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

Sample Files: AI-Complaint-Assistant with prompt (edit)

Revision as of 20:30, 7 April 2024

27 bytes added , 7 April 2024

m

no edit summary

Waghanna

Bureaucrats, Interface administrators, Administrators

326

edits

@@ Line 5: / Line 5: @@
 [[File: ComplaintAssessmentPrompt-Schema.zip]]
 [[File: openFDA device_search_fields.xlsx]]
-<code>
-Settings.txt:
-CONFIG:OpenFDA-Vertex-V1.0   //identifies schema version
-Open FDA API Query specification:
+;Settings.txt:
-https_url1:api.fda.gov/device/event.json?
+:CONFIG:OpenFDA-Vertex-V1.0   //identifies schema version
-limit1:100
-REPORT
+:Open FDA API Query specification:
-report_title:Complaint Reportability Assessment
+:https_url1:api.fda.gov/device/event.json?
+:limit1:100
-// Data fields analyzed in MDR query results
+:REPORT
-data1_fields:product_problems, device.brand_name, patient.patient_problems, device.manufacturer_d_name, report_number, mdr_text.text
+:report_title:Complaint Reportability Assessment
-// General keyword search terms (in any field)
+:// Data fields analyzed in MDR query results
-KEYWORD1-SEARCH:
+:data1_fields:product_problems, device.brand_name, patient.patient_problems, device.manufacturer_d_name, report_number, mdr_text.text
-// Query search fields and terms
+:// General keyword search terms (in any field)
-SEARCH1-FIELDS:SEARCH1-TERMS
+:KEYWORD1-SEARCH:
-date_received:[20200101+TO+20240315]
-device.device_report_product_code:(FMF)
-// Query results sorting
+:// Query search fields and terms
-SORT1-FIELD:SORT1-TERM
+:SEARCH1-FIELDS:SEARCH1-TERMS
-date_received:desc
+:date_received:[20200101+TO+20240315]
+:device.device_report_product_code:(FMF)
-// Query count field/term
+:// Query results sorting
-COUNT1-FIELD:COUNT1-TERM
+:SORT1-FIELD:SORT1-TERM
+:date_received:desc
-AI CONFIGURATION & PROMPTS:
+:// Query count field/term
-// Prompt that summarizes the product problem
+:COUNT1-FIELD:COUNT1-TERM
-AI-ProblemSummaryPrompt:Describe the following product problem in a couple of sentences. Include essential details.
-// Prompt that counts the instances of items
+:AI CONFIGURATION & PROMPTS:
-AI-CountSummaryPrompt:List each unique item along with the count for each item.
+:// Prompt that summarizes the product problem
-// Prompt that summarizes the problem similarity to a product problem
+:AI-ProblemSummaryPrompt:Describe the following product problem in a couple of sentences. Include essential details.
-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.
+:// Prompt that counts the instances of items
-// Prompt that analyzes the similarity between input problem and MAUDE results matching query criteria
+:AI-CountSummaryPrompt:List each unique item along with the count for each item.
-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.
+:// Prompt that summarizes the problem similarity to a product problem
-// 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-ReportSummaryPrompt: List the top matching problem reports with the highest similarity scores. Include all details about the matching problems.
+:// Prompt that analyzes the similarity between input problem and MAUDE results matching query criteria
-// Maximum number of words in each intermediate report.
+: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-WordsPerReport:1500
+:// Prompt that summarizes the most similar problems
-// LLM Pro-Vision temperature index (0..1f)
+:AI-ReportSummaryPrompt: List the top matching problem reports with the highest similarity scores. Include all details about the matching problems.
-AI-ModelTemperature:0.05
+:// Maximum number of words in each intermediate report.
-// LLM Pro-Vision TOP_P index (0..1f)
+:AI-WordsPerReport:1500
-AI-ModelTopP:0.4
+:// LLM Pro-Vision temperature index (0..1f)
-// LLM Pro-Vision TOP_K (Number of words for next word prediction)
+:AI-ModelTemperature:0.05
-AI-ModelTopK:10
+:// LLM Pro-Vision TOP_P index (0..1f)
-// LLM Maximum output words (1..2048)
+:AI-ModelTopP:0.4
-AI-ModelMaxOutputTokens:2048
+:// LLM Pro-Vision TOP_K (Number of words for next word prediction)
-</code>
+:AI-ModelTopK:10
+:// LLM Maximum output words (1..2048)
+:AI-ModelMaxOutputTokens:2048
 </blockquote>