> ## Documentation Index
> Fetch the complete documentation index at: https://docs.unleashx.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Update Evaluation

> Update an existing evaluation configuration. Pass eval_id and only the fields you want to change.

Update an existing evaluation configuration. `eval_id` is required; send only the fields you want to change.

Creating a new one: see [Create Evaluation](https://docs.unleashx.ai/api-reference/evaluation/create-config.md).

## Providers and models

Send the provider and model **names** exactly as written below (copy and paste). A model must belong to the provider you send with it. This list is loaded live, so new providers and models appear here automatically.

### LLM

Use for `llm_provider` (provider) and `llm_model` (model). The same list works for `fallback_provider` and `fallback_model`.

### Transcription (recording source)

Use for `transcription_provider` (provider) and `transcription_model` (model).


## OpenAPI

````yaml api-reference/openapi.json POST /evaluation/create-update-config
openapi: 3.1.0
info:
  title: >-
    UnleashX - Build human like conversations | Voice Agents | Automations | AI
    Workforce
  version: 1.0.0
  description: UnleashX - Your home for human like conversations
servers:
  - url: https://www.tryunleashx.com/api/v1/global/
security:
  - bearerAuth: []
paths:
  /evaluation/create-update-config:
    post:
      tags:
        - Evaluation
      summary: Update evaluation
      description: >-
        Update an existing evaluation configuration. Pass eval_id and only the
        fields you want to change.
      parameters:
        - name: token
          in: header
          required: true
          description: API token for authentication
          schema:
            type: string
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required:
                - eval_id
              properties:
                eval_id:
                  type: integer
                  description: Pass to update an existing evaluation
                eval_name:
                  type: string
                  description: Evaluation name
                call_source:
                  type: string
                  description: '`agent`, `app`, `recording`, `api` or `webhook`'
                agent_id:
                  type: string
                  description: Agent(s) to evaluate (agent source)
                app_id:
                  type: string
                  description: App to evaluate (app source)
                source_config:
                  type: object
                  description: Source-specific config (api / webhook)
                system_prompt:
                  type: string
                  description: Evaluation system prompt
                llm_provider:
                  type: string
                  description: >-
                    LLM provider name, e.g. `openai`. See the list of providers
                    and models below.
                llm_model:
                  type: string
                  description: >-
                    LLM model name of the chosen provider, e.g. `gpt-4o-mini`.
                    See the list of providers and models below.
                fallback_provider:
                  type: string
                  description: >-
                    Fallback LLM provider name. See the list of providers and
                    models below.
                fallback_model:
                  type: string
                  description: >-
                    Fallback model name of the chosen fallback provider. See the
                    list of providers and models below.
                transcription_provider:
                  type: string
                  description: >-
                    Transcription provider name (recording source), e.g.
                    `deepgram`. See the list of providers and models below.
                transcription_model:
                  type: string
                  description: >-
                    Transcription model name of the chosen provider, e.g.
                    `nova-2`. See the list of providers and models below.
                temperature:
                  type: integer
                  description: Sampling temperature
                skip_shorter_than:
                  type: integer
                  description: Skip calls shorter than this many seconds
                run_on_all_past_and_future_calls:
                  type: boolean
                  description: Evaluate past calls as well as future ones
                ground_truth_sources:
                  type: array
                  items:
                    type: string
                  description: Ground-truth sources
                cron_expression:
                  type: string
                  description: Schedule for recurring evaluation
                status:
                  type: integer
                  description: Evaluation status
      responses:
        '200':
          description: Success
          content:
            application/json:
              schema:
                type: object
      security: []
components:
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer

````

This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.