Skip to content

Latest commit

 

History

History
338 lines (230 loc) · 13 KB

MessageApi.md

File metadata and controls

338 lines (230 loc) · 13 KB
Raw

trieve_py_client.MessageApi

All URIs are relative to https://api.trieve.ai

Method HTTP request Description
create_message_completion_handler POST /api/message Create a message
edit_message_handler PUT /api/message Edit a message
get_all_topic_messages GET /api/messages/{messages_topic_id} Get all messages for a given topic
regenerate_message_handler DELETE /api/message Regenerate message

create_message_completion_handler

str create_message_completion_handler(tr_dataset, create_message_data)

Create a message

Create a message Create a message. Messages are attached to topics in order to coordinate memory of gen-AI chat sessions. We are considering refactoring this resource of the API soon. Currently, you can only send user messages. If the topic is a RAG topic then the response will include Chunks first on the stream. The structure will look like [chunks]||mesage. See docs.trieve.ai for more information.

Example

  • Api Key Authentication (ApiKey):
import trieve_py_client
from trieve_py_client.models.create_message_data import CreateMessageData
from trieve_py_client.rest import ApiException
from pprint import pprint

# Defining the host is optional and defaults to https://api.trieve.ai
# See configuration.py for a list of all supported configuration parameters.
configuration = trieve_py_client.Configuration(
    host = "https://api.trieve.ai"
)

# The client must configure the authentication and authorization parameters
# in accordance with the API server security policy.
# Examples for each auth method are provided below, use the example that
# satisfies your auth use case.

# Configure API key authorization: ApiKey
configuration.api_key['ApiKey'] = os.environ["API_KEY"]

# Uncomment below to setup prefix (e.g. Bearer) for API key, if needed
# configuration.api_key_prefix['ApiKey'] = 'Bearer'

# Enter a context with an instance of the API client
with trieve_py_client.ApiClient(configuration) as api_client:
    # Create an instance of the API class
    api_instance = trieve_py_client.MessageApi(api_client)
    tr_dataset = 'tr_dataset_example' # str | The dataset id to use for the request
    create_message_data = trieve_py_client.CreateMessageData() # CreateMessageData | JSON request payload to create a message completion

    try:
        # Create a message
        api_response = api_instance.create_message_completion_handler(tr_dataset, create_message_data)
        print("The response of MessageApi->create_message_completion_handler:\n")
        pprint(api_response)
    except Exception as e:
        print("Exception when calling MessageApi->create_message_completion_handler: %s\n" % e)

Parameters

Name Type Description Notes
tr_dataset str The dataset id to use for the request
create_message_data CreateMessageData JSON request payload to create a message completion

Return type

str

Authorization

ApiKey

HTTP request headers

  • Content-Type: application/json
  • Accept: text/plain, application/json

HTTP response details

Status code Description Response headers
200 This will be a JSON response of a string containing the LLM's generated inference. Response if not streaming. -
400 Service error relating to getting a chat completion -

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

edit_message_handler

edit_message_handler(tr_dataset, edit_message_data)

Edit a message

Edit a message Edit a message which exists within the topic's chat history. This will delete the message and replace it with a new message. The new message will be generated by the AI based on the new content provided in the request body. The response will include Chunks first on the stream if the topic is using RAG. The structure will look like [chunks]||mesage. See docs.trieve.ai for more information.

Example

  • Api Key Authentication (ApiKey):
import trieve_py_client
from trieve_py_client.models.edit_message_data import EditMessageData
from trieve_py_client.rest import ApiException
from pprint import pprint

# Defining the host is optional and defaults to https://api.trieve.ai
# See configuration.py for a list of all supported configuration parameters.
configuration = trieve_py_client.Configuration(
    host = "https://api.trieve.ai"
)

# The client must configure the authentication and authorization parameters
# in accordance with the API server security policy.
# Examples for each auth method are provided below, use the example that
# satisfies your auth use case.

# Configure API key authorization: ApiKey
configuration.api_key['ApiKey'] = os.environ["API_KEY"]

# Uncomment below to setup prefix (e.g. Bearer) for API key, if needed
# configuration.api_key_prefix['ApiKey'] = 'Bearer'

# Enter a context with an instance of the API client
with trieve_py_client.ApiClient(configuration) as api_client:
    # Create an instance of the API class
    api_instance = trieve_py_client.MessageApi(api_client)
    tr_dataset = 'tr_dataset_example' # str | The dataset id to use for the request
    edit_message_data = trieve_py_client.EditMessageData() # EditMessageData | JSON request payload to edit a message and get a new stream

    try:
        # Edit a message
        api_instance.edit_message_handler(tr_dataset, edit_message_data)
    except Exception as e:
        print("Exception when calling MessageApi->edit_message_handler: %s\n" % e)

Parameters

Name Type Description Notes
tr_dataset str The dataset id to use for the request
edit_message_data EditMessageData JSON request payload to edit a message and get a new stream

Return type

void (empty response body)

Authorization

ApiKey

HTTP request headers

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

HTTP response details

Status code Description Response headers
200 This will be a HTTP stream, check the chat or search UI for an example how to process this -
400 Service error relating to getting a chat completion -

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

get_all_topic_messages

List[Message] get_all_topic_messages(tr_dataset, messages_topic_id)

Get all messages for a given topic

Get all messages for a given topic Get all messages for a given topic. If the topic is a RAG topic then the response will include Chunks first on each message. The structure will look like [chunks]||mesage. See docs.trieve.ai for more information.

Example

  • Api Key Authentication (ApiKey):
import trieve_py_client
from trieve_py_client.models.message import Message
from trieve_py_client.rest import ApiException
from pprint import pprint

# Defining the host is optional and defaults to https://api.trieve.ai
# See configuration.py for a list of all supported configuration parameters.
configuration = trieve_py_client.Configuration(
    host = "https://api.trieve.ai"
)

# The client must configure the authentication and authorization parameters
# in accordance with the API server security policy.
# Examples for each auth method are provided below, use the example that
# satisfies your auth use case.

# Configure API key authorization: ApiKey
configuration.api_key['ApiKey'] = os.environ["API_KEY"]

# Uncomment below to setup prefix (e.g. Bearer) for API key, if needed
# configuration.api_key_prefix['ApiKey'] = 'Bearer'

# Enter a context with an instance of the API client
with trieve_py_client.ApiClient(configuration) as api_client:
    # Create an instance of the API class
    api_instance = trieve_py_client.MessageApi(api_client)
    tr_dataset = 'tr_dataset_example' # str | The dataset id to use for the request
    messages_topic_id = 'messages_topic_id_example' # str | The ID of the topic to get messages for.

    try:
        # Get all messages for a given topic
        api_response = api_instance.get_all_topic_messages(tr_dataset, messages_topic_id)
        print("The response of MessageApi->get_all_topic_messages:\n")
        pprint(api_response)
    except Exception as e:
        print("Exception when calling MessageApi->get_all_topic_messages: %s\n" % e)

Parameters

Name Type Description Notes
tr_dataset str The dataset id to use for the request
messages_topic_id str The ID of the topic to get messages for.

Return type

List[Message]

Authorization

ApiKey

HTTP request headers

  • Content-Type: Not defined
  • Accept: application/json

HTTP response details

Status code Description Response headers
200 All messages relating to the topic with the given ID -
400 Service error relating to getting the messages -

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

regenerate_message_handler

str regenerate_message_handler(tr_dataset, regenerate_message_data)

Regenerate message

Regenerate message Regenerate the assistant response to the last user message of a topic. This will delete the last message and replace it with a new message. The response will include Chunks first on the stream if the topic is using RAG. The structure will look like [chunks]||mesage. See docs.trieve.ai for more information.

Example

  • Api Key Authentication (ApiKey):
import trieve_py_client
from trieve_py_client.models.regenerate_message_data import RegenerateMessageData
from trieve_py_client.rest import ApiException
from pprint import pprint

# Defining the host is optional and defaults to https://api.trieve.ai
# See configuration.py for a list of all supported configuration parameters.
configuration = trieve_py_client.Configuration(
    host = "https://api.trieve.ai"
)

# The client must configure the authentication and authorization parameters
# in accordance with the API server security policy.
# Examples for each auth method are provided below, use the example that
# satisfies your auth use case.

# Configure API key authorization: ApiKey
configuration.api_key['ApiKey'] = os.environ["API_KEY"]

# Uncomment below to setup prefix (e.g. Bearer) for API key, if needed
# configuration.api_key_prefix['ApiKey'] = 'Bearer'

# Enter a context with an instance of the API client
with trieve_py_client.ApiClient(configuration) as api_client:
    # Create an instance of the API class
    api_instance = trieve_py_client.MessageApi(api_client)
    tr_dataset = 'tr_dataset_example' # str | The dataset id to use for the request
    regenerate_message_data = trieve_py_client.RegenerateMessageData() # RegenerateMessageData | JSON request payload to delete an agent message then regenerate it in a strem

    try:
        # Regenerate message
        api_response = api_instance.regenerate_message_handler(tr_dataset, regenerate_message_data)
        print("The response of MessageApi->regenerate_message_handler:\n")
        pprint(api_response)
    except Exception as e:
        print("Exception when calling MessageApi->regenerate_message_handler: %s\n" % e)

Parameters

Name Type Description Notes
tr_dataset str The dataset id to use for the request
regenerate_message_data RegenerateMessageData JSON request payload to delete an agent message then regenerate it in a strem

Return type

str

Authorization

ApiKey

HTTP request headers

  • Content-Type: application/json
  • Accept: text/plain, application/json

HTTP response details

Status code Description Response headers
200 This will be a JSON response of a string containing the LLM's generated inference. Response if not streaming. -
400 Service error relating to getting a chat completion -

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