example:
ai_agent_extract_structuredThe type of AI agent to be used for extraction.Value is always ai_agent_extract_structuredAI agent processor used to handle basic text.
Show child attributes
Show child attributes
llm_endpoint_params
AI LLM endpoint params AWS/AI LLM endpoint params Google/AI LLM endpoint params IBM/AI LLM endpoint params OpenAIobject
The parameters for the LLM endpoint specific to a model.
example:
azure__openai__gpt_4o_miniThe model used for the AI agent for basic text. For specific model values, see the available models list.example:
8400The number of tokens for completion.example:
(\{user_question\}[\s\S]*?\{content\}|\{content\}[\s\S]*?\{user_question\})The prompt template contains contextual information of the request and the user prompt.
When passing prompt_template parameters, you must include inputs for {user_question} and {content}.
{current_date} is optional, depending on the use.example:
You are a helpful travel assistant specialized in budget travelSystem messages try to help the LLM “understand” its role and what it is supposed to do.AI agent processor used to handle basic text.
Show child attributes
Show child attributes
llm_endpoint_params
AI LLM endpoint params AWS/AI LLM endpoint params Google/AI LLM endpoint params IBM/AI LLM endpoint params OpenAIobject
The parameters for the LLM endpoint specific to a model.
example:
azure__openai__gpt_4o_miniThe model used for the AI agent for basic text. For specific model values, see the available models list.example:
8400The number of tokens for completion.example:
(\{user_question\}[\s\S]*?\{content\}|\{content\}[\s\S]*?\{user_question\})The prompt template contains contextual information of the request and the user prompt.
When passing prompt_template parameters, you must include inputs for {user_question} and {content}.
{current_date} is optional, depending on the use.example:
You are a helpful travel assistant specialized in budget travelSystem messages try to help the LLM “understand” its role and what it is supposed to do.AI agent processor used to to handle longer text.
Show child attributes
Show child attributes
Show child attributes
Show child attributes
example:
azure__openai__text_embedding_ada_002The model used for the AI agent for calculating embeddings.llm_endpoint_params
AI LLM endpoint params AWS/AI LLM endpoint params Google/AI LLM endpoint params IBM/AI LLM endpoint params OpenAIobject
The parameters for the LLM endpoint specific to a model.
example:
azure__openai__gpt_4o_miniThe model used for the AI agent for basic text. For specific model values, see the available models list.example:
8400The number of tokens for completion.example:
(\{user_question\}[\s\S]*?\{content\}|\{content\}[\s\S]*?\{user_question\})The prompt template contains contextual information of the request and the user prompt.
When passing prompt_template parameters, you must include inputs for {user_question} and {content}.
{current_date} is optional, depending on the use.example:
You are a helpful travel assistant specialized in budget travelSystem messages try to help the LLM “understand” its role and what it is supposed to do.Copy
Ask AI
{
"type": "ai_agent_extract_structured",
"basic_image": {
"llm_endpoint_params": {
"type": "openai_params",
"frequency_penalty": 1.5,
"presence_penalty": 1.5,
"stop": "<|im_end|>",
"temperature": 0,
"top_p": 1
},
"model": "azure__openai__gpt_4o_mini",
"num_tokens_for_completion": 8400,
"prompt_template": "It is `{current_date}`, consider these travel options `{content}` and answer the `{user_question}`.",
"system_message": "You are a helpful travel assistant specialized in budget travel"
},
"basic_text": {
"llm_endpoint_params": {
"type": "openai_params",
"frequency_penalty": 1.5,
"presence_penalty": 1.5,
"stop": "<|im_end|>",
"temperature": 0,
"top_p": 1
},
"model": "azure__openai__gpt_4o_mini",
"num_tokens_for_completion": 8400,
"prompt_template": "It is `{current_date}`, consider these travel options `{content}` and answer the `{user_question}`.",
"system_message": "You are a helpful travel assistant specialized in budget travel"
},
"long_text": {
"embeddings": {
"model": "azure__openai__text_embedding_ada_002",
"strategy": {
"id": "basic",
"num_tokens_per_chunk": 64
}
},
"llm_endpoint_params": {
"type": "openai_params",
"frequency_penalty": 1.5,
"presence_penalty": 1.5,
"stop": "<|im_end|>",
"temperature": 0,
"top_p": 1
},
"model": "azure__openai__gpt_4o_mini",
"num_tokens_for_completion": 8400,
"prompt_template": "It is `{current_date}`, consider these travel options `{content}` and answer the `{user_question}`.",
"system_message": "You are a helpful travel assistant specialized in budget travel"
}
}