Feature #3641
Updated by Ram Kordale 5 months ago
Let the first cell contain all inputs. Inputs are questions_file, model, index, board, grade, subject, chapter_num, styles (which is an array of strings) Also, set CONTEXT_SIZE to 40960. questions_file has the format: Chapter 1 E Chapter 2 E ... where E is of the format: E1 E2 ... where Ei is of format #$Exercise: <exercise#> (example: 1.2.5.1) #$Question: <question> #$Figure: <figure_list> [comment:List List of <GCS URLs> with name <exercise #>.1.jpg, <exercise #>.2.jpg...] #>.2.jpg... #$Answer: <answer> \-for every <style> in styles \--template[key, value] = ["stylexyz1abc", <style>] \--num_tokens=0 \--for every question in the file \--prompt=<question> \--response,num_tokens=call_openai_api(version=1.0, prompt, attachments, template, "temperature": 1, "max_tokens": 4096, "top_p": 1, "frequency_penalty": 0, "presence_penalty": 0, prompt) [comment: attachments = <figure_list>] are all the figures that need to be attached to the openai thread] \---if (num_tokens > CONTEXT_SIZE) num_tokens=0 \---styled_question = content between "###---###---###" \---store styled_question and answer with key <board>-<grade>-<subject>-<chapter>-<exercise>-<style> \---if <board>-<grade>-<subject>-<chapter>-<exercise>-standard does not exist \----store <question> and answer with key <board>-<grade>-<subject>-<chapter>-<exercise>-standard. You can start with a single entry file such as #$Exercise: 1.2.5.1 #$Question: Maya dyes dresses. She had to dye 30 dresses. She has so far finished 20 dresses. What fraction of dresses has she finished? #$Answer: 2/3