Client.Chat

Overview

Available Operations

create - Chat
delete_all - Deletes all saved Chats owned by a user
delete - Deletes saved Chats
retrieve - Retrieves a Chat
list - Retrieves all saved Chats
retrieve_application - Gets the metadata for a custom Chat application
upload_files - Upload files for Chat
retrieve_files - Get files uploaded by a user for Chat
delete_files - Delete files uploaded by a user for chat
retrieve_file - Download a chat file
create_stream - Chat

create

Have a conversation with Glean AI.

Example Usage: citationResponse

from glean.api_client import Glean
import os


with Glean(
    api_token=os.getenv("GLEAN_API_TOKEN"),
) as glean:

    res = glean.client.chat.create(messages=[], timeout_millis=30000)

    # Handle response
    print(res)

Example Usage: defaultExample

from glean.api_client import Glean, models
import os


with Glean(
    api_token=os.getenv("GLEAN_API_TOKEN"),
) as glean:

    res = glean.client.chat.create(messages=[
        {
            "fragments": [
                models.ChatMessageFragment(
                    text="What are the company holidays this year?",
                ),
            ],
        },
    ], timeout_millis=30000)

    # Handle response
    print(res)

Example Usage: gptAgentExample

from glean.api_client import Glean, models
import os


with Glean(
    api_token=os.getenv("GLEAN_API_TOKEN"),
) as glean:

    res = glean.client.chat.create(messages=[
        {
            "fragments": [
                models.ChatMessageFragment(
                    text="Who was the first person to land on the moon?",
                ),
            ],
        },
    ], agent_config={
        "agent": models.AgentEnum.GPT,
    }, timeout_millis=30000)

    # Handle response
    print(res)

Example Usage: streamingExample

from glean.api_client import Glean
import os


with Glean(
    api_token=os.getenv("GLEAN_API_TOKEN"),
) as glean:

    res = glean.client.chat.create(messages=[], timeout_millis=30000)

    # Handle response
    print(res)

Example Usage: updateResponse

from glean.api_client import Glean
import os


with Glean(
    api_token=os.getenv("GLEAN_API_TOKEN"),
) as glean:

    res = glean.client.chat.create(messages=[], timeout_millis=30000)

    # Handle response
    print(res)

Parameters

Parameter	Type	Required	Description	Example
`messages`	List[models.ChatMessage]	✔️	A list of chat messages, from most recent to least recent. At least one message must specify a USER author.
`locale`	Optional[str]	➖	The client's preferred locale in rfc5646 format (e.g. `en`, `ja`, `pt-BR`). If omitted, the `Accept-Language` will be used. If not present or not supported, defaults to the closest match or `en`.
`timezone_offset`	Optional[int]	➖	The offset of the client's timezone in minutes from UTC. e.g. PDT is -420 because it's 7 hours behind UTC.
`session_info`	Optional[models.SessionInfo]	➖	N/A
`save_chat`	Optional[bool]	➖	Save the current interaction as a Chat for the user to access and potentially continue later.
`chat_id`	Optional[str]	➖	The id of the Chat that context should be retrieved from and messages added to. An empty id starts a new Chat, and the Chat is saved if saveChat is true.
`agent_config`	Optional[models.AgentConfig]	➖	Describes the agent that executes the request.
`inclusions`	Optional[models.ChatRestrictionFilters]	➖	N/A
`exclusions`	Optional[models.ChatRestrictionFilters]	➖	N/A
`timeout_millis`	Optional[int]	➖	Timeout in milliseconds for the request. A `408` error will be returned if handling the request takes longer.	30000
`application_id`	Optional[str]	➖	The ID of the application this request originates from, used to determine the configuration of underlying chat processes. This should correspond to the ID set during admin setup. If not specified, the default chat experience will be used.
`agent_id`	Optional[str]	➖	The ID of the Agent that should process this chat request. Only Agents with trigger set to 'User chat message' are invokable through this API. If not specified, the default chat experience will be used.
`stream`	Optional[bool]	➖	If set, response lines will be streamed one-by-one as they become available. Each will be a ChatResponse, formatted as JSON, and separated by a new line. If false, the entire response will be returned at once. Note that if this is set and the model being used does not support streaming, the model's response will not be streamed, but other messages from the endpoint still will be.
`retries`	Optional[utils.RetryConfig]	➖	Configuration to override the default retry behavior of the client.

Response

models.ChatResponse

Errors

Error Type	Status Code	Content Type
errors.GleanError	4XX, 5XX	/

delete_all

Deletes all saved Chats a user has had and all their contained conversational content.

Example Usage

from glean.api_client import Glean
import os


with Glean(
    api_token=os.getenv("GLEAN_API_TOKEN"),
) as glean:

    glean.client.chat.delete_all()

    # Use the SDK ...

Parameters

Parameter	Type	Required	Description
`locale`	Optional[str]	➖	The client's preferred locale in rfc5646 format (e.g. `en`, `ja`, `pt-BR`). If omitted, the `Accept-Language` will be used. If not present or not supported, defaults to the closest match or `en`.
`timezone_offset`	Optional[int]	➖	The offset of the client's timezone in minutes from UTC. e.g. PDT is -420 because it's 7 hours behind UTC.
`retries`	Optional[utils.RetryConfig]	➖	Configuration to override the default retry behavior of the client.

Errors

Error Type	Status Code	Content Type
errors.GleanError	4XX, 5XX	/

delete

Deletes saved Chats and all their contained conversational content.

Example Usage

from glean.api_client import Glean
import os


with Glean(
    api_token=os.getenv("GLEAN_API_TOKEN"),
) as glean:

    glean.client.chat.delete(ids=[])

    # Use the SDK ...

Parameters

Parameter	Type	Required	Description
`ids`	List[str]	✔️	A non-empty list of ids of the Chats to be deleted.
`locale`	Optional[str]	➖	The client's preferred locale in rfc5646 format (e.g. `en`, `ja`, `pt-BR`). If omitted, the `Accept-Language` will be used. If not present or not supported, defaults to the closest match or `en`.
`timezone_offset`	Optional[int]	➖	The offset of the client's timezone in minutes from UTC. e.g. PDT is -420 because it's 7 hours behind UTC.
`retries`	Optional[utils.RetryConfig]	➖	Configuration to override the default retry behavior of the client.

Errors

Error Type	Status Code	Content Type
errors.GleanError	4XX, 5XX	/

retrieve

Retrieves the chat history between Glean Assistant and the user for a given Chat. Omit pagination fields to return the full message history (existing behavior). Use last alone for the latest page, last with before for older messages, or first with after for newer messages. Each page is chronological and includes pagination cursors and page flags.

Example Usage

from glean.api_client import Glean
import os


with Glean(
    api_token=os.getenv("GLEAN_API_TOKEN"),
) as glean:

    res = glean.client.chat.retrieve(id="<id>")

    # Handle response
    print(res)

Parameters

Parameter	Type	Required	Description
`id`	str	✔️	The id of the Chat to be retrieved.
`locale`	Optional[str]	➖	The client's preferred locale in rfc5646 format (e.g. `en`, `ja`, `pt-BR`). If omitted, the `Accept-Language` will be used. If not present or not supported, defaults to the closest match or `en`.
`timezone_offset`	Optional[int]	➖	The offset of the client's timezone in minutes from UTC. e.g. PDT is -420 because it's 7 hours behind UTC.
`first`	Optional[int]	➖	Maximum number of messages to return from the start of the chat, or after the cursor when after is set. Pair with after for newer messages; alone returns the earliest messages. Mutually exclusive with last and before.
`after`	Optional[str]	➖	An opaque message cursor from this chat. Returns messages strictly newer than this cursor. Pair with first. Mutually exclusive with before; cannot be combined with last.
`last`	Optional[int]	➖	Maximum number of messages to return from the end of the chat, or before the cursor when before is set. Alone returns the latest messages; pair with before for older messages. Mutually exclusive with first and after.
`before`	Optional[str]	➖	An opaque message cursor from this chat. Returns messages strictly older than this cursor. Pair with last. Mutually exclusive with after; cannot be combined with first.
`retries`	Optional[utils.RetryConfig]	➖	Configuration to override the default retry behavior of the client.

Response

models.GetChatResponse

Errors

Error Type	Status Code	Content Type
errors.AccessRequestPermissionDeniedResponseError	403	application/json
errors.GleanError	4XX, 5XX	/

list

Retrieves all the saved Chats between Glean Assistant and the user. The returned Chats contain only metadata and no conversational content.

Example Usage

from glean.api_client import Glean
import os


with Glean(
    api_token=os.getenv("GLEAN_API_TOKEN"),
) as glean:

    res = glean.client.chat.list()

    # Handle response
    print(res)

Parameters

Parameter	Type	Required	Description
`locale`	Optional[str]	➖	The client's preferred locale in rfc5646 format (e.g. `en`, `ja`, `pt-BR`). If omitted, the `Accept-Language` will be used. If not present or not supported, defaults to the closest match or `en`.
`timezone_offset`	Optional[int]	➖	The offset of the client's timezone in minutes from UTC. e.g. PDT is -420 because it's 7 hours behind UTC.
`retries`	Optional[utils.RetryConfig]	➖	Configuration to override the default retry behavior of the client.

Response

models.ListChatsResponse

Errors

Error Type	Status Code	Content Type
errors.GleanError	4XX, 5XX	/

retrieve_application

Gets the Chat application details for the specified application ID.

Example Usage

from glean.api_client import Glean
import os


with Glean(
    api_token=os.getenv("GLEAN_API_TOKEN"),
) as glean:

    res = glean.client.chat.retrieve_application(id="<id>")

    # Handle response
    print(res)

Parameters

Parameter	Type	Required	Description
`id`	str	✔️	The id of the Chat application to be retrieved.
`locale`	Optional[str]	➖	The client's preferred locale in rfc5646 format (e.g. `en`, `ja`, `pt-BR`). If omitted, the `Accept-Language` will be used. If not present or not supported, defaults to the closest match or `en`.
`timezone_offset`	Optional[int]	➖	The offset of the client's timezone in minutes from UTC. e.g. PDT is -420 because it's 7 hours behind UTC.
`retries`	Optional[utils.RetryConfig]	➖	Configuration to override the default retry behavior of the client.

Response

models.GetChatApplicationResponse

Errors

Error Type	Status Code	Content Type
errors.GleanError	4XX, 5XX	/

upload_files

Upload files for Chat.

Example Usage

from glean.api_client import Glean
import os


with Glean(
    api_token=os.getenv("GLEAN_API_TOKEN"),
) as glean:

    res = glean.client.chat.upload_files(files=[])

    # Handle response
    print(res)

Parameters

Parameter	Type	Required	Description
`files`	List[models.UploadChatFilesRequestFile]	✔️	Raw files to be uploaded for chat in binary format.
`locale`	Optional[str]	➖	The client's preferred locale in rfc5646 format (e.g. `en`, `ja`, `pt-BR`). If omitted, the `Accept-Language` will be used. If not present or not supported, defaults to the closest match or `en`.
`timezone_offset`	Optional[int]	➖	The offset of the client's timezone in minutes from UTC. e.g. PDT is -420 because it's 7 hours behind UTC.
`retries`	Optional[utils.RetryConfig]	➖	Configuration to override the default retry behavior of the client.

Response

models.UploadChatFilesResponse

Errors

Error Type	Status Code	Content Type
errors.GleanError	4XX, 5XX	/

retrieve_files

Get files uploaded by a user for Chat.

Example Usage

from glean.api_client import Glean
import os


with Glean(
    api_token=os.getenv("GLEAN_API_TOKEN"),
) as glean:

    res = glean.client.chat.retrieve_files(file_ids=[
        "<value 1>",
    ])

    # Handle response
    print(res)

Parameters

Parameter	Type	Required	Description
`file_ids`	List[str]	✔️	IDs of files to fetch.
`locale`	Optional[str]	➖	The client's preferred locale in rfc5646 format (e.g. `en`, `ja`, `pt-BR`). If omitted, the `Accept-Language` will be used. If not present or not supported, defaults to the closest match or `en`.
`timezone_offset`	Optional[int]	➖	The offset of the client's timezone in minutes from UTC. e.g. PDT is -420 because it's 7 hours behind UTC.
`retries`	Optional[utils.RetryConfig]	➖	Configuration to override the default retry behavior of the client.

Response

models.GetChatFilesResponse

Errors

Error Type	Status Code	Content Type
errors.GleanError	4XX, 5XX	/

delete_files

Delete files uploaded by a user for Chat.

Example Usage

from glean.api_client import Glean
import os


with Glean(
    api_token=os.getenv("GLEAN_API_TOKEN"),
) as glean:

    glean.client.chat.delete_files(file_ids=[
        "<value 1>",
        "<value 2>",
        "<value 3>",
    ])

    # Use the SDK ...

Parameters

Parameter	Type	Required	Description
`file_ids`	List[str]	✔️	IDs of files to delete.
`locale`	Optional[str]	➖	The client's preferred locale in rfc5646 format (e.g. `en`, `ja`, `pt-BR`). If omitted, the `Accept-Language` will be used. If not present or not supported, defaults to the closest match or `en`.
`timezone_offset`	Optional[int]	➖	The offset of the client's timezone in minutes from UTC. e.g. PDT is -420 because it's 7 hours behind UTC.
`retries`	Optional[utils.RetryConfig]	➖	Configuration to override the default retry behavior of the client.

Errors

Error Type	Status Code	Content Type
errors.GleanError	4XX, 5XX	/

retrieve_file

Download the raw content of a file generated or uploaded during a chat session (for example, an image produced by the assistant). Returns the file bytes with a Content-Type header matching the file's MIME type.

Example Usage

from glean.api_client import Glean
import os


with Glean(
    api_token=os.getenv("GLEAN_API_TOKEN"),
) as glean:

    res = glean.client.chat.retrieve_file(file_id="<id>")

    # Handle response
    print(res)

Parameters

Parameter	Type	Required	Description
`file_id`	str	✔️	Identifier of the chat file to download.
`preview`	Optional[bool]	➖	When true and the file is a PDF, the response is served inline (Content-Disposition: inline) instead of as an attachment.
`retries`	Optional[utils.RetryConfig]	➖	Configuration to override the default retry behavior of the client.

Response

httpx.Response

Errors

Error Type	Status Code	Content Type
errors.GleanError	4XX, 5XX	/

create_stream

Have a conversation with Glean AI.

Example Usage: citationResponse

from glean.api_client import Glean
import os


with Glean(
    api_token=os.getenv("GLEAN_API_TOKEN"),
) as glean:

    res = glean.client.chat.create_stream(messages=[], timeout_millis=30000)

    # Handle response
    print(res)

Example Usage: defaultExample

from glean.api_client import Glean, models
import os


with Glean(
    api_token=os.getenv("GLEAN_API_TOKEN"),
) as glean:

    res = glean.client.chat.create_stream(messages=[
        {
            "fragments": [
                models.ChatMessageFragment(
                    text="What are the company holidays this year?",
                ),
            ],
        },
    ], timeout_millis=30000)

    # Handle response
    print(res)

Example Usage: gptAgentExample

from glean.api_client import Glean, models
import os


with Glean(
    api_token=os.getenv("GLEAN_API_TOKEN"),
) as glean:

    res = glean.client.chat.create_stream(messages=[
        {
            "fragments": [
                models.ChatMessageFragment(
                    text="Who was the first person to land on the moon?",
                ),
            ],
        },
    ], agent_config={
        "agent": models.AgentEnum.GPT,
    }, timeout_millis=30000)

    # Handle response
    print(res)

Example Usage: streamingExample

from glean.api_client import Glean
import os


with Glean(
    api_token=os.getenv("GLEAN_API_TOKEN"),
) as glean:

    res = glean.client.chat.create_stream(messages=[], timeout_millis=30000)

    # Handle response
    print(res)

Example Usage: updateResponse

from glean.api_client import Glean
import os


with Glean(
    api_token=os.getenv("GLEAN_API_TOKEN"),
) as glean:

    res = glean.client.chat.create_stream(messages=[], timeout_millis=30000)

    # Handle response
    print(res)

Parameters

Parameter	Type	Required	Description	Example
`messages`	List[models.ChatMessage]	✔️	A list of chat messages, from most recent to least recent. At least one message must specify a USER author.
`timezone_offset`	Optional[int]	➖	The offset of the client's timezone in minutes from UTC. e.g. PDT is -420 because it's 7 hours behind UTC.
`session_info`	Optional[models.SessionInfo]	➖	N/A
`save_chat`	Optional[bool]	➖	Save the current interaction as a Chat for the user to access and potentially continue later.
`chat_id`	Optional[str]	➖	The id of the Chat that context should be retrieved from and messages added to. An empty id starts a new Chat, and the Chat is saved if saveChat is true.
`agent_config`	Optional[models.AgentConfig]	➖	Describes the agent that executes the request.
`inclusions`	Optional[models.ChatRestrictionFilters]	➖	N/A
`exclusions`	Optional[models.ChatRestrictionFilters]	➖	N/A
`timeout_millis`	Optional[int]	➖	Timeout in milliseconds for the request. A `408` error will be returned if handling the request takes longer.	30000
`application_id`	Optional[str]	➖	The ID of the application this request originates from, used to determine the configuration of underlying chat processes. This should correspond to the ID set during admin setup. If not specified, the default chat experience will be used.
`agent_id`	Optional[str]	➖	The ID of the Agent that should process this chat request. Only Agents with trigger set to 'User chat message' are invokable through this API. If not specified, the default chat experience will be used.
`stream`	Optional[bool]	➖	If set, response lines will be streamed one-by-one as they become available. Each will be a ChatResponse, formatted as JSON, and separated by a new line. If false, the entire response will be returned at once. Note that if this is set and the model being used does not support streaming, the model's response will not be streamed, but other messages from the endpoint still will be.
`retries`	Optional[utils.RetryConfig]	➖	Configuration to override the default retry behavior of the client.

Response

str

Errors

Error Type	Status Code	Content Type
errors.GleanError	4XX, 5XX	/

GeezerVison

Expand file tree

README.md

Latest commit

History

README.md

File metadata and controls

Client.Chat

Overview

Available Operations

create

Example Usage: citationResponse

Example Usage: defaultExample

Example Usage: gptAgentExample

Example Usage: streamingExample

Example Usage: updateResponse

Parameters

Response

Errors

delete_all

Example Usage

Parameters

Errors

delete

Example Usage

Parameters

Errors

retrieve

Example Usage

Parameters

Response

Errors

list

Example Usage

Parameters

Response

Errors

retrieve_application

Example Usage

Parameters

Response

Errors

upload_files

Example Usage

Parameters

Response

Errors

retrieve_files

Example Usage

Parameters

Response

Errors

delete_files

Example Usage

Parameters

Errors

retrieve_file

Example Usage

Parameters

Response

Errors

create_stream

Example Usage: citationResponse

Example Usage: defaultExample

Example Usage: gptAgentExample

Example Usage: streamingExample

Example Usage: updateResponse

Parameters

Response

Errors