Jump to content

Sample Files: AI-Complaint-Assistant with prompt: Difference between revisions

m
no edit summary
mNo edit summary
mNo edit summary
Line 12: Line 12:
| <strong>Settings.txt</strong>
| <strong>Settings.txt</strong>
|-
|-
| CONFIG:OpenFDA-Vertex-V1.0  // identifies schema version
| CONFIG:OpenFDA-Vertex-V1.0  // identifies schema version (readonly)
|https_url1:api.fda.gov/device/event.json?   // openFDA api for source data
https_url1:  // openFDA api for source data
|limit1:100
limit1:   // limit of query results
|report_title:Complaint Reportability Assessment
report_title:   // title of output report
|data1_fields:  // data fields to be analyzed in MDR query results
data1_fields:  // data fields to be analyzed in MDR query results
|KEYWORD1-SEARCH:  // general keyword search terms (matched in any field)
KEYWORD1-SEARCH:  // general keyword search terms (matched in any field)


|SEARCH1-FIELDS:SEARCH1-TERMS  // query search fields and terms
SEARCH1-FIELDS:SEARCH1-TERMS  // query search fields and terms
|date_received:[20200101+TO+20240315]
date_received:[20200101+TO+20240315]
|device.device_report_product_code:(FMF)
device.device_report_product_code:(FMF)


|SORT1-FIELD:SORT1-TERM  // query results sorting
SORT1-FIELD:SORT1-TERM  // query results sorting
|date_received:desc
date_received:desc


|COUNT1-FIELD:COUNT1-TERM  // query count field/term
COUNT1-FIELD:COUNT1-TERM  // query count field/term


|AI CONFIGURATION & PROMPTS:
AI CONFIGURATION & PROMPTS:
|// Prompt that summarizes the product problem
AI-ProblemSummaryPrompt:  // Prompt that summarizes the product problem
|AI-ProblemSummaryPrompt:Describe the following product problem in a couple of sentences. Include essential details.
AI-CountSummaryPrompt:   // Prompt that counts the instances of items
|// Prompt that counts the instances of items
AI-ProblemSimilarityPrompt:   // Prompt that summarizes the problem similarity to a product problem
|AI-CountSummaryPrompt:List each unique item along with the count for each item.
AI-MDRSimilarityPrompt:   // Prompt that analyzes the similarity between input problem and MAUDE results matching query criteria
|// Prompt that summarizes the problem similarity to a product problem
AI-ReportSummaryPrompt:   // Prompt that summarizes the most similar problems  
|AI-ProblemSimilarityPrompt:Analyze the similarity of this problem ({{problem_input}}) to the following problem. Use semantic similarity measurement. Present the result with the similarity score as a percentage followed by a concise explanation of the similarity score.
AI-WordsPerReport:   // Number of words in each intermediate report (recommended: 1500, range: 100-5000).
|// Prompt that analyzes the similarity between input problem and MAUDE results matching query criteria
AI-ModelTemperature:   // LLM Temperature index (recommended: 0.05, range: 0..1f)
|AI-MDRSimilarityPrompt:Match the most similar problem reports to this ({{problem_input}}). Include all important details. Include all reference numbers. Include the similarity scores as a percentage. Explain the similarities. Use semantic similarity measurements. Present results in descending similarity scores. For each matching result, include the matching report number followed by the similarity score followed by a brief description of the problem followed by an explanation of the similarities.
AI-ModelTopP:   // LLM TOP_P index (recommended: 0.4, range: 0..1f)
|// Prompt that summarizes the most similar problems
AI-ModelTopK:   // LLM TOP_K number of words for next word prediction (recommended: 10, range: 1-128)
|AI-ReportSummaryPrompt: List the top matching problem reports with the highest similarity scores. Include all details about the matching problems.
AI-ModelMaxOutputTokens:   // LLM maximum output words (range: 1-2048)
|// Maximum number of words in each intermediate report.  
|AI-WordsPerReport:1500
|// LLM Pro-Vision temperature index (0..1f)
|AI-ModelTemperature:0.05
|// LLM Pro-Vision TOP_P index (0..1f)
|AI-ModelTopP:0.4
|// LLM Pro-Vision TOP_K (Number of words for next word prediction)
|AI-ModelTopK:10
|// LLM Maximum output words (1..2048)
|AI-ModelMaxOutputTokens:2048
|}
|}