Understanding the Search Endpoint
Introduction
This section goes over all the parameters you need in order to POST to /layar/gpt/retrieval/search and the values contained in the response.
Parameters
{
"query": "What does JAK2 protein do?",
"embedder": "multi-qa-MiniLM-L6-cos-v1",
"retriever": {
"document": {
"indexName": "CGPTTextDocumentStore",
"reranker": true,
"searchRatio": 0.5,
"searchType": "hybrid",
"numHits": 5,
"relevanceThreshold": 0.2,
"lookupFilter": "documentId"
},
"table": {
"indexName": "CGPTTableStore",
"reranker": true,
"searchRatio": 0.5,
"searchType": "hybrid",
"numHits": 5,
"relevanceThreshold": 0.2,
"lookupFilter": "documentId"
}
},
"searchFilters" : [{
"documentId" : "AZWvMlBe-OBvyKYpiNE-",
"provider": "dldev02.vyasa.com",
"documentType": "TABLE",
"searchConditions" : [{"field" : "drug",
"operator": '==',
"value": 'humira'}
}]
]
}
query (required)
The RAG query that will be used to fetch relevant chunks.
embedder (required)
Directs the endpoint to only return chunks that were embedded with a specific model.
retriever (optional)
Two dictionaries that contains multiple values. These parameters allow you to determine how information is pulled from RAG, which helps the system retrieve relevant content to assist in answering the prompt. Documents and Tables are stored separately, because of this retriever has parameters for both.
document
index_name
A string specifying where the document is being stored. This value will always beCGPTTextDocumentStore when retrieving documents from RAG.
Index_name Considerations
In most use cases you will not need to provide an
index_name. When not provided, the default document or table store will be used.
reranker
A boolean value that causes a second sorting of relevant tokens to take place before the tokens are sent to the LLM. Turning this off can help improve the time it takes a response to be generated.
search_ratio
A floating-point number between 0 and 1. This value determines what sort of RAG search is used. There are two types of searches "Keyword search" or "Vector search".
Keyword search uses words from the given prompt and looks for phrases in RAG, which dictates what chunks to return to the LLM.
Vector search puts weight on the relevance of a specific token, even if it doesn't fully match words given in the prompt.
If this value isn't supplied, response generation will use a default of 0.5, which indicates balanced use of both search types. The lower the value, the more RAG will favor keyword search and higher will favor vector search.
Score Normalization
When using search_ratio, the ending score that is seen in the API response is normalized. This is because vector and keyword search both return different scores. The value of the search ratio is then used to produce a new score that favors either vector or keyword, depending on the value given.
Search_Ratio Suggestions
It's best to experiment with this value to help curate responses to your specific needs.
searchType
Allows you to determine what sort of chunk search is performed. The value must be one of three choices hybrid, vector, ore keyword
num_hits
An integer that determines how many relevant sections to pull from RAG.
Num_Hits Suggestion
Using higher values can cause unwanted information to be forwarded to the LLM, resulting in unwanted responses. Testing various values will help curate responses to your specific needs.
relevance_threshold
A floating-point number. This value determines the chunks obtained by RAG. The value defaults to .5 if not provided. Increasing the number will cause RAG to only pull chunks over a specific relevance_threshold, which can cause fewer chunks to be returned.
lookupFilter
A string specifying a documentId or savedListId . For more information on how to obtain this please view Upload Document or Create Document Set.
table
The table dictionary is very similar to document. The only difference is indexNamemust be CGPTTableStore.
searchFilters (required)
A list of nested JSON containing the document or set you wish to search along with the metadata search conditions.
documentId (required)
A string containing the documentId you want to search on. Required if savedListIdis not provided.
provider (required)
A string containing the provider the documents are contained in. For the most part this is going to be the URL of the environment.
documentType (required)
A string containing the document type the search will be targeting. This value can be two things either TABLE or DOCUMENT.
documentType With Mixed Sets
Sets you create may have a mix of
TABLEandDOCUMENTin them. In this case you must provide a search filter for bothTABLEandDOCUMENTin order to ensure you get chunks back from both types.
searchConditions (required)
A list of JSON dictionaries that contain the metadata filters.
field (required)
A string containing the field you want to filter on.
Nested JSON
Metadata can be nested JSON. Lets look at an example metadata JSON
{'Pubmed_Author' : 'D Schindler', 'Section' : 'abstract', 'Methodology' : { 'approach': 'double blind', 'centers': 5, 'locations' ['North America', 'Europe']}General structure for searching nested JSON is
parentkey_childkey.
If you wanted to filter forlocationsthefieldwould need to beMethodology_locations.
operator (required)
A string value detailing what operator should be used for the specific field. The valid operators are < , !=, >=, not in, in, like, >, ==, and <=. It's important to keep in mind what sort of data type is associated with the field.
For example, if the data type for the field is a list you can use not inand in but you can't use ==or the greater than / less than operators. Vice versa if the data type is an integer, you can't use in or not in.
value (required)
The specific value you are looking for that is in the fieldspecified.
Response
{
"search_results": [
{
"rawText": "Safety and Efficacy of the Xanomeline \nTransdermal Therapeutic System (TTS) in Patients with Mild to Moderate Alzheimer’s Disease 1. Introduction The M1 muscarinic-cholinergic receptor is 1 of 5 characterized muscarinic-cholinergic \nreceptor subtypes (Fisher and Barak 1994). M1 receptors in the cerebral cortex and \nhippocampus are, for the most part, preserved in Alzheimer’s disease (AD), while the \npresynaptic neurons projecting to these receptors from the nucleus basalis of Meynert \ndegenerate (Bierer et al. 1995). The presynaptic loss of cholinergic neurons has been \ncorrelated to the antimortum cognitive impairment in AD patients, prompting speculation \nthat replacement therapy with cholinomimetics will alleviate the cognitive dysfunction of \nthe disorder (Fisher and Barak 1994). Xanomeline is a novel M1 agonist which has shown high affinity for the M1 receptor \nsubtype (in transfected cells), and substantially less or no affinity for other muscarinic \nsubtypes. Positron emission tomography (PET) studies of 11C-labeled xanomeline in \ncynomolgus monkeys have suggested that the compound crosses the blood-brain barrier \nand preferentially binds the striatum and neocortex. Clinical development of an oral formulation of xanomeline for the indication of mild and \nmoderate AD was initiated approximately 4 years ago. A large-scale study of safety and \nefficacy provided evidence that an oral dosing regimen of 75 mg three times daily (TID) \nmay be associated with enhanced cognition and improved clinical global impression, \nrelative to placebo. As well, a dramatic reduction in psychosis, agitation, and other \nproblematic behaviors, which often complicate the course of the disease, was \ndocumented. However, the discontinuation rate associated with this oral dosing regimen \nwas 58.6%, and alternative clinical strategies have been sought to improve tolerance for \nthe compound. To that end, development of a Transdermal Therapeutic System (TTS) has been initiated. \nRelative to the oral formulation, the transdermal formulation eliminates high \nconcentrations of xanomeline in the gastrointestinal (GI) tract and presystemic (first-\npass) metabolism. Three transdermal delivery systems, hereafter referred to as the \nxanomeline TTS Formulation A, xanomeline TTS Formulation B, and xanomeline TTS \nformulation E have been manufactured by Lohman Therapy Systems GmbH of \nAndernach Germany. TTS Formulation A is 27 mg xanomeline freebase in a 25-cm2 matrix. TTS Formulation B is 57.6 mg xanomeline freebase in a 40-cm2 matrix. \nFormulation E has been produced in 2 patch sizes: 1) 54 mg xanomeline freebase with \n0.06 mg Vitamin E USP in a 50-cm2 matrix and 2) 27 mg xanomeline freebase with 0.03 \nmg Vitamin E USP in a 25-cm2 matrix. For a detailed description of the composition of Xanomeline (LY246708) H2Q-MC-LZZT(c) Copyright © 2006 Eli Lilly and Company \nClinical Study Protocol Document Page 6 these formulations please refer to Part II, Section 14 of the Xanomeline (LY246708) \nClinical Investigator’s Brochure. For characterization of the safety, tolerance, and \npharmacokinetics of xanomeline TTS Formulations A, B, and E, please refer to Part II, \nSections 7, 8, and 10 of the Xanomeline (LY246708) Clinical Investigator’s Brochure. \nFormulation E will be studied in this protocol, H2Q-MC-LZZT(c). Xanomeline (LY246708) H2Q-MC-LZZT(c) Copyright © 2006 Eli Lilly and Company \nClinical Study Protocol Document Page 7 2. Objectives 2.1. Primary Objectives The primary objectives of this study are • To determine if there is a statistically significant relationship (overall \nType 1 error rate, α=.05) between the change in both ADAS-Cog (see \nAttachment LZZT.2) and CIBIC+ (see Attachment LZZT.3) scores, and \ndrug dose (0, 50 cm2 [54 mg], and 75 cm2 [81 mg]). • To document the safety profile of the xanomeline TTS. 2.2. Secondary Objectives \nThe secondary objectives of this study are • To assess the dose-dependent improvement in behavior. Improved scores \non the Revised Neuropsychiatric Inventory (NPI-X) will indicate \nimprovement in these areas (see Attachment LZZT.4). • To assess the dose-dependent improvements in activities of daily living. \nImproved scores on the Disability Assessment for Dementia (DAD) will \nindicate improvement in these areas (see Attachment LZZT.5). • To assess the dose-dependent improvements in an extended assessment of \ncognition that integrates attention/concentration tasks. The Alzheimer’s \nDisease Assessment Scale-14 item Cognitive Subscale, hereafter referred \nto as ADAS-Cog (14), will be used for this assessment (see Attachment \nLZZT.2). • To assess the treatment response as a function of Apo E genotype. Xanomeline (LY246708) H2Q-MC-LZZT(c) Copyright © 2006 Eli Lilly and Company \nClinical Study Protocol Document Page 8 3. Investigational Plan",
"documentId": "AZJG44FGVDPvRiqB7N50::::dldev01.vyasa.com",
"score": 1.0,
"chunkId": "07709ae1-82be-5284-b282-10356fd18db3",
"paragraphId": 2,
"score_contribution": {
"keyword": [
8.314862
],
"vector": [
0.6323809
],
"rerank_score": [
5.4015737
]
}
},
{
"rawText": "3.1. Summary of Study Design \nPatients with probable mild to moderate AD will be studied in a randomized, double-\nblind, parallel (3 arm), placebo-controlled trial of 26 weeks duration. The study will be \nconducted on an outpatient basis. Approximately 300 patients will be enrolled (see \nSchedule of Events for Protocol H2Q-MC-LZZT(c), Attachment LZZT.1). Following informed consent, patients will be screened at Visit 1. At screening, patients \nwill undergo complete neuropsychiatric assessment, psychometric testing, and general \nmedical assessment (including medical history, pre-existing conditions, physical \nexamination). In addition, vital signs, temperature, medication history, \nelectrocardiogram (ECG), chest x-ray, and safety laboratories will be obtained. During \nthe screening visit, patients will wear a placebo TTS to determine willingness and ability \nto comply with transdermal administration procedures. If patients have not had central \nnervous system (CNS) imaging in the previous 12 months, a computed tomography (CT) \nor magnetic resonance imaging (MRI) scan will be obtained. If patients are insulin \ndependent diabetics, a hemoglobin A1c will be obtained. Screening exams and \nprocedures may be performed after Visit 1; however, their results must be completed and \navailable prior to randomization. The screening process should occur within 2 weeks of \nrandomization (Visit 3 of the study). Patients who meet enrollment criteria from Visit 1 will proceed to Visit 2 at which time \nthey will undergo a 24-hour Ambulatory ECG. At Visit 3 the Ambulatory ECG will be \nremoved and patients will be randomized to 1 of 3 treatment arms. The treatment arms \nwill include a placebo arm, a low-dose xanomeline arm (50 cm2 TTS Formulation E, 54 \nmg xanomeline), and a high-dose xanomeline arm (75 cm2 TTS Formulation E, 81 mg \nxanomeline). All patients receiving xanomeline will be started at 50 cm2 TTS \nFormulation E. For the first 8 weeks of treatment, patients will be assessed at clinic visits \nevery 2 weeks and, thereafter, at clinic visits every 4 weeks. Patients who discontinue \nprior to Visit 12 (Week 24) will be brought back for full efficacy assessments at or near \nto 24 weeks, whenever possible. A Data Safety Monitoring Board (DSMB), chaired by an external cardiologist, will meet \nafter 75, 150, 225, and 300 patients have completed 1 month of treatment. The DSMB \nwill review cardiovascular findings to decide if discontinuation of the study or any \ntreatment arm is appropriate, if additional cardiovascular monitoring is required, if \nfurther cardiovascular monitoring is unnecessary, or if adjustment of dose within a \ntreatment arm (or arms) is appropriate (see Section 3.9.4). At Visits 3, 8, 10, and 12, efficacy instruments (ADAS-Cog, CIBIC+, and DAD) will be \nadministered. NPI-X will be administered at 2-week intervals either at clinic visits or via \na telephone interview. Vital signs, temperature, and an assessment of adverse events will Xanomeline (LY246708) H2Q-MC-LZZT(c) Copyright © 2006 Eli Lilly and Company \nClinical Study Protocol Document Page 9 be obtained at all clinic visits. An electrocardiogram (ECG), and chemistry/hematology \nsafety labs will be obtained at Visits 4, 5, 7, 8, 9, 10, 11, 12, and 13. Urinalysis will be \ndone at Visits 4, 9, and 12. Use of concomitant medications will be collected at Visits 3, \n4, 5, 7, 8, 9, 10, 11, 12, and 13. Plasma levels of xanomeline and metabolites will be \nobtained at Visits 3, 4, 5, 7, 9, and 11. At Visits 3, 4, 5, 7, 8, 9, 10, 11, and 12, \nmedications will be dispensed to the patients. Visits 1 through 13 should be scheduled relative to Visit 3 (Week 0 - randomization). \nVisits 4, 5, 7, 8, and 13 should occur within 3 days of their scheduled date. Visits 9, 10, \n11, and 12 should occur within 4 days of their scheduled date. At Visit 13 patients will \nbe given the option to enter the open-label extension phase (see Section 3.10.3. Study \nExtensions). Visit 1 2 3 4 5 7 8 9 10 11 12Week -2 -.3 0 2 4 6 8 12 16 20 2413 26ScreenPlacebointerim analysis\n(50% complete)interim analysis\n(50% complete)50 cm2(54 mg)75 cm2(81 mg)50 cm2(54 mg) Figure LZZT.1. Illustration of study design for Protocol H2Q-MC-LZZT(c).",
"documentId": "AZJG44FGVDPvRiqB7N50::::dldev01.vyasa.com",
"score": 0.48904604,
"chunkId": "06b9f66e-4893-5c8b-bd19-63a85a49ac4f",
"paragraphId": 3,
"score_contribution": {
"keyword": [
5.1375847
],
"vector": [
0.31103456
],
"rerank_score": [
-0.15793051
]
}
},
{
"rawText": "Treatment-emergent adverse events (also referred to as treatment-emergent signs and \nsymptoms, or TESS) are defined as any event reported during the postrandomization Xanomeline (LY246708) H2Q-MC-LZZT(c) Copyright © 2006 Eli Lilly and Company \nClinical Study Protocol Document Page 47 period (Weeks 0 - 26) that is worse in severity than during the baseline period, or one that \noccurs for the first time during the postrandomization period. 4.5. Subgroup Analyses \nThe effect of age, gender, origin, baseline disease severity as measured by MMSE, Apo \nE, and patient education level upon efficacy will be evaluated if sample sizes are \nsufficient to warrant such analyses. For example, if all patients are Caucasian, then there \nis no need to evaluate the co-factor origin. The ANCOVA and ANOVA models \ndescribed above will be supplemented with terms for the main effect and interaction with \ntreatment. Each co-factor will be analyzed in separate models. The test for treatment-by-\nsubgroup interaction will address whether the response to xanomeline, compared with \nplacebo, is different or consistent between levels of the co-factor. 4.6. Interim Efficacy Analyses \nTwo interim efficacy analyses are planned. The first interim analysis will occur when \napproximately 50% of the patients have completed 8 weeks; the second interim analysis \nis to be conducted when approximately 50% of the patients have completed 24 weeks of \nthe study. The purpose of these interim analyses is to provide a rationale for the \ninitiation of subsequent studies of xanomeline TTS, or if the outcome is negative to stop \ndevelopment of xanomeline TTS. The method developed by Enas and Offen (1993) will \nbe used as a guideline as to whether or not to stop one treatment arm, or the study, to \ndeclare ineffectiveness. The outcome of the interim analyses will not affect in any way \nthe conduct, results, or analysis of the current study, unless the results are so negative \nthat they lead to a decision to terminate further development of xanomeline TTS in AD. \nHence, adjustments to final computed p-values are not appropriate. Planned interim analyses, and any unplanned interim analyses, will be conducted under \nthe auspices of the data monitoring board assigned to this study. Only the data \nmonitoring board is authorized to review completely unblinded interim efficacy and \nsafety analyses and, if necessary, to disseminate those results. The data monitoring board \nwill disseminate interim results only if absolutely necessary. Any such dissemination \nwill be documented and described in the final study report. Study sites will not receive \ninformation about interim results unless they need to know for the safety of their patients. 4.7. Interim Safety Analyses \nAn analysis of the cardiovascular safety monitoring (see section 3.9.4) will be performed \nwhen approximately 25 patients from each treatment arm have completed at least 2 \nweeks at the treatment arms’ respective full dosage (Visit 5). If necessary, this analysis \nwill be repeated every 25 patients per arm. This analysis will be conducted under the \nauspices of the DSMB. This board membership will be composed of 3 external Xanomeline (LY246708) H2Q-MC-LZZT(c) Copyright © 2006 Eli Lilly and Company \nClinical Study Protocol Document Page 48 cardiologists who will be the voting members of the board, a Lilly cardiologist, a Lilly \nstatistician, and the Lilly research physician in charge of the study. Only the DSMB is \nauthorized to review completely unblinded cardiovascular safety analyses and, if \nnecessary, to disseminate those results. The outcome of the cardiovascular safety \nanalyses will determine the need for further Ambulatory ECGs. 4.8. Pharmacokinetic/Pharmacodynamic Analyses \nPlasma concentrations of xanomeline will be determined from samples obtained at \nselected visits (Section 3.9.2). The plasma concentration data for xanomeline, dosing \ninformation, and patient characteristics such as weight, gender and origin will be pooled \nand analyzed using a population pharmacokinetic analysis approach (for example, \nNONMEM). This approach preserves the individual pharmacokinetic differences \nthrough structural and statistical models. The population pharmacokinetic parameters \nthrough the structural model, and the interindividual and random residual variability \nthrough the components of the statistical models will be estimated. An attempt will also \nbe made to correlate plasma concentrations with efficacy and safety data by means of \npopulation pharmacokinetic/pharmacodynamic modeling. Xanomeline (LY246708) H2Q-MC-LZZT(c) Copyright © 2006 Eli Lilly and Company \nClinical Study Protocol Document Page 49 5. Informed Consent, Ethical Review, and Regulatory \nConsiderations",
"documentId": "AZJG44FGVDPvRiqB7N50::::dldev01.vyasa.com",
"score": 0.4097227,
"chunkId": "71eaf141-ceae-54e8-9d4b-12a4d237cfee",
"paragraphId": 22,
"score_contribution": {
"keyword": [
3.4252913
],
"vector": [
0.3643101
],
"rerank_score": [
-1.3522785
]
}
},
{
"rawText": "[5] CNS imaging (CT scan or MRI of brain) compatible with AD within \npast 1 year. Xanomeline (LY246708) H2Q-MC-LZZT(c) Copyright © 2006 Eli Lilly and Company \nClinical Study Protocol Document Page 12 The following findings are incompatible with AD: a) Large vessel strokes 1) Any definite area of encephalomalacia consistent with ischemic \nnecrosis in any cerebral artery territory. 2) Large, confluent areas of encephalomalacia in parieto-occipital \nor frontal regions consistent with watershed infarcts. The above are exclusionary. Exceptions are made for small areas of \ncortical asymmetry which may represent a small cortical stroke or a \nfocal area of atrophy provided there is no abnormal signal intensity \nin the immediately underlying parenchyma. Only one such \nquestionable area allowed per scan, and size is restricted to ≤1cm in \nfrontal/parietal/temporal cortices and ≤2 cm in occipital cortex. b) Small vessel ischemia 1) Lacunar infarct is defined as an area of abnormal intensity seen \non CT scan or on both T1 and T2 weighted MRI images in the \nbasal ganglia, thalamus or deep white matter which is ≤1 cm in \nmaximal diameter. A maximum of one lacune is allowed per \nscan. 2) Leukoariosis or leukoencephalopathy is regarded as an \nabnormality seen on T2 but not T1 weighted MRIs, or on CT. \nThis is accepted if mild or moderate in extent, meaning \ninvolvement of less than 25% of cortical white matter. c) Miscellaneous 1) Benign small extra-axial tumors (ie, meningiomas) are accepted \nif they do not contact or indent the brain parenchyma. 2) Small extra-axial arachnoid cysts are accepted if they do not \nindent or deform the brain parenchyma. [6] Investigator has obtained informed consent signed by the patient \n(and/or legal representative) and by the caregiver. [7] Geographic proximity to investigator’s site that allows adequate \nfollow-up. [8] A reliable caregiver who is in frequent or daily contact with the patient \nand who will accompany the patient to the office and/or be available \nby telephone at designated times, will monitor administration of \nprescribed medications, and will be responsible for the overall care of \nthe patient at home. The caregiver and the patient must be able to \ncommunicate in English and willing to comply with 26 weeks of \ntransdermal therapy. Xanomeline (LY246708) H2Q-MC-LZZT(c) Copyright © 2006 Eli Lilly and Company \nClinical Study Protocol Document Page 13 3.4.2.2. Exclusion Criteria Patients will be excluded from the study for any of the following reasons: [9] Persons who have previously completed or withdrawn from this study \nor any other study investigating xanomeline TTS or the oral \nformulation of xanomeline. [10] Use of any investigational agent or approved Alzheimer’s therapeutic \nmedication within 30 days prior to enrollment into the study. [11] Serious illness which required hospitalization within 3 months of \nscreening. [12] Diagnosis of serious neurological conditions, including a) Stroke or vascular dementia documented by clinical history and/or \nradiographic findings interpretable by the investigator as indicative of \nthese disorders b) Seizure disorder other than simple childhood febrile seizures c) Severe head trauma resulting in protracted loss of consciousness \nwithin the last 5 years, or multiple episodes of head trauma d) Parkinson’s disease e) Multiple sclerosis f) Amyotrophic lateral sclerosis g) Myasthenia gravis. [13] Episode of depression meeting DSM-IV criteria within 3 months of \nscreening. [14] A history within the last 5 years of the following: a) Schizophrenia b) Bipolar Disease c) Ethanol or psychoactive drug abuse or dependence. [15] A history of syncope within the last 5 years. [16b] Evidence from ECG recording at screening of any of the following \nconditions : a) Left bundle branch block b) Bradycardia ≤50 beats per minute c) Sinus pauses >2 seconds d) Second or third degree heart block unless treated with a pacemaker Xanomeline (LY246708) H2Q-MC-LZZT(c) Copyright © 2006 Eli Lilly and Company \nClinical Study Protocol Document Page 14 e) Wolff-Parkinson-White syndrome f) Sustained supraventricular tachyarrhythmia including SVT≥10 sec, \natrial fibrillation, atrial flutter. g) Ventricular tachycardia at a rate of ≥120 beats per minute lasting \n≥10 seconds. [17] A history within the last 5 years of a serious cardiovascular disorder, \nincluding a) Clinically significant arrhythmia b) Symptomatic sick sinus syndrome not treated with a pacemaker c) Congestive heart failure refractory to treatment d) Angina except angina controlled with PRN nitroglycerin e) Resting heart rate <50 or >100 beats per minute, on physical exam f) Uncontrolled hypertension. [18] A history within the last 5 years of a serious gastrointestinal disorder, \nincluding a) Chronic peptic/duodenal/gastric/esophageal ulcer that are untreated \nor refractory to treatment b) Symptomatic diverticular disease c) Inflammatory bowel disease",
"documentId": "AZJG44FGVDPvRiqB7N50::::dldev01.vyasa.com",
"score": 0.40605038,
"chunkId": "d888daa3-b6a5-512b-a280-c12836d010b2",
"paragraphId": 5,
"score_contribution": {
"keyword": [
3.5597384
],
"vector": [
0.34869015
],
"rerank_score": [
-3.440978
]
}
},
{
"rawText": "t) Antiarrhythmics including but not limited to the following \n Adenocard® (adenosine) \n Cordarone® (amiodarone) \n Ethmozine® (moricizine) \n Mexitil® (mexiletine) \n Norpace® (disopyramide) \n Procan® (procainamide) \n Quinaglute® (quinidine) \n Rythmol® (propafenone) \n Tambocor® (flecainide) \n Tonocard® (tocainide) Xanomeline (LY246708) H2Q-MC-LZZT(c) Copyright © 2006 Eli Lilly and Company \nClinical Study Protocol Document Page 23 Requirement of these drugs for control of cardiac arrhythmia \nindicates that the patient should be excluded from the study. If \ndiscontinuation of an antiarrhythmic is considered, please discuss \ncase with CRO medical monitor. \n u) Miscellaneous drugs including but not limited to \n Coenzyme Q 2 weeks \n Eskalith®, Lithobid® (lithium) 2 weeks \n Ginkgo biloba 1 week \n Lecithin 1 week \n Lupron 2 weeks \n Tamoxifen 1 month \n v) Estrogen supplements are permitted during the study, but dosage \n must be stable for at least 3 months prior to enrollment. \n 3.4.2.3. Violation of Criteria for Enrollment The criteria for enrollment must be followed explicitly. If there is inadvertent enrollment \nof individuals who do not meet enrollment criteria, these individuals should be \ndiscontinued from the study. Such individuals can remain in the study only if there are \nethical reasons to have them continue. In these cases, the investigator must obtain \napproval from the Lilly research physician for the study participant to continue in the \nstudy (even if the study is being conducted through a contract research organization). 3.4.3. Disease Diagnostic Criteria \nProbable AD will be defined clinically by NINCDS/ADRDA guidelines as follows: • Diagnosis of probable AD as defined by National Institute of \nNeurological and Communicative Disorders and Stroke (NINCDS) \nand the Alzheimer’s Disease and Related Disorders Association \n(ADRDA) guidelines. • Mild to moderate severity of AD will be defined by the Mini-Mental \nState Exam as follows: • Mini-Mental State Examination (MMSE) score of 10 to 23. • The absence of other causes of dementia will be performed by clinical \nopinion and by the following: • Hachinski Ischemic Scale score of ≤4. Xanomeline (LY246708) H2Q-MC-LZZT(c) Copyright © 2006 Eli Lilly and Company \nClinical Study Protocol Document Page 24 • CNS imaging (CT scan or MRI of brain) compatible with AD \nwithin past 1 year (see Section 3.4.2.1). 3.4.4. Sample Size \nApproximately 100 patients will be randomized to each of the 3 treatment groups. \nPrevious experience with the oral formulation of xanomeline suggests that this sample \nsize has 90% power to detect a 3.0 mean treatment difference in ADAS-Cog (p<.05, two-\nsided), based on a standard deviation of 6.5. Furthermore, this sample size has 80% \npower to detect a 0.36 mean treatment difference in CIBIC+ (p<.05, two-sided), based on \na standard deviation of 0.9. 3.5. Patient Assignment \nCommencing at Visit 1, all patients will be assigned an identification number. This \nidentification number and the patient’s three initials must appear on all patient-related \ndocuments submitted to Lilly. When qualified for enrollment at Visit 3 the patient will be randomized to 1 of 3 \ntreatment arms. 3.6. Dosage and Administration 3.6.1. Materials and Supplies \nPrimary Study Material: Xanomeline TTS (adhesive patches) 50 cm2, 54 mg* \n 25 cm2, 27 mg* \nComparator Material: Placebo TTS Identical in appearance to primary study material \n*All doses are measured in terms of the xanomeline base. Patches should be stored at controlled room temperature, and all used patches must be \nhandled and disposed of as biohazardous waste. For a detailed description of the composition of these formulations please refer to Part II, \nSection 14 of the Xanomeline (LY246708) Clinical Investigator’s Brochure. 3.6.2. TTS Administration Procedures \nTo test acute tolerance of transdermal formulation, patients will have a TTS (placebo) \nadministered at the start of Visit 1, and removed at the conclusion of Visit 1. The \npatient’s and caregiver’s willingness to comply with 26 weeks of transdermal therapy \nshould be elicited, and those patients/caregivers unwilling to comply should be excluded. Xanomeline (LY246708) H2Q-MC-LZZT(c) Copyright © 2006 Eli Lilly and Company \nClinical Study Protocol Document Page 25 Upon enrollment at Visit 3, and on the morning of each subsequent day of therapy , \nxanomeline or placebo will be administered with the application of 2 adhesive patches, \none 50 cm2 in area, the other 25 cm2 in area. Each morning, prior to the application of the \npatches, hydrocortisone cream (1%) should be applied to the skin at the intended site of \nadministration, rubbed in, and allowed to penetrate for approximately 30 minutes. \nThereafter, excess cream should be wiped away and the patches applied.",
"documentId": "AZJG44FGVDPvRiqB7N50::::dldev01.vyasa.com",
"score": 0.65824616,
"chunkId": "98a93919-e277-5d79-985e-114bb39e39c2",
"paragraphId": 9,
"score_contribution": {
"keyword": [
5.8628693
],
"vector": [
0.44510782
],
"rerank_score": [
-8.789688
]
}
}
],
"embedder": "multi-qa-MiniLM-L6-cos-v1"
}
search_results
An array of dictionaries, each containing the chunk related to your query, the document the chunk was found in, and various similarity scores associated with the chunk in relation to the query.
raw_text
A string containing the text of the chunk.
documentId
A string containing the documentId as well as the provider. The formatting for this string is documentId::::provider.
score
The normalized similarity score of the chunk. This number uses both the keyword score and vector score along with the search ratio used at the time of the request.
chunkId
The unique ID of the chunk.
paragraphId
This represents the id of the paragraph that was contained in a specific document. The lower the number the closer to the start of the document the paragraph came from.
score_contribution
A dictionary containing the keyword, vector, and rerank score.
keyword
The keyword similarity score of the chunk in relation to the query used in the request.
vector
The vector similarity score of the chunk in relation to the query used in the request.
rerank_score
The similarity score after reranking occurs. This value only appears if reranker is set to true in the request body.
embedder
The embedding model that was used the chunk embedding, this will correspond to the embedderused in the request body.
Updated 29 days ago