---
title: "Returns the system and user prompt templates for the given llm task in all supported languages"
method: POST
path: "/llm/create_prompt_templates"
tags: ["llm"]
---

# Returns the system and user prompt templates for the given llm task in all supported languages

`POST /llm/create_prompt_templates`

## Query parameters

- `approach_type` 'LLM_ZERO_SHOT' | 'LLM_FEW_SHOT', required
- `strategy_type` 'TAGGING_DEFAULT' | 'METADATA_DEFAULT' | 'SENTENCE_ANNOTATION_DEFAULT' | 'NER_INLINE_TAGS' | 'CONTEXT_ANCHORED_FUZZY_MATCHING', required

## Request body

- BodyLlmCreatePromptTemplates
  - `llm_job_params` LLMJobParameters, required
    - `project_id` integer, required — Project ID associated with the job
    - `llm_job_type` 'TAGGING' | 'METADATA_EXTRACTION' | 'ANNOTATION' | 'SENTENCE_ANNOTATION', required
    - `specific_task_parameters` union, required — Specific parameters for the LLMJob w.r.t it's type
      - TaggingParams
        - `llm_job_type` 'TAGGING', required
        - `sdoc_ids` integer[], required — IDs of the source documents to analyse
        - `tag_ids` integer[], required — IDs of the tags to use for the document tagging
      - MetadataExtractionParams
        - `llm_job_type` 'METADATA_EXTRACTION', required
        - `sdoc_ids` integer[], required — IDs of the source documents to analyse
        - `project_metadata_ids` integer[], required — IDs of the project metadata to use for the metadata extraction
      - AnnotationParams
        - `llm_job_type` 'ANNOTATION', required
        - `sdoc_ids` integer[], required — IDs of the source documents to analyse
        - `code_ids` integer[], required — IDs of the codes to use for the annotation
        - `delete_existing_annotations` boolean — Delete existing annotations before creating new ones
      - SentenceAnnotationParams
        - `llm_job_type` 'SENTENCE_ANNOTATION', required
        - `sdoc_ids` integer[], required — IDs of the source documents to analyse
        - `code_ids` integer[], required — IDs of the codes to use for the sentence annotation
        - `delete_existing_annotations` boolean — Delete existing annotations before creating new ones
  - `example_ids` integer[], nullable

## Response `200`

Successful Response

- LLMPromptTemplates[]
  - `language` string, required — The language of the prompt template
  - `system_prompt` string, required — The system prompt to use for the job
  - `user_prompt` string, required — The user prompt to use for the job

## Other responses

- `422` — Validation Error

## Changes

- **2026-09-01** `dfbb3fb9f16e` — 1 breaking
  - added the new required `query` request parameter `strategy_type`
- **2026-07-15** `1af5a8046f20` — 2 info
  - added the optional property `detail/items/ctx` to the response with the `422` status
  - added the optional property `detail/items/input` to the response with the `422` status
- **2026-06-29** `ab1f53e958b7` — 2 info
  - added the new optional request property `llm_job_params/specific_task_parameters/oneOf[subschema #3: AnnotationParams]/delete_existing_annotations`
  - the `delete_existing_annotations` request property default value changed from `true` to `false`
- **2025-09-05** `d59c807fb985` — 1 breaking
  - removed the enum value `MODEL_TRAINING` from the `query` request parameter `approach_type`
- **2025-08-22** `53e769440a25` — 3 warning, 2 info
  - removed the request property `llm_job_params/specific_task_parameters/oneOf[subschema #3: AnnotationParams]/delete_existing_annotations`
  - removed the optional property `detail/items/ctx` from the response with the `422` status
  - removed the optional property `detail/items/input` from the response with the `422` status
  - added the new enum value `MODEL_TRAINING` to the `query` request parameter `approach_type`
  - …1 more

[Change history](https://skmtc.dev/uhh-lt/apis/discourse-analysis-tool-suite-api/changes/llm/create_prompt_templates/post.md)

---

[API](https://skmtc.dev/uhh-lt/apis/discourse-analysis-tool-suite-api.md) · [All operations](https://skmtc.dev/uhh-lt/apis/discourse-analysis-tool-suite-api/llms.txt) · [OpenAPI document](https://skmtc-service-production.skmtc.workers.dev/v1/apis/uhh-lt/discourse-analysis-tool-suite-api/revisions/4c6052711f99/schema)