API docs by Redocly

Scalytics Connect API (1.0.0)

Download OpenAPI specification:

API documentation for Scalytics Connect, including the OpenAI-compatible Scalytics API.

Scalytics API

OpenAI-compatible API for local models

Lists the models available to the authenticated user.

Authorizations:
BearerAuth

Responses

Response samples

Content type
application/json
{
  • "object": "list",
  • "data": [
    ]
}

Creates a model response for the given chat conversation using the configured local model.

Authorizations:
BearerAuth
Request Body schema: application/json
required
required
Array of objects (ChatMessage)

A list of messages comprising the conversation history.

stream
boolean
Default: false

Whether to stream back partial progress.

temperature
number <float> [ 0 .. 2 ]

Controls randomness. Lower values make the output more deterministic.

max_tokens
integer

The maximum number of tokens to generate in the completion.

top_p
number <float> [ 0 .. 1 ]

Nucleus sampling parameter.

frequency_penalty
number <float> [ -2 .. 2 ]

Penalizes new tokens based on their existing frequency in the text so far.

presence_penalty
number <float> [ -2 .. 2 ]

Penalizes new tokens based on whether they appear in the text so far.

model
string

Optional ID of the model to use. Currently ignored by the server.

object

Options for streaming responses.

Responses

Request samples

Content type
application/json
{
  • "messages": [
    ],
  • "stream": false,
  • "temperature": 2,
  • "max_tokens": 0,
  • "top_p": 1,
  • "frequency_penalty": -2,
  • "presence_penalty": -2,
  • "model": "string",
  • "stream_options": {
    }
}

Response samples

Content type
{
  • "id": "string",
  • "object": "chat.completion",
  • "created": 0,
  • "model": "string",
  • "choices": [
    ],
  • "usage": {
    }
}

Initiates a Deep Search task and streams results via Server-Sent Events (SSE).

Authorizations:
BearerAuth
Request Body schema: application/json
required
query
required
string

The user's initial search query or topic.

reasoningModelName
required
string

Required. Name/ID of the LLM for planning and intermediate reasoning. Use GET /v1/models to see available models.

synthesisModelName
required
string

Required. Name/ID of the LLM for final report synthesis. Use GET /v1/models to see available models.

search_providers
Array of strings
Default: []
Items Enum: "google" "bing" "brave" "openalex" "wikipedia" "duckduckgo"

Search providers. Defaults to a standard set if not provided.

max_distinct_search_queries
integer
Default: 7

Max distinct search engine queries.

max_results_per_provider_query
integer
Default: 5

Max search results per provider per query.

max_url_exploration_depth
integer

Max depth for exploring links. Defaults are handled by the Python service configuration.

max_hops
integer

Max research hops/iterations. Defaults are handled by the Python service configuration.

chunk_size_words
integer

Target chunk size in words. Defaults are handled by the Python service configuration.

chunk_overlap_words
integer

Target chunk overlap in words. Defaults are handled by the Python service configuration.

top_k_retrieval_per_hop
integer

Top-K chunks to retrieve from vector store per hop. Defaults are handled by the Python service configuration.

Responses

Request samples

Content type
application/json
{
  • "query": "string",
  • "reasoningModelName": "string",
  • "synthesisModelName": "string",
  • "search_providers": [ ],
  • "max_distinct_search_queries": 7,
  • "max_results_per_provider_query": 5,
  • "max_url_exploration_depth": 0,
  • "max_hops": 0,
  • "chunk_size_words": 0,
  • "chunk_overlap_words": 0,
  • "top_k_retrieval_per_hop": 0
}

Generates embeddings for a list of text strings.

Authorizations:
BearerAuth
Request Body schema: application/json
required
texts
required
Array of strings

A list of text strings to be embedded.

model_identifier
string

Optional identifier (e.g., ID or name) of the embedding model to use. If None, the service's default will be used.

Responses

Request samples

Content type
application/json
{
  • "texts": [
    ],
  • "model_identifier": "sentence-transformers/all-MiniLM-L6-v2"
}

Response samples

Content type
application/json
{
  • "success": true,
  • "data": {
    }
}

Adds a list of documents to the vector store.

Authorizations:
BearerAuth
Request Body schema: application/json
required
required
Array of objects (DocumentItemInput)

A list of document items to add.

group_id
required
string

An identifier to group these documents (e.g., user ID, session ID, collection name).

Responses

Request samples

Content type
application/json
{
  • "documents": [
    ],
  • "group_id": "string"
}

Response samples

Content type
application/json
{
  • "success": true,
  • "message": "string",
  • "details": { }
}

Searches vector documents based on a query text.

Authorizations:
BearerAuth
Request Body schema: application/json
required
query_text
required
string

The text to search for.

group_id
string

Optional group ID to scope the search within.

top_k
integer [ 1 .. 100 ]
Default: 5

Number of top results to return.

Responses

Request samples

Content type
application/json
{
  • "query_text": "string",
  • "group_id": "string",
  • "top_k": 5
}

Response samples

Content type
application/json
{
  • "success": true,
  • "message": "string",
  • "results": [
    ],
  • "details": { }
}

Deletes all vector documents associated with a specific group ID.

Authorizations:
BearerAuth
Request Body schema: application/json
required
group_id
required
string

The ID of the group whose vector documents should be deleted.

Responses

Request samples

Content type
application/json
{
  • "group_id": "string"
}

Response samples

Content type
application/json
{
  • "success": true,
  • "message": "string",
  • "details": { }
}

Creates an image given a prompt.

Authorizations:
BearerAuth
Request Body schema: application/json
required
model
required
string

ID of the model to use for image generation.

prompt
required
string

A text description of the desired image(s).

n
integer
Default: 1

The number of images to generate. (Currently only 1 is supported).

size
string
Default: "1024x1024"
Enum: "256x256" "512x512" "1024x1024" "1792x1024" "1024x1792"

The size of the generated images.

response_format
string
Default: "b64_json"
Enum: "url" "b64_json"

The format in which the generated images are returned.

Responses

Request samples

Content type
application/json
{
  • "model": "string",
  • "prompt": "string",
  • "n": 1,
  • "size": "256x256",
  • "response_format": "url"
}

Response samples

Content type
application/json
{
  • "created": 0,
  • "data": []
}

Vector Service

Generates embeddings for a list of text strings.

Authorizations:
BearerAuth
Request Body schema: application/json
required
texts
required
Array of strings

A list of text strings to be embedded.

model_identifier
string

Optional identifier (e.g., ID or name) of the embedding model to use. If None, the service's default will be used.

Responses

Request samples

Content type
application/json
{
  • "texts": [
    ],
  • "model_identifier": "sentence-transformers/all-MiniLM-L6-v2"
}

Response samples

Content type
application/json
{
  • "success": true,
  • "data": {
    }
}

Adds a list of documents to the vector store.

Authorizations:
BearerAuth
Request Body schema: application/json
required
required
Array of objects (DocumentItemInput)

A list of document items to add.

group_id
required
string

An identifier to group these documents (e.g., user ID, session ID, collection name).

Responses

Request samples

Content type
application/json
{
  • "documents": [
    ],
  • "group_id": "string"
}

Response samples

Content type
application/json
{
  • "success": true,
  • "message": "string",
  • "details": { }
}

Searches vector documents based on a query text.

Authorizations:
BearerAuth
Request Body schema: application/json
required
query_text
required
string

The text to search for.

group_id
string

Optional group ID to scope the search within.

top_k
integer [ 1 .. 100 ]
Default: 5

Number of top results to return.

Responses

Request samples

Content type
application/json
{
  • "query_text": "string",
  • "group_id": "string",
  • "top_k": 5
}

Response samples

Content type
application/json
{
  • "success": true,
  • "message": "string",
  • "results": [
    ],
  • "details": { }
}

Deletes all vector documents associated with a specific group ID.

Authorizations:
BearerAuth
Request Body schema: application/json
required
group_id
required
string

The ID of the group whose vector documents should be deleted.

Responses

Request samples

Content type
application/json
{
  • "group_id": "string"
}

Response samples

Content type
application/json
{
  • "success": true,
  • "message": "string",
  • "details": { }
}