mirror of https://github.com/aljazceru/Auto-GPT.git synced 2025-12-19 06:54:22 +01:00

Files

merwanehamadi ece9e85b41 Add agent protocol within agbenchmark (#5239 )

Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>

2023-09-16 15:31:12 -07:00

22 KiB

Raw Blame History

agbenchmark.agent_protocol_client.AgentApi

All URIs are relative to http://localhost

Method	HTTP request	Description
create_agent_task	POST /agent/tasks	Creates a task for the agent.
download_agent_task_artifact	GET /agent/tasks/{task_id}/artifacts/{artifact_id}	Download a specified artifact.
execute_agent_task_step	POST /agent/tasks/{task_id}/steps	Execute a step in the specified agent task.
get_agent_task	GET /agent/tasks/{task_id}	Get details about a specified agent task.
get_agent_task_step	GET /agent/tasks/{task_id}/steps/{step_id}	Get details about a specified task step.
list_agent_task_artifacts	GET /agent/tasks/{task_id}/artifacts	List all artifacts that have been created for the given task.
list_agent_task_steps	GET /agent/tasks/{task_id}/steps	List all steps for the specified task.
list_agent_tasks_ids	GET /agent/tasks	List all tasks that have been created for the agent.
upload_agent_task_artifacts	POST /agent/tasks/{task_id}/artifacts	Upload an artifact for the specified task.

create_agent_task

Task create_agent_task(task_request_body=task_request_body)

Creates a task for the agent.

Example

import time
import os
import agent_protocol_client
from agbenchmark.agent_protocol_client.models.task import Task
from agbenchmark.agent_protocol_client.models.task_request_body import TaskRequestBody
from agbenchmark.agent_protocol_client.rest import ApiException
from pprint import pprint

# Defining the host is optional and defaults to http://localhost
# See configuration.py for a list of all supported configuration parameters.
configuration = agbenchmark.agent_protocol_client.Configuration(
    host = "http://localhost"
)


# Enter a context with an instance of the API client
async with agbenchmark.agent_protocol_client.ApiClient(configuration) as api_client:
    # Create an instance of the API class
    api_instance = agbenchmark.agent_protocol_client.AgentApi(api_client)
    task_request_body = agbenchmark.agent_protocol_client.TaskRequestBody() # TaskRequestBody |  (optional)

    try:
        # Creates a task for the agent.
        api_response = await api_instance.create_agent_task(task_request_body=task_request_body)
        print("The response of AgentApi->create_agent_task:\n")
        pprint(api_response)
    except Exception as e:
        print("Exception when calling AgentApi->create_agent_task: %s\n" % e)

Parameters

Name	Type	Description	Notes
task_request_body	TaskRequestBody		[optional]

Return type

Task

Authorization

No authorization required

HTTP request headers

Content-Type: application/json
Accept: application/json

HTTP response details

Status code	Description	Response headers
200	A new agent task was successfully created.	-
0	Internal Server Error	-

[Back to top] [Back to API list] [Back to Model list] [Back to README]

download_agent_task_artifact

bytearray download_agent_task_artifact(task_id, artifact_id)

Download a specified artifact.

Example

import time
import os
import agent_protocol_client
from agbenchmark.agent_protocol_client.rest import ApiException
from pprint import pprint

# Defining the host is optional and defaults to http://localhost
# See configuration.py for a list of all supported configuration parameters.
configuration = agbenchmark.agent_protocol_client.Configuration(
    host = "http://localhost"
)


# Enter a context with an instance of the API client
async with agbenchmark.agent_protocol_client.ApiClient(configuration) as api_client:
    # Create an instance of the API class
    api_instance = agbenchmark.agent_protocol_client.AgentApi(api_client)
    task_id = 'task_id_example' # str | ID of the task
    artifact_id = 'artifact_id_example' # str | ID of the artifact

    try:
        # Download a specified artifact.
        api_response = await api_instance.download_agent_task_artifact(task_id, artifact_id)
        print("The response of AgentApi->download_agent_task_artifact:\n")
        pprint(api_response)
    except Exception as e:
        print("Exception when calling AgentApi->download_agent_task_artifact: %s\n" % e)

Parameters

Name	Type	Description	Notes
task_id	str	ID of the task
artifact_id	str	ID of the artifact

Return type

bytearray

Authorization

No authorization required

HTTP request headers

Content-Type: Not defined
Accept: application/octet-stream

HTTP response details

Status code	Description	Response headers
200	Returned the content of the artifact.	-
0	Internal Server Error	-

[Back to top] [Back to API list] [Back to Model list] [Back to README]

execute_agent_task_step

Step execute_agent_task_step(task_id, step_request_body=step_request_body)

Execute a step in the specified agent task.

Example

import time
import os
import agent_protocol_client
from agbenchmark.agent_protocol_client.models.step import Step
from agbenchmark.agent_protocol_client.models.step_request_body import StepRequestBody
from agbenchmark.agent_protocol_client.rest import ApiException
from pprint import pprint

# Defining the host is optional and defaults to http://localhost
# See configuration.py for a list of all supported configuration parameters.
configuration = agbenchmark.agent_protocol_client.Configuration(
    host = "http://localhost"
)


# Enter a context with an instance of the API client
async with agbenchmark.agent_protocol_client.ApiClient(configuration) as api_client:
    # Create an instance of the API class
    api_instance = agbenchmark.agent_protocol_client.AgentApi(api_client)
    task_id = 'task_id_example' # str | ID of the task
    step_request_body = agbenchmark.agent_protocol_client.StepRequestBody() # StepRequestBody |  (optional)

    try:
        # Execute a step in the specified agent task.
        api_response = await api_instance.execute_agent_task_step(task_id, step_request_body=step_request_body)
        print("The response of AgentApi->execute_agent_task_step:\n")
        pprint(api_response)
    except Exception as e:
        print("Exception when calling AgentApi->execute_agent_task_step: %s\n" % e)

Parameters

Name	Type	Description	Notes
task_id	str	ID of the task
step_request_body	StepRequestBody		[optional]

Return type

Step

Authorization

No authorization required

HTTP request headers

Content-Type: application/json
Accept: application/json

HTTP response details

Status code	Description	Response headers
200	Executed step for the agent task.	-
0	Internal Server Error	-

[Back to top] [Back to API list] [Back to Model list] [Back to README]

get_agent_task

Task get_agent_task(task_id)

Get details about a specified agent task.

Example

import time
import os
import agent_protocol_client
from agbenchmark.agent_protocol_client.models.task import Task
from agbenchmark.agent_protocol_client.rest import ApiException
from pprint import pprint

# Defining the host is optional and defaults to http://localhost
# See configuration.py for a list of all supported configuration parameters.
configuration = agbenchmark.agent_protocol_client.Configuration(
    host = "http://localhost"
)


# Enter a context with an instance of the API client
async with agbenchmark.agent_protocol_client.ApiClient(configuration) as api_client:
    # Create an instance of the API class
    api_instance = agbenchmark.agent_protocol_client.AgentApi(api_client)
    task_id = 'task_id_example' # str | ID of the task

    try:
        # Get details about a specified agent task.
        api_response = await api_instance.get_agent_task(task_id)
        print("The response of AgentApi->get_agent_task:\n")
        pprint(api_response)
    except Exception as e:
        print("Exception when calling AgentApi->get_agent_task: %s\n" % e)

Parameters

Name	Type	Description	Notes
task_id	str	ID of the task

Return type

Task

Authorization

No authorization required

HTTP request headers

Content-Type: Not defined
Accept: application/json

HTTP response details

Status code	Description	Response headers
200	Returned details about an agent task.	-
0	Internal Server Error	-

[Back to top] [Back to API list] [Back to Model list] [Back to README]

get_agent_task_step

Step get_agent_task_step(task_id, step_id)

Get details about a specified task step.

Example

import time
import os
import agent_protocol_client
from agbenchmark.agent_protocol_client.models.step import Step
from agbenchmark.agent_protocol_client.rest import ApiException
from pprint import pprint

# Defining the host is optional and defaults to http://localhost
# See configuration.py for a list of all supported configuration parameters.
configuration = agbenchmark.agent_protocol_client.Configuration(
    host = "http://localhost"
)


# Enter a context with an instance of the API client
async with agbenchmark.agent_protocol_client.ApiClient(configuration) as api_client:
    # Create an instance of the API class
    api_instance = agbenchmark.agent_protocol_client.AgentApi(api_client)
    task_id = 'task_id_example' # str | ID of the task
    step_id = 'step_id_example' # str | ID of the step

    try:
        # Get details about a specified task step.
        api_response = await api_instance.get_agent_task_step(task_id, step_id)
        print("The response of AgentApi->get_agent_task_step:\n")
        pprint(api_response)
    except Exception as e:
        print("Exception when calling AgentApi->get_agent_task_step: %s\n" % e)

Parameters

Name	Type	Description	Notes
task_id	str	ID of the task
step_id	str	ID of the step

Return type

Step

Authorization

No authorization required

HTTP request headers

Content-Type: Not defined
Accept: application/json

HTTP response details

Status code	Description	Response headers
200	Returned details about an agent task step.	-
0	Internal Server Error	-

[Back to top] [Back to API list] [Back to Model list] [Back to README]

list_agent_task_artifacts

List[Artifact] list_agent_task_artifacts(task_id)

List all artifacts that have been created for the given task.

Example

import time
import os
import agent_protocol_client
from agbenchmark.agent_protocol_client.models.artifact import Artifact
from agbenchmark.agent_protocol_client.rest import ApiException
from pprint import pprint

# Defining the host is optional and defaults to http://localhost
# See configuration.py for a list of all supported configuration parameters.
configuration = agbenchmark.agent_protocol_client.Configuration(
    host = "http://localhost"
)


# Enter a context with an instance of the API client
async with agbenchmark.agent_protocol_client.ApiClient(configuration) as api_client:
    # Create an instance of the API class
    api_instance = agbenchmark.agent_protocol_client.AgentApi(api_client)
    task_id = 'task_id_example' # str | ID of the task

    try:
        # List all artifacts that have been created for the given task.
        api_response = await api_instance.list_agent_task_artifacts(task_id)
        print("The response of AgentApi->list_agent_task_artifacts:\n")
        pprint(api_response)
    except Exception as e:
        print("Exception when calling AgentApi->list_agent_task_artifacts: %s\n" % e)

Parameters

Name	Type	Description	Notes
task_id	str	ID of the task

Return type

List[Artifact]

Authorization

No authorization required

HTTP request headers

Content-Type: Not defined
Accept: application/json

HTTP response details

Status code	Description	Response headers
200	Returned the content of the artifact.	-
0	Internal Server Error	-

[Back to top] [Back to API list] [Back to Model list] [Back to README]

list_agent_task_steps

List[str] list_agent_task_steps(task_id)

List all steps for the specified task.

Example

import time
import os
import agent_protocol_client
from agbenchmark.agent_protocol_client.rest import ApiException
from pprint import pprint

# Defining the host is optional and defaults to http://localhost
# See configuration.py for a list of all supported configuration parameters.
configuration = agbenchmark.agent_protocol_client.Configuration(
    host = "http://localhost"
)


# Enter a context with an instance of the API client
async with agbenchmark.agent_protocol_client.ApiClient(configuration) as api_client:
    # Create an instance of the API class
    api_instance = agbenchmark.agent_protocol_client.AgentApi(api_client)
    task_id = 'task_id_example' # str | ID of the task

    try:
        # List all steps for the specified task.
        api_response = await api_instance.list_agent_task_steps(task_id)
        print("The response of AgentApi->list_agent_task_steps:\n")
        pprint(api_response)
    except Exception as e:
        print("Exception when calling AgentApi->list_agent_task_steps: %s\n" % e)

Parameters

Name	Type	Description	Notes
task_id	str	ID of the task

Return type

List[str]

Authorization

No authorization required

HTTP request headers

Content-Type: Not defined
Accept: application/json

HTTP response details

Status code	Description	Response headers
200	Returned list of agent's step IDs for the specified task.	-
0	Internal Server Error	-

[Back to top] [Back to API list] [Back to Model list] [Back to README]

list_agent_tasks_ids

List[str] list_agent_tasks_ids()

List all tasks that have been created for the agent.

Example

import time
import os
import agent_protocol_client
from agbenchmark.agent_protocol_client.rest import ApiException
from pprint import pprint

# Defining the host is optional and defaults to http://localhost
# See configuration.py for a list of all supported configuration parameters.
configuration = agbenchmark.agent_protocol_client.Configuration(
    host = "http://localhost"
)


# Enter a context with an instance of the API client
async with agbenchmark.agent_protocol_client.ApiClient(configuration) as api_client:
    # Create an instance of the API class
    api_instance = agbenchmark.agent_protocol_client.AgentApi(api_client)

    try:
        # List all tasks that have been created for the agent.
        api_response = await api_instance.list_agent_tasks_ids()
        print("The response of AgentApi->list_agent_tasks_ids:\n")
        pprint(api_response)
    except Exception as e:
        print("Exception when calling AgentApi->list_agent_tasks_ids: %s\n" % e)

Parameters

This endpoint does not need any parameter.

Return type

List[str]

Authorization

No authorization required

HTTP request headers

Content-Type: Not defined
Accept: application/json

HTTP response details

Status code	Description	Response headers
200	Returned list of agent's task IDs.	-
0	Internal Server Error	-

[Back to top] [Back to API list] [Back to Model list] [Back to README]

upload_agent_task_artifacts

Artifact upload_agent_task_artifacts(task_id, file, relative_path=relative_path)

Upload an artifact for the specified task.

Example

import time
import os
import agent_protocol_client
from agbenchmark.agent_protocol_client.models.artifact import Artifact
from agbenchmark.agent_protocol_client.rest import ApiException
from pprint import pprint

# Defining the host is optional and defaults to http://localhost
# See configuration.py for a list of all supported configuration parameters.
configuration = agbenchmark.agent_protocol_client.Configuration(
    host = "http://localhost"
)


# Enter a context with an instance of the API client
async with agbenchmark.agent_protocol_client.ApiClient(configuration) as api_client:
    # Create an instance of the API class
    api_instance = agbenchmark.agent_protocol_client.AgentApi(api_client)
    task_id = 'task_id_example' # str | ID of the task
    file = None # bytearray | File to upload.
    relative_path = 'relative_path_example' # str | Relative path of the artifact in the agent's workspace. (optional)

    try:
        # Upload an artifact for the specified task.
        api_response = await api_instance.upload_agent_task_artifacts(task_id, file, relative_path=relative_path)
        print("The response of AgentApi->upload_agent_task_artifacts:\n")
        pprint(api_response)
    except Exception as e:
        print("Exception when calling AgentApi->upload_agent_task_artifacts: %s\n" % e)

Parameters

Name	Type	Description	Notes
task_id	str	ID of the task
file	bytearray	File to upload.
relative_path	str	Relative path of the artifact in the agent's workspace.	[optional]

Return type

Artifact

Authorization

No authorization required

HTTP request headers

Content-Type: multipart/form-data
Accept: application/json

HTTP response details

Status code	Description	Response headers
200	Returned the content of the artifact.	-
0	Internal Server Error	-

[Back to top] [Back to API list] [Back to Model list] [Back to README]

22 KiB Raw Blame History

agbenchmark.agent_protocol_client.AgentApi

create_agent_task

Example

Parameters

Return type

Authorization

HTTP request headers

HTTP response details

download_agent_task_artifact

Example

Parameters

Return type

Authorization

HTTP request headers

HTTP response details

execute_agent_task_step

Example

Parameters

Return type

Authorization

HTTP request headers

HTTP response details

get_agent_task

Example

Parameters

Return type

Authorization

HTTP request headers

HTTP response details

get_agent_task_step

Example

Parameters

Return type

Authorization

HTTP request headers

HTTP response details

list_agent_task_artifacts

Example

Parameters

Return type

Authorization

HTTP request headers

HTTP response details

list_agent_task_steps

Example

Parameters

Return type

Authorization

HTTP request headers

HTTP response details

list_agent_tasks_ids

Example

Parameters

Return type

Authorization

HTTP request headers

HTTP response details

upload_agent_task_artifacts

Example

Parameters

Return type

Authorization

HTTP request headers

HTTP response details

22 KiB

Raw Blame History