Typesense Conversation Models API
Create and manage conversation models that define which LLM provider and configuration to use for generating conversational answers from search results.
OpenAPI Specification
openapi: 3.1.0
info:
title: Typesense Analytics Analytics Events Conversation Models API
description: The Typesense Analytics API allows developers to track and analyze search behavior by recording click, conversion, and visit events. It provides endpoints for creating analytics rules, logging events with metadata tags, and retrieving popular queries and queries with no results. This data can be used to improve search relevance through query suggestions, curations, and understanding user search patterns.
version: '30.1'
contact:
name: Typesense Support
url: https://typesense.org/support
license:
name: GPL-3.0
url: https://www.gnu.org/licenses/gpl-3.0.html
termsOfService: https://typesense.org/terms
servers:
- url: '{protocol}://{hostname}:{port}'
description: Typesense Server
variables:
protocol:
default: http
enum:
- http
- https
hostname:
default: localhost
port:
default: '8108'
security:
- api_key_header: []
tags:
- name: Conversation Models
description: Create and manage conversation models that define which LLM provider and configuration to use for generating conversational answers from search results.
paths:
/conversations/models:
get:
operationId: listConversationModels
summary: List All Conversation Models
description: Retrieves all conversation models configured in the Typesense instance. Conversation models define the LLM provider and parameters used for generating answers in conversational search.
tags:
- Conversation Models
responses:
'200':
description: List of conversation models
content:
application/json:
schema:
type: array
items:
$ref: '#/components/schemas/ConversationModel'
'401':
description: Unauthorized
post:
operationId: createConversationModel
summary: Create A Conversation Model
description: Creates a new conversation model that specifies the LLM provider, model name, API key, and system prompt for generating conversational answers from search results.
tags:
- Conversation Models
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/ConversationModelCreateSchema'
responses:
'201':
description: Conversation model created
content:
application/json:
schema:
$ref: '#/components/schemas/ConversationModel'
'400':
description: Bad request - invalid model configuration
'401':
description: Unauthorized
/conversations/models/{modelId}:
parameters:
- $ref: '#/components/parameters/modelId'
get:
operationId: getConversationModel
summary: Retrieve A Conversation Model
description: Retrieves a specific conversation model by ID.
tags:
- Conversation Models
responses:
'200':
description: Conversation model retrieved
content:
application/json:
schema:
$ref: '#/components/schemas/ConversationModel'
'401':
description: Unauthorized
'404':
description: Conversation model not found
put:
operationId: updateConversationModel
summary: Update A Conversation Model
description: Updates an existing conversation model configuration including the LLM provider, model name, and system prompt.
tags:
- Conversation Models
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/ConversationModelUpdateSchema'
responses:
'200':
description: Conversation model updated
content:
application/json:
schema:
$ref: '#/components/schemas/ConversationModel'
'400':
description: Bad request
'401':
description: Unauthorized
'404':
description: Conversation model not found
delete:
operationId: deleteConversationModel
summary: Delete A Conversation Model
description: Deletes a conversation model by ID.
tags:
- Conversation Models
responses:
'200':
description: Conversation model deleted
content:
application/json:
schema:
type: object
properties:
id:
type: string
description: ID of the deleted conversation model.
'401':
description: Unauthorized
'404':
description: Conversation model not found
components:
schemas:
ConversationModelUpdateSchema:
type: object
properties:
model_name:
type: string
description: Updated LLM model name.
api_key:
type: string
description: Updated API key for the LLM provider.
system_prompt:
type: string
description: Updated system prompt.
max_bytes:
type: integer
description: Updated maximum context bytes.
ConversationModel:
type: object
properties:
id:
type: string
description: Unique identifier of the conversation model.
model_name:
type: string
description: Name of the LLM model.
system_prompt:
type: string
description: System prompt for the model.
max_bytes:
type: integer
description: Maximum context bytes.
history_collection:
type: string
description: Collection storing conversation history.
ttl:
type: integer
description: TTL for conversation history.
ConversationModelCreateSchema:
type: object
required:
- model_name
- api_key
- system_prompt
properties:
model_name:
type: string
description: Name of the LLM model to use, such as gpt-4o, claude-3-opus, or a model hosted on a compatible endpoint.
api_key:
type: string
description: API key for authenticating with the LLM provider.
account_id:
type: string
description: Account ID for the LLM provider if required.
system_prompt:
type: string
description: System prompt that instructs the LLM how to generate answers from the search results context. This prompt is prepended to every conversation.
max_bytes:
type: integer
description: Maximum number of bytes of search context to send to the LLM.
history_collection:
type: string
description: Name of the collection to store conversation history.
ttl:
type: integer
description: Time-to-live in seconds for conversation history entries.
parameters:
modelId:
name: modelId
in: path
required: true
description: ID of the conversation model.
schema:
type: string
securitySchemes:
api_key_header:
type: apiKey
in: header
name: X-TYPESENSE-API-KEY
description: API key for authenticating requests to the Typesense server.
externalDocs:
description: Typesense Analytics Documentation
url: https://typesense.org/docs/30.1/api/analytics-query-suggestions.html