Input path: /home/debian/html/nutritwin/output_llm/6891b30d8b865/input.json Output path: /home/debian/html/nutritwin/output_llm/6891b30d8b865/output.json Input text: Un verre de jus d'orange frais. DB path: __deriveddata__/DerivedObjects/Data/KcalMeDB_fr.sl3 Picto path: __deriveddata__/DerivedObjects/Data/PictoMatcherNetNG_fr.json Sport grounding path: __deriveddata__/DerivedObjects/Data/DerivedSportMET.json ================================================================================================================================== Prompt from user: Un verre de jus d'orange frais. ================================================================================================================================== ==================================== Prompt ============================================= Identify in this list of intents: ["Identify food and beverage consumption or declaration", "Identify the user physical activity", "Answer a nutrition question", "Other intent"], the intents of the prompt: ###Un verre de jus d'orange frais.###. Format the result in JSON format: {"intents": []}. ========================================================================================= ------------------------------ LLM Raw response ----------------------------- {"intents": ["Identify food and beverage consumption or declaration"]} ----------------------------------------------------------------------------- ----------------- Make it compliant ------------------ {"intents": ["Identify food and beverage consumption or declaration"]} ------------------------------------------------------ ERROR: wrong object representation: {'intents': ['Identify food and beverage consumption or declaration']} ------------------------ After simplification ------------------------ { "intents": [ "Identify food and beverage consumption or declaration" ] } ---------------------------------------------------------------------- ==================================== Prompt ============================================= Convert this natural language query : """Un verre de jus d'orange frais.""" into an array of JSON. Ignore what it is not connected to nutrition, beverage or food. Provide a solution without explanation. Use the following ontology and only this ontology described in this Turtle/RDF model: """ @prefix food: . @prefix rdfs: . @prefix xsd: . @prefix owl: . @prefix prov: . food: a owl:Ontology ; rdfs:comment "Definition of the food archetype"@en . food:name a owl:DatatypeProperty; rdfs:label "name"@en; rdfs:comment """Food or beverage identifier, the name should not contain information related to quantity or container (like glass...). Ignore food or beverage when it is not consumed in the past, now or in the future. The cooking mode is not in the name. The name is only in french."""@en; rdfs:range xsd:string. food:quantity a owl:DatatypeProperty ; rdfs:label "quantity"@en; rdfs:comment "The quantity of food or drink that is or was consumed. Quantity is only in french. Here are examples: 'un quignon', 'un cornet', 'un verre', 'une tranche', 'une boule', 'un', 'deux', 'trois',... Keep the same language."@en; rdfs:range xsd:string. food:cookingMethod a owl:DatatypeProperty ; rdfs:label "cooking method"@en; rdfs:comment "The cooking method of food. The cooking method is in french."@en; rdfs:range xsd:string. food:type a owl:DatatypeProperty ; rdfs:label "type of food"@en; rdfs:comment "Identify the type of food."@en; rdfs:range xsd:string. food:food a food:type ; rdfs:label "food" . food:beverage a food:type ; rdfs:label "beverage" . food:timeOfTheDay a owl:DatatypeProperty ; rdfs:label "time of the day"@en; rdfs:comment "Time of the day when food or drink was consumed."@en; rdfs:range xsd:string. food:breakfast a food:timeOfTheDay ; rdfs:label "breakfast" . food:lunch a food:timeOfTheDay ; rdfs:label "lunch" . food:snacking a food:timeOfTheDay ; rdfs:label "snacking" . food:dinner a food:timeOfTheDay ; rdfs:label "dinner" . food:brand a owl:DatatypeProperty ; rdfs:label "Brand"@en; rdfs:comment """Food or beverage brand. The restaurants are not brand. When the name is very known (ex: Activia, Coca) and the brand is not mentioned, guess the brand."""@en; rdfs:range xsd:string. food:company a owl:DatatypeProperty ; rdfs:label "Company"@en; rdfs:comment "Product company."@en; rdfs:range xsd:string. food:enumEvent a rdfs:Class . food:event a owl:DatatypeProperty ; rdfs:label "event"@en; rdfs:comment "Event of eating or drinking. Each must have an event"@en; rdfs:range food:enumEvent. food:intent a food:enumEvent ; rdfs:label "intent" . rdfs:comment "When the event should happen"@en. food:declaration a food:enumEvent ; rdfs:label "declaration" . rdfs:comment "When the event has already occured"@en. food:unknownEvent a food:enumEvent ; rdfs:label "unknown" ; rdfs:comment "When the event is unknown in the day"@en. food:event a owl:DatatypeProperty ; rdfs:label "event"@en; rdfs:comment "Event of eating or drinking. Each must have an event"@en; rdfs:range food:enumEvent. food:intent a food:enumEvent ; rdfs:label "intent" . rdfs:comment "When the event should happen"@en. food:declaration a food:enumEvent ; rdfs:label "declaration" . rdfs:comment "When the event has already occured"@en. food:unknownEvent a food:enumEvent ; rdfs:label "unknown" ; rdfs:comment "When the event is unknown in the day"@en. """ Here is an example of result: [ { "name": "blanquette de veau", "quantity": "un plat", "cookingMethod": "mijot\u00e9", "timeOfTheDay": "lunch", "company": "Leclerc", "type": "food", "event": "declaration" }, { "name": "eau", "brand": "Evian", "company": "Danone", "timeOfTheDay": "breakfast", "quantity": "un verre", "type": "beverage", "event": "intent" } ] ========================================================================================= ------------------------------ LLM Raw response ----------------------------- [ { "name": "jus d'orange frais", "quantity": "un verre", "type": "beverage", "event": "unknown" } ] ----------------------------------------------------------------------------- ----------------- Make it compliant ------------------ [ { "name": "jus d'orange frais", "quantity": "un verre", "type": "beverage", "event": "unknown" } ] ------------------------------------------------------ ------------------------ After simplification ------------------------ [ { "name": "jus d'orange frais", "quantity": "un verre", "type": "beverage", "event": "unknown" } ] ---------------------------------------------------------------------- --------------------------------- LLM result ----------------------------------- {'response': [{'name': "jus d'orange frais", 'quantity': 'un verre', 'type': 'beverage', 'event': 'unknown'}], 'cost': 0.09738} -------------------------------------------------------------------------------- ----------- result to be analyzed ----------- {'name': "jus d'orange frais", 'quantity': 'un verre', 'type': 'beverage', 'event': 'unknown'} First try: SELECT V_Name,V_Comment,V_NormName,V_NormComment,V_PackType,V_GTIN,V_GTINRef,V_ID,V_GlobalCount,V_NormTrademark,V_Trademark,V_NormAggr FROM KCALME_TABLE WHERE V_NormName LIKE '% ju orange frai %' AND (V_NormTrademark = '' OR V_NormTrademark IS NULL) --> CPU time in DB: 0.1260 seconds Word: Jus d'Orange Fraîchement Pressé - dist: 0.4303080141544342 - row: 40912 Word: Jus d'Orange Fraîchement Pressé à Froid - dist: 0.4437500834465027 - row: 55460 Word: Jus d'Orange, Mangue et Fraise - dist: 0.4661060571670532 - row: 1833 Word: Pur Jus d'Orange Fraîchement Pressé - dist: 0.4880441427230835 - row: 7206 Word: Jus d'Orange - dist: 0.49152639508247375 - row: 3845 Found embedding word: Jus d'Orange Fraîchement Pressé Traceback (most recent call last): File "/home/debian/html/nutritwin/resources/KCALLMMainService.py", line 71, in omess = KCALLMMain.runEvent(event) ^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/debian/html/nutritwin/resources/KCALLMMain.py", line 132, in runEvent resp = KCALLMMainSpeechToData.execute(speech, imagePath, image64, comment, appId, device, version, age, gender, longitude, latitude, test) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/debian/html/nutritwin/resources/KCALLMMainSpeechToData.py", line 39, in execute omess = executeLLMSingle(text, imagePath, image64, comment, model) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/debian/html/nutritwin/resources/KCALLMMainSpeechToData.py", line 195, in executeLLMSingle sols = KCALLMNutritionUtilities.getBestSolutions(jresult["response"], dbPath, dbEmbeddingPath, jVoca) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/debian/html/nutritwin/resources/KCALLMNutritionUtilities.py", line 395, in getBestSolutions dbCursor.execute(q) sqlite3.OperationalError: near "Orange": syntax error