algolia_client_agent_studio library

Classes

AgentCompletionAlgoliaParams
AgentCompletionRequest
AgentConfigCreate
AgentConfigUpdate
AgentSegment
Represents a segment of algolia agent header.
AgentStudioClient
AgentTestConfiguration
AgentWithVersionResponse
AlgoliaDisplayResultsToolConfig
AlgoliaNoResponse
Represents a successful API response with no content (HTTP 204).
AlgoliaRecommendToolConfigInput
AlgoliaRecommendToolIndexConfig
AlgoliaSearchToolConfig
AlgoliaSearchToolIndexConfig
AllowedDomainBulkDelete
AllowedDomainBulkInsert
AllowedDomainCreate
AllowedDomainListResponse
AllowedDomainResponse
AnthropicProviderInput
ApiClient
An abstract class representing an API client with specific properties and options.
ApiRequest
Represents an API request to be sent to Algolia.
ApplicationConfigPatch
ApplicationConfigResponse
AssistantMessageV4
AssistantMessageV5
AzureOpenAIProviderInput
BaseProviderInput
ChunkedHelperOptions
Optional configuration for chunked helpers that batch records and poll for task completion.
ClientOptions
ClientSideToolConfig
ClientToolsArgsSchema
ConversationBaseResponse
ConversationFullResponse
ConversationMetadata
Episode
ErrorBase
Facets
FacetsParam
FeedbackCreationRequest
FeedbackResponse
Host
Represents an Algolia host.
HttpRequest
Represents an Http request.
HttpResponse
Represents an Http response
HTTPValidationError
IndexSearchParameters
McpServerToolConfig
McpToolConfig
MemoryRecord
MessageResponse
NumberParam
NumberParamConstraint
OpenAICompatibleProviderInput
OpenAIProviderInput
PaginatedAgentsResponse
PaginatedConversationsResponse
PaginatedProviderAuthenticationsResponse
PaginatedSecretKeysResponse
PaginationMetadata
ProviderAuthenticationCreate
ProviderAuthenticationPatch
ProviderAuthenticationResponse
ReasoningPart
ReasoningPartV4
ReasoningPartV5
Requester
A contract Requester to define an interface for handling HTTP requests and responses.
RequestOptions
Represents options for configuring a request to an endpoint.
RetryStrategy
Component to run http requests with retry logic.
SearchParameters
SearchParametersOverrides
SecretKeyCreate
SecretKeyPatch
SecretKeyResponse
StartPart
StartStepPart
StepStartPartV4
StepStartPartV5
StringArrayParam
StringArrayParamConstraint
TextParam
TextPart
TextPartV4
TextPartV5
ToolApprovalRequestPart
ToolCallPart
ToolInvocationPartV4
ToolInvocationV4
ToolPartV5
ToolResultOutput
ToolResultPart
TransformationOptions
Options for the ingestion transporter used by *WithTransformation helpers.
UnknownToolConfig
UserDataResponse
UserMessageMetadataV5
UserMessageV4
UserMessageV5
ValidationError

Enums

AdvancedSyntaxFeatures
AdvancedSyntaxFeatures.
AgentStatus
AlternativesAsExact
AlternativesAsExact.
CallType
Indicate whether the HTTP call performed is of type read (GET) or write (POST, PUT ..). Used to determine which timeout duration to use.
CompatibilityMode
Support Compatibility modes for the completion API.
ExactOnSingleWordQuery
Determines how the Exact ranking criterion is computed when the search query has only one word. - attribute. The Exact ranking criterion is 1 if the query word and attribute value are the same. For example, a search for "road" will match the value "road", but not "road trip". - none. The Exact ranking criterion is ignored on single-word searches. - word. The Exact ranking criterion is 1 if the query word is found in the attribute value. The query word must have at least 3 characters and must not be a stop word. Only exact matches will be highlighted, partial and prefix matches won't.
MemoryType
Memory types implemented so far. Follows LangMem's ontology: https://langchain-ai.github.io/langmem/concepts/conceptual_guide/#memory-types.
MessageRole
Role of a message in the conversation.
ProviderName
QueryType
Determines if and how query words are interpreted as prefixes. By default, only the last query word is treated as a prefix (prefixLast). To turn off prefix search, use prefixNone. Avoid prefixAll, which treats all query words as prefixes. This might lead to counterintuitive results and makes your search slower. For more information, see Prefix searching.
RemoveWordsIfNoResults
Strategy for removing words from the query when it doesn't return any results. This helps to avoid returning empty search results. - none. No words are removed when a query doesn't return results. - lastWords. Treat the last (then second to last, then third to last) word as optional, until there are results or at most 5 words have been removed. - firstWords. Treat the first (then second, then third) word as optional, until there are results or at most 5 words have been removed. - allOptional. Treat all words as optional. For more information, see Remove words to improve results.
RequestMethod
Provides enumerated HTTP verbs
SupportedLanguage
ISO code for a supported language.
ToolResultOutputType
The valid 'type' of tool results.
ToolState
TypoToleranceEnum
  • min. Return matches with the lowest number of typos. For example, if you have matches without typos, only include those. But if there are no matches without typos (with 1 typo), include matches with 1 typo (2 typos). - strict. Return matches with the two lowest numbers of typos. With strict, the Typo ranking criterion is applied first in the ranking setting.
  • VoteEnum

    Constants

    defaultMaxRetries → const int
    Default maximum number of retries for chunked helpers and wait operations.
    defaultReplaceAllObjectsMaxRetries → const int
    Default maximum number of retries used by replaceAllObjects.
    platformRequestIdAsQueryParameter → const bool
    Whether the platform mints the Request-ID as the x-algolia-request-id query parameter instead of the header. Browsers must: the header is not covered by the API's CORS allow-list. Also the fallback for unknown platforms (wasm web included), where only the query parameter is safe.
    requestIdHeader → const String
    The name of the header carrying the Request-ID minted when a client supports it.
    requestIdQueryParameter → const String
    The name of the query parameter carrying a Request-ID; the server consults it only when the header is absent.

    Functions

    generateRequestId() String
    Returns a fresh 11-character base62 identifier suitable for the Request-ID header.
    hasRequestIdHeader(Map<String, dynamic>? headers) bool
    Whether the given headers already carry a Request-ID entry, whatever its casing.
    hasRequestIdQueryParameter(Map<String, dynamic>? queryParameters) bool
    Whether the given query parameters already carry an x-algolia-request-id entry, whatever its casing; a minted header would shadow it.
    mintedRequestIdOptions({bool asQueryParameter = platformRequestIdAsQueryParameter}) RequestOptions
    Request options carrying a freshly minted Request-ID on the given channel: the header on native platforms, the query parameter on the web.

    Exceptions / Errors

    AlgoliaApiException
    Exception thrown when the Algolia API returns an error.
    AlgoliaException
    Abstract base class for all Algolia exceptions.
    AlgoliaIOException
    Exception thrown when there is an input/output error during a request to the Algolia API.
    AlgoliaTimeoutException
    Exception thrown when a request to the Algolia API times out.
    AlgoliaWaitException
    Exception thrown when an error occurs during the wait strategy. For example: maximum number of retry exceeded.
    UnreachableHostsException
    Exception thrown when all hosts for the Algolia API are unreachable.