Sample Files: AI-Complaint-Assistant for document: Difference between revisions

Latest revision as of 19:14, 9 April 2024

Note: Community members can edit this page.

You can share your own app files on this page. Please include a brief description of your app files.

Sample App Files[edit]

Media: Basic-Complaint-Assessment-for-document.zip Description: Settings include MAUDE filters on product code (FMF) and date range (from 2020 to present). Prompts for matching the given complaint information against the top similar product problem codes, and the most similar individual MAUDE reports using semantic similarity evaluation.

@@ Line 1: / Line 1: @@
+<blockquote> <div style="background: Lavender; padding: 20px; border: 1px solid gray;">'''Note:''' Community members can edit this page.</div></blockquote>
 You can share your own app files on this page. Please include a brief description of your app files.
-<blockquote>
-'''''Reference files'''''
-[[File: ComplaintAssessmentDocument-Schema.zip]]
-[[File: openFDA device_search_fields.xlsx]]
-{| role="presentation" class="wikitable mw-collapsible mw-collapsed"
-| <strong>Settings.txt</strong>
-|-
-|
-CONFIG:OpenFDA-Vertex-V1.0   // identifies schema version (readonly)
-https_url1:   // openFDA api for source data
-limit1:   // limit of query results
-report_title:   // title of output report
-data1_fields:   // data fields to be analyzed in MDR query results
-KEYWORD1-SEARCH:   // general keyword search terms (matched in any field)
-SEARCH1-FIELDS:SEARCH1-TERMS   // query search fields and terms, see openFDA device_search_fields.xlsx for full details of searchable fields
-date_received:  // example field
-device.device_report_product_code:  // example field
-SORT1-FIELD:SORT1-TERM   // query results sorting
-date_received:desc
-COUNT1-FIELD:COUNT1-TERM   // query count field/term
-AI-ProblemSummaryPrompt:   // Prompt that summarizes the product problem
-AI-CountSummaryPrompt:   // Prompt that counts the instances of items
-AI-ProblemSimilarityPrompt:   // Prompt that summarizes the problem similarity to a product problem
-AI-MDRSimilarityPrompt:   // Prompt that analyzes the similarity between input problem and MAUDE results matching query criteria
-AI-ReportSummaryPrompt:   // Prompt that summarizes the most similar problems
-AI-WordsPerReport:   // Number of words in each intermediate report (recommended: 1500, range: 100-5000)
-AI-ModelTemperature:   // LLM Temperature index (recommended: 0.05, range: 0..1f)
-AI-ModelTopP:   // LLM TOP_P index (recommended: 0.4, range: 0..1f)
-AI-ModelTopK:   // LLM TOP_K number of words for next word prediction (recommended: 10, range: 1-128)
-AI-ModelMaxOutputTokens:   // LLM maximum output words (range: 1-2048)
-|}
-</blockquote>
 ==Sample App Files==
 [[Media: Basic-Complaint-Assessment-for-document.zip]]
-Description: Settings includes filter on product code FMF and date range from 2020 to present. Prompts for matching top similar product problem codes and individual MAUDE reports using semantic similarity.
+Description: Settings include MAUDE filters on product code (FMF) and date range (from 2020 to present). Prompts for matching the given complaint information against the top similar product problem codes, and the most similar individual MAUDE reports using semantic similarity evaluation.