# ExtractorUpdateRequest Attributes of an extractor to change. Every field is optional. A field left out of the request body keeps its current value, and so does a field sent explicitly as null -- null means \"leave this alone\", not \"clear it\". An empty string is a value, not an absence: it writes an empty string to the column, which for schema and prompt is the meaningful \"use the default\" setting. An empty llm or vision_llm is rejected with 400, since a model cannot be cleared. guardrails_settings replaces the whole object rather than merging into it, so a request carrying one key drops every other guardrail setting the extractor had. Send the complete settings object to change one of its fields. The column cannot be reset to null; an empty object is the closest equivalent. ## Properties Name | Type | Description | Notes ------------ | ------------- | ------------- | ------------- **name** | **str** | Human-readable name | [optional] **description** | **str** | What this extractor does | [optional] **llm** | **str** | Identifier or version of the language model the extractor uses | [optional] **var_schema** | **str** | JSONSchema that the extractor outputs, serialized as a string. Must be empty or a JSON object; a string, array or other non-object value is rejected with 400. When schema is not empty, the output is always returned as a JSON object. When schema is empty the extractor is unconstrained and its results are returned as free-form text rather than an object. | [optional] **prompt** | **str** | Custom prompt text for the extractor. If empty, default prompt will be used. If combined with schema, prompt can customize the output, but cannot change its format as it will always be JSON object. | [optional] **pre_prompt_summary** | **str** | Pre-prompt summary text for the extractor | [optional] **keep_intermediate_results** | **bool** | Flag indicating whether to keep intermediate results during extraction | [optional] **system_prompt** | **str** | System prompt text for the extractor | [optional] **max_num_chunks** | **int** | Maximum number of chunks to process | [optional] **vision** | **str** | Vision mode setting. One of 'on', 'off' or 'auto'. | [optional] **vision_llm** | **str** | Vision LLM model identifier | [optional] **image_batch_image_prompt** | **str** | Image batch processing prompt | [optional] **image_batch_final_prompt** | **str** | Final prompt for image batch processing | [optional] **guardrails_settings** | [**GuardrailsSettings**](GuardrailsSettings.md) | | [optional] ## Example ```python from h2ogpte.rest_async.models.extractor_update_request import ExtractorUpdateRequest # TODO update the JSON string below json = "{}" # create an instance of ExtractorUpdateRequest from a JSON string extractor_update_request_instance = ExtractorUpdateRequest.from_json(json) # print the JSON string representation of the object print(ExtractorUpdateRequest.to_json()) # convert the object into a dict extractor_update_request_dict = extractor_update_request_instance.to_dict() # create an instance of ExtractorUpdateRequest from a dict extractor_update_request_from_dict = ExtractorUpdateRequest.from_dict(extractor_update_request_dict) ```