This week was focused on building an OpenAI API for text generation and integration with other project components. OpenAI’s text generation capabilities are extensive and offer a range of input modalities and model parameterization.\u00a0 In their tutorials and documentation, OpenAI “recommend[s] first attempting to get good results with prompt engineering, prompt chaining (breaking complex tasks into multiple prompts), and function calling.” To do so, I started by asking ChatGPT to “translate” ASL given syntactically ASL sentences. ChatGPT had a lot of success doing this correctly given isolates phrases without much context or prompting. I then went to\u00a0 describe my prompt as GPT will be used in the context of our project as follows:<\/p>\n
I will give you sequential single word inputs. Your objective is to correctly interpret a sequence of signed ASL words in accordance with ASL grammar and syntax rules and construct an appropriate english sentence translation. You can expect Subject, Verb, Object word order and topic-comment sentence structure. Upon receiving a new word input, you should respond with your best approximation of a complete English sentence using the words you’ve been given so far. Can you do that?<\/p><\/blockquote>\n
It worked semi successfully but ChatGPT had substantial difficulty moving away from the “conversational” context it’s expected to function within.<\/p>\n
So far, I’ve used ChatGPT-4 and some personal credits to work in the OpenAI API playground but would like to limit personal spending on LLM building and fine-tuning going forward. I would like to use credits towards gpt-3.5-turbo since fine-tuning for GPT-4 is in an experimental access program and for the scope of our project, I expect gpt-3.5-turbo to be a robust model for in terms of accurate translation results.<\/span><\/p>\n
from openai import OpenAI\r\nclient = OpenAI()<\/code>\r\n\r\nbehavior = \"You are an assistant that receives word by word inputs and interprets them in accordance with ASL grammatical syntax. Once a complete sentence can be formed, that sentence should be sent to the user as a response. If more than 10 seconds have passed since the last word, you should send a response to the user with the current sentence.\"\r\nresponse = client.chat.completions.create(\r\nmodel=\"gpt-3.5-turbo\",\r\nmessages=[\r\n{\"role\": \"system\", \"content\": behavior},\r\n{\"role\": \"user\", \"content\": \"last\"},\r\n{\"role\": \"user\", \"content\": \"year\"},\r\n{\"role\": \"user\", \"content\": \"me\"},\r\n{\"role\": \"user\", \"content\": \"went\"},\r\n{\"role\": \"user\", \"content\": \"Spain\"},\r\n{\"role\": \"assistant\", \"content\": \"I went to Spain a year ago.\"},\r\n{\"role\": \"user\", \"content\": \"where\"}\r\n])<\/code><\/pre>\nThe system message helps set the behavior of the assistant.<\/p>\n
eventually, we would like to use an Openai text generation model such that we provide word inputs as a stream and only receive text in complete English sentences.<\/p>\n
SVO (Subject, Verb, Object) is the most common sentence word order in ASL and\u00a0Object, Subject, Verb (OSV) necessarily uses non-manual features (facial expression) to\u00a0introduce the object of a sentence as the topic. As a result, we will restrict the scope of our current LLM to successfully interpreting SVO sign order.<\/p>\n","protected":false},"excerpt":{"rendered":"
This week was focused on building an OpenAI API for text generation and integration with other project components. OpenAI’s text generation capabilities are extensive and offer a range of input modalities and model parameterization.\u00a0 In their tutorials and documentation, OpenAI “recommend[s] first attempting to get good results with prompt engineering, prompt chaining (breaking complex tasks … <\/p>\n