Sample Files: AI-Complaint-Assistant with prompt - Revision history

Waghanna at 19:14, 9 April 2024

2024-04-09T19:14:14Z

← Older revision		Revision as of 19:14, 9 April 2024
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.		You can share your own app files on this page. Please include a brief description of your app files.

Waghanna at 00:55, 8 April 2024

2024-04-08T00:55:15Z

← Older revision		Revision as of 00:55, 8 April 2024
Line 3:		Line 3:
	==Sample App Files==		==Sample App Files==
	[[Media: Basic-Complaint-Assessment-with-prompt.zip]]		[[Media: Basic-Complaint-Assessment-with-prompt.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.

Waghanna: Waghanna moved page App Files: AI-Complaint-Assistant with prompt to Sample Files: AI-Complaint-Assistant with prompt without leaving a redirect

2024-04-07T21:29:04Z

Waghanna moved page App Files: AI-Complaint-Assistant with prompt to Sample Files: AI-Complaint-Assistant with prompt without leaving a redirect

← Older revision	Revision as of 21:29, 7 April 2024
(No difference)

Waghanna at 21:20, 7 April 2024

2024-04-07T21:20:25Z

@@ Line 1: / Line 1: @@
 You can share your own app files on this page. Please include a brief description of your app files.
 ==Sample App Files==
 [[Media: Basic-Complaint-Assessment-with-prompt.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.

Waghanna at 20:59, 7 April 2024

2024-04-07T20:59:32Z

← Older revision		Revision as of 20:59, 7 April 2024
Line 36:		Line 36:

	AI-ProblemSummaryPrompt: // Prompt that summarizes the product problem		AI-ProblemSummaryPrompt: // Prompt that summarizes the product problem

	AI-CountSummaryPrompt: // Prompt that counts the instances of items		AI-CountSummaryPrompt: // Prompt that counts the instances of items

	AI-ProblemSimilarityPrompt: // Prompt that summarizes the problem similarity to a product problem		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-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-ReportSummaryPrompt: // Prompt that summarizes the most similar problems
	AI-WordsPerReport: // Number of words in each intermediate report (recommended: 1500, range: 100-5000).
			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-ModelTemperature: // LLM Temperature index (recommended: 0.05, range: 0..1f)

	AI-ModelTopP: // LLM TOP_P index (recommended: 0.4, 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-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)		AI-ModelMaxOutputTokens: // LLM maximum output words (range: 1-2048)
	\|}		\|}

Waghanna at 20:58, 7 April 2024

2024-04-07T20:58:38Z

← Older revision		Revision as of 20:58, 7 April 2024
Line 11:		Line 11:
	\| <strong>Settings.txt</strong>		\| <strong>Settings.txt</strong>
	\|-		\|-
	\| CONFIG:OpenFDA-Vertex-V1.0 // identifies schema version (readonly)		\|
			CONFIG:OpenFDA-Vertex-V1.0 // identifies schema version (readonly)

	https_url1: // openFDA api for source data		https_url1: // openFDA api for source data

	limit1: // limit of query results		limit1: // limit of query results

	report_title: // title of output report		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, see openFDA device_search_fields.xlsx for full details of searchable fields
	date_received:~~[20200101+TO+20240315]~~
	device.device_report_product_code:~~(FMF)~~		date_received: // example field

			device.device_report_product_code: // example field

	SORT1-FIELD:SORT1-TERM // query results sorting		SORT1-FIELD:SORT1-TERM // query results sorting

Waghanna at 20:50, 7 April 2024

2024-04-07T20:50:50Z

← Older revision		Revision as of 20:50, 7 April 2024
Line 7:		Line 7:

	[[File: openFDA device_search_fields.xlsx]]		[[File: openFDA device_search_fields.xlsx]]


	{\| role="presentation" class="wikitable mw-collapsible mw-collapsed"		{\| role="presentation" class="wikitable mw-collapsible mw-collapsed"
Line 28:		Line 27:
	COUNT1-FIELD:COUNT1-TERM // query count field/term		COUNT1-FIELD:COUNT1-TERM // query count field/term

	~~AI CONFIGURATION & PROMPTS:~~
	AI-ProblemSummaryPrompt: // Prompt that summarizes the product problem		AI-ProblemSummaryPrompt: // Prompt that summarizes the product problem
	AI-CountSummaryPrompt: // Prompt that counts the instances of items		AI-CountSummaryPrompt: // Prompt that counts the instances of items

Waghanna at 20:49, 7 April 2024

2024-04-07T20:49:38Z

← Older revision		Revision as of 20:49, 7 April 2024
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~~
	\|}		\|}

Waghanna at 20:42, 7 April 2024

2024-04-07T20:42:27Z

@@ Line 8: / Line 8: @@
 [[File: openFDA device_search_fields.xlsx]]
-:SEARCH1-FIELDS:SEARCH1-TERMS   // query search fields and terms
+{| role="presentation" class="wikitable mw-collapsible mw-collapsed"
-:date_received:[20200101+TO+20240315]
+| <strong>Settings.txt</strong>
-:device.device_report_product_code:(FMF)
+|-
-:SORT1-FIELD:SORT1-TERM   // query results sorting
+|SEARCH1-FIELDS:SEARCH1-TERMS   // query search fields and terms
-:date_received:desc
+|date_received:[20200101+TO+20240315]
-:COUNT1-FIELD:COUNT1-TERM   // query count field/term
+|SORT1-FIELD:SORT1-TERM   // query results sorting
 </blockquote>

Waghanna at 20:35, 7 April 2024

2024-04-07T20:35:06Z

← Older revision		Revision as of 20:35, 7 April 2024
Line 9:		Line 9:

	;Settings.txt:		;Settings.txt:
	:CONFIG:OpenFDA-Vertex-V1.0 //identifies schema version		:CONFIG:OpenFDA-Vertex-V1.0 // identifies schema version
			:https_url1:api.fda.gov/device/event.json? // openFDA api for source data
	~~:Open FDA API Query specification:~~
	:https_url1:api.fda.gov/device/event.json?
	:limit1:100		:limit1:100

	~~:REPORT~~
	:report_title:Complaint Reportability Assessment		:report_title:Complaint Reportability Assessment
			:data1_fields: // data fields to be analyzed in MDR query results
			:KEYWORD1-SEARCH: // general keyword search terms (matched in any field)

	:~~// Data fields analyzed in MDR query results~~		:SEARCH1-FIELDS:SEARCH1-TERMS // query search fields and terms
	:~~data1_fields:product_problems, device.brand_name, patient.patient_problems, device.manufacturer_d_name, report_number, mdr_text.text~~

	~~:// General keyword search terms (in any field)~~
	~~:KEYWORD1~~-~~SEARCH:~~

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

	~~:// Query results sorting~~		:SORT1-FIELD:SORT1-TERM // query results sorting
	:SORT1-FIELD:SORT1-TERM
	:date_received:desc		:date_received:desc

	~~:// Query count field/term~~		:COUNT1-FIELD:COUNT1-TERM // query count field/term
	:COUNT1-FIELD:COUNT1-TERM

	:AI CONFIGURATION & PROMPTS:		:AI CONFIGURATION & PROMPTS: