indicate no metadata.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "after": {
      "type": "string",
      "description": "Identifier for the last job from the previous pagination request."
    },
    "limit": {
      "type": "integer",
      "description": "Number of fine-tuning jobs to retrieve."
    },
    "metadata": {
      "type": "object",
      "description": "Optional metadata filter. To filter, use the syntax `metadata[k]=v`. Alternatively, set `metadata=null` to indicate no metadata."
    }
  },
  "required": [
    "PCID"
  ]
}

openai_data_list_vector_store_files

Returns a list of vector store files. Parameters:

Parameter	Type	Required	Default	Description
`vector_store_id`	string	Yes	—	The ID of the vector store that the files belong to.
`limit`	integer	No	—	A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.
`order`	string	No	—	Sort order by the `created_at` timestamp of the objects. `asc` for ascending order and `desc` for descending order.
`after`	string	No	—	A cursor for use in pagination. `after` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.
`before`	string	No	—	A cursor for use in pagination. `before` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, starting with obj_foo, your subsequent call can include before=obj_foo in order to fetch the previous page of the list.
`filter`	string	No	—	Filter by file status. One of `in_progress`, `completed`, `failed`, `cancelled`.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "vector_store_id": {
      "type": "string",
      "description": "The ID of the vector store that the files belong to."
    },
    "limit": {
      "type": "integer",
      "description": "A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20."
    },
    "order": {
      "type": "string",
      "description": "Sort order by the `created_at` timestamp of the objects. `asc` for ascending order and `desc` for descending order.",
      "enum": [
        "asc",
        "desc"
      ]
    },
    "after": {
      "type": "string",
      "description": "A cursor for use in pagination. `after` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list."
    },
    "before": {
      "type": "string",
      "description": "A cursor for use in pagination. `before` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, starting with obj_foo, your subsequent call can include before=obj_foo in order to fetch the previous page of the list."
    },
    "filter": {
      "type": "string",
      "description": "Filter by file status. One of `in_progress`, `completed`, `failed`, `cancelled`.",
      "enum": [
        "in_progress",
        "completed",
        "failed",
        "cancelled"
      ]
    }
  },
  "required": [
    "PCID",
    "vector_store_id"
  ]
}

openai_data_list_vector_stores

Returns a list of vector stores. Parameters:

Parameter	Type	Required	Default	Description
`limit`	integer	No	—	A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.
`order`	string	No	—	Sort order by the `created_at` timestamp of the objects. `asc` for ascending order and `desc` for descending order.
`after`	string	No	—	A cursor for use in pagination. `after` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.
`before`	string	No	—	A cursor for use in pagination. `before` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, starting with obj_foo, your subsequent call can include before=obj_foo in order to fetch the previous page of the list.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "limit": {
      "type": "integer",
      "description": "A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20."
    },
    "order": {
      "type": "string",
      "description": "Sort order by the `created_at` timestamp of the objects. `asc` for ascending order and `desc` for descending order.",
      "enum": [
        "asc",
        "desc"
      ]
    },
    "after": {
      "type": "string",
      "description": "A cursor for use in pagination. `after` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list."
    },
    "before": {
      "type": "string",
      "description": "A cursor for use in pagination. `before` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, starting with obj_foo, your subsequent call can include before=obj_foo in order to fetch the previous page of the list."
    }
  },
  "required": [
    "PCID"
  ]
}

openai_data_modify_vector_store

Modifies a vector store. Parameters:

Parameter	Type	Required	Default	Description
`vector_store_id`	string	Yes	—	The ID of the vector store to modify.
`expires_after`	object	No	—	Expires After
`metadata`	object	No	—	Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
`name`	string	null	No	—	The name of the vector store.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "vector_store_id": {
      "type": "string",
      "description": "The ID of the vector store to modify."
    },
    "expires_after": {
      "description": "Expires After"
    },
    "metadata": {
      "type": "object",
      "description": "Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.   Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters."
    },
    "name": {
      "type": [
        "string",
        "null"
      ],
      "description": "The name of the vector store."
    }
  },
  "required": [
    "PCID",
    "vector_store_id"
  ]
}

openai_data_retrieve_batch

Retrieves a batch. Parameters:

Parameter	Type	Required	Default	Description
`batch_id`	string	Yes	—	The ID of the batch to retrieve.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "batch_id": {
      "type": "string",
      "description": "The ID of the batch to retrieve."
    }
  },
  "required": [
    "PCID",
    "batch_id"
  ]
}

openai_data_retrieve_file

Returns information about a specific file. Parameters:

Parameter	Type	Required	Default	Description
`file_id`	string	Yes	—	The ID of the file to use for this request.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "file_id": {
      "type": "string",
      "description": "The ID of the file to use for this request."
    }
  },
  "required": [
    "PCID",
    "file_id"
  ]
}

openai_data_retrieve_fine_tuning_job

Get info about a fine-tuning job. Learn more about fine-tuning Parameters:

Parameter	Type	Required	Default	Description
`fine_tuning_job_id`	string	Yes	—	The ID of the fine-tuning job.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "fine_tuning_job_id": {
      "type": "string",
      "description": "The ID of the fine-tuning job."
    }
  },
  "required": [
    "PCID",
    "fine_tuning_job_id"
  ]
}

openai_data_retrieve_vector_store_file_content

Retrieve the parsed contents of a vector store file. Parameters:

Parameter	Type	Required	Default	Description
`vector_store_id`	string	Yes	—	The ID of the vector store.
`file_id`	string	Yes	—	The ID of the file within the vector store.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "vector_store_id": {
      "type": "string",
      "description": "The ID of the vector store."
    },
    "file_id": {
      "type": "string",
      "description": "The ID of the file within the vector store."
    }
  },
  "required": [
    "PCID",
    "vector_store_id",
    "file_id"
  ]
}

openai_data_search_vector_store

Search a vector store for relevant chunks based on a query and file attributes filter. Parameters:

Parameter	Type	Required	Default	Description
`vector_store_id`	string	Yes	—	The ID of the vector store to search.
`filters`	object	No	—	A filter to apply based on file attributes.
`max_num_results`	integer	No	—	The maximum number of results to return. This number should be between 1 and 50 inclusive.
`query`	string[]	Yes	—	A query string for a search
`ranking_options`	object	No	—	Ranking options for search.
`rewrite_query`	boolean	No	—	Whether to rewrite the natural language query for vector search.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "vector_store_id": {
      "type": "string",
      "description": "The ID of the vector store to search."
    },
    "filters": {
      "description": "A filter to apply based on file attributes."
    },
    "max_num_results": {
      "type": "integer",
      "description": "The maximum number of results to return. This number should be between 1 and 50 inclusive."
    },
    "query": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "A query string for a search"
    },
    "ranking_options": {
      "type": "object",
      "description": "Ranking options for search.",
      "properties": {
        "ranker": {
          "type": "string",
          "description": "The ranker value",
          "enum": [
            "auto",
            "default-2024-11-15"
          ]
        },
        "score_threshold": {
          "type": "number",
          "description": "Score Threshold"
        }
      }
    },
    "rewrite_query": {
      "type": "boolean",
      "description": "Whether to rewrite the natural language query for vector search."
    }
  },
  "required": [
    "PCID",
    "vector_store_id",
    "query"
  ]
}

openai_data_update_eval

Update certain properties of an evaluation. Parameters:

Parameter	Type	Required	Default	Description
`eval_id`	string	Yes	—	The ID of the evaluation to update.
`metadata`	object	No	—	Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
`name`	string	No	—	Rename the evaluation.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "eval_id": {
      "type": "string",
      "description": "The ID of the evaluation to update."
    },
    "metadata": {
      "type": "object",
      "description": "Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.   Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters."
    },
    "name": {
      "type": "string",
      "description": "Rename the evaluation."
    }
  },
  "required": [
    "PCID",
    "eval_id"
  ]
}

openai_data_update_vector_store_file_attributes

Update attributes on a vector store file. Parameters:

Parameter	Type	Required	Default	Description
`vector_store_id`	string	Yes	—	The ID of the vector store the file belongs to.
`file_id`	string	Yes	—	The ID of the file to update attributes.
`attributes`	object	Yes	—	Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "vector_store_id": {
      "type": "string",
      "description": "The ID of the vector store the file belongs to."
    },
    "file_id": {
      "type": "string",
      "description": "The ID of the file to update attributes."
    },
    "attributes": {
      "type": "object",
      "description": "Set of 16 key-value pairs that can be attached to an object. This can be  useful for storing additional information about the object in a structured  format, and querying for objects via API or the dashboard. Keys are strings  with a maximum length of 64 characters. Values are strings with a maximum  length of 512 characters, booleans, or numbers."
    }
  },
  "required": [
    "PCID",
    "vector_store_id",
    "file_id",
    "attributes"
  ]
}

​Tools

​openai_data_add_upload_part

​openai_data_cancel_batch

​openai_data_cancel_eval_run

​openai_data_cancel_fine_tuning_job

​openai_data_cancel_upload

​openai_data_cancel_vector_store_file_batch

​openai_data_complete_upload

​openai_data_create_batch

​openai_data_create_eval

​openai_data_create_eval_run

​openai_data_create_file

​openai_data_create_fine_tuning_checkpoint_permission

​openai_data_create_fine_tuning_job

​openai_data_create_upload

​openai_data_create_vector_store

​openai_data_create_vector_store_file

​openai_data_create_vector_store_file_batch

​openai_data_delete_eval

​openai_data_delete_eval_run

​openai_data_delete_file

​openai_data_delete_fine_tuning_checkpoint_permission

​openai_data_delete_vector_store

​openai_data_delete_vector_store_file

​openai_data_download_file

​openai_data_get_eval

​openai_data_get_eval_run

​openai_data_get_eval_run_output_item

​openai_data_get_eval_run_output_items

​openai_data_get_eval_runs

​openai_data_get_vector_store

​openai_data_get_vector_store_file

​openai_data_get_vector_store_file_batch

​openai_data_list_batches

​openai_data_list_evals

​openai_data_list_files

​openai_data_list_files_in_vector_store_batch

​openai_data_list_fine_tuning_checkpoint_permissions

​openai_data_list_fine_tuning_events

​openai_data_list_fine_tuning_job_checkpoints

​openai_data_list_paginated_fine_tuning_jobs

​openai_data_list_vector_store_files

​openai_data_list_vector_stores

​openai_data_modify_vector_store

​openai_data_retrieve_batch

​openai_data_retrieve_file

​openai_data_retrieve_fine_tuning_job

​openai_data_retrieve_vector_store_file_content

​openai_data_search_vector_store

​openai_data_update_eval

​openai_data_update_vector_store_file_attributes

Tools

openai_data_add_upload_part

openai_data_cancel_batch

openai_data_cancel_eval_run

openai_data_cancel_fine_tuning_job

openai_data_cancel_upload

openai_data_cancel_vector_store_file_batch

openai_data_complete_upload

openai_data_create_batch

openai_data_create_eval

openai_data_create_eval_run

openai_data_create_file

openai_data_create_fine_tuning_checkpoint_permission

openai_data_create_fine_tuning_job

openai_data_create_upload

openai_data_create_vector_store

openai_data_create_vector_store_file

openai_data_create_vector_store_file_batch

openai_data_delete_eval

openai_data_delete_eval_run

openai_data_delete_file

openai_data_delete_fine_tuning_checkpoint_permission

openai_data_delete_vector_store

openai_data_delete_vector_store_file

openai_data_download_file

openai_data_get_eval

openai_data_get_eval_run

openai_data_get_eval_run_output_item

openai_data_get_eval_run_output_items

openai_data_get_eval_runs

openai_data_get_vector_store

openai_data_get_vector_store_file

openai_data_get_vector_store_file_batch

openai_data_list_batches

openai_data_list_evals

openai_data_list_files

openai_data_list_files_in_vector_store_batch

openai_data_list_fine_tuning_checkpoint_permissions

openai_data_list_fine_tuning_events

openai_data_list_fine_tuning_job_checkpoints

openai_data_list_paginated_fine_tuning_jobs

openai_data_list_vector_store_files

openai_data_list_vector_stores

openai_data_modify_vector_store

openai_data_retrieve_batch

openai_data_retrieve_file

openai_data_retrieve_fine_tuning_job

openai_data_retrieve_vector_store_file_content

openai_data_search_vector_store

openai_data_update_eval

openai_data_update_vector_store_file_attributes