Join BoxWorks 2024 to discover what's possible with content and AI!
Register now!The AI agent to be used for structured extraction.
ai_agent_extract_structured
The type of AI agent to be used for extraction.
Value is always ai_agent_extract_structured
AI agent tool used to handle basic text.
The parameters for the LLM endpoint specific to OpenAI / Google models.
azure__openai__gpt_3_5_turbo_16k
The model used for the AI agent for basic text. For specific model values, see the available models list.
8400
1
The number of tokens for completion.
(\{user_question\}[\s\S]*?\{content\}|\{content\}[\s\S]*?\{user_question\})
It is `{current_date}`, consider these travel options `{content}` and answer the `{user_question}`.
10000
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.
You are a helpful travel assistant specialized in budget travel
System messages try to help the LLM "understand" its role and what it is supposed to do.
AI agent tool used to to handle longer text.
openai__text_embedding_ada_002
The model used for the AI agent for calculating embeddings.
basic
The strategy used for the AI agent for calculating embeddings.
64
1
The number of tokens per chunk.
The parameters for the LLM endpoint specific to OpenAI / Google models.
azure__openai__gpt_3_5_turbo_16k
The model used for the AI agent for basic text. For specific model values, see the available models list.
8400
1
The number of tokens for completion.
(\{user_question\}[\s\S]*?\{content\}|\{content\}[\s\S]*?\{user_question\})
It is `{current_date}`, consider these travel options `{content}` and answer the `{user_question}`.
10000
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.
You are a helpful travel assistant specialized in budget travel
System messages try to help the LLM "understand" its role and what it is supposed to do.
{
"type": "ai_agent_extract_structured",
"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_3_5_turbo_16k",
"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": "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_3_5_turbo_16k",
"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"
}
}