h]ddlmZmZddlmZddlmZmZmZm Z m Z ddl m Z m Z mZGddeZGddeZGd d eZGd d Zy ))ListDict)Field) AtomicAgent AgentConfig BaseIOSchemaBaseToolBaseToolConfig) ChatHistorySystemPromptGeneratorBaseDynamicContextProviderc6eZdZUdZeddZeeed<y)BatchReviewSentimentInputSchemaz)Schema for multiple user review contents..z&List of text contents of user reviews. descriptionreviewsN) __name__ __module__ __qualname____doc__rrrstr__annotations__@/var/www/html/hubwallet-dev/src/core/batch_sentiment_analyzer.pyrr s 3 <GT#YrrceZdZUdZeddZeed<eddZe e eefed<eddZ e eefed <edd Z e eefed <y ) ReviewSentimentOutputSchemaa Schema for analyzed sentiment data from the review. overall_sentiment: One of (positive, negative, mixed, neutral) relevant_emotions_with_arousal: List of dict mapping emotion to arousal (e.g. [{"anger": "passive"}]) relevant_topics_sentiment: Dict mapping topics (e.g. Food Quality) to sentiment (e.g. "Positive") important_words_sentiment: Dict mapping important words to sentiment (e.g. {"delicious": "Positive"}) .z Overall sentiment of the review.roverall_sentimentz4List of relevant emotions with their arousal levels.relevant_emotions_with_arousalz"Sentiment for each relevant topic.relevant_topics_sentimentz8Sentiment for important words extracted from the review.important_words_sentimentN) rrrrrrrrrrrr r!rrrrrs#34VWsW;@ O<"Dc3h$816 =1tCH~16 S1tCH~rrc6eZdZUdZeddZeeed<y) BatchReviewSentimentOutputSchemaz9Schema for analyzed sentiment data from multiple reviews..zList of analysis results for each review containing: overall_sentiment, relevant_emotions_with_arousal, relevant_topics_sentiment, and important_words_sentimentr sentimentsN) rrrrrr$rrrrrrr#r#'s%C49  G5J01rr#c:eZdZddedefdZdeedeefdZy) BatchReviewSentimentAnalyzermodel temperaturectdggdddg}t||||}tttf||_y) a Initialize the BatchReviewSentimentAnalyzer for batch processing. Args: client: The LLM client (e.g., from instructor.from_openai) model: The model identifier to use temperature: Sampling temperature for the LLM zTYou are an expert sentiment analysis system that processes multiple reviews at once.)z7Analyze each review in the provided list independently.zFor each review, determine:z91. Overall sentiment (positive, negative, mixed, neutral)zG2. Relevant emotions with arousal levels (e.g., [{'anger': 'passive'}])z>3. Sentiment for relevant topics (Service, Food Quality, etc.)z* Evaluate each of the following topics: zBService Experience, Cleanliness & Hygiene, Ambiance & Atmosphere, zCPricing & Value, Online Ordering & Delivery, Complaint Resolution, z@Customer Loyalty, Menu Preferences, Waiting Time, Portion Size, zCStaff Friendliness, Payment Experience, Special Requests Handling, zDReservation Experience, Parking & Accessibility, Food Presentation, z2Seasonal Trends, Offer & Promotions, Food Quality.z.4. Sentiment for important words in the reviewzMMaintain the exact same order of reviews in your output as received in input.z3Return all results in a single structured response.zReturn a JSON object whose value is an array of JSON objects. Each object must have the keys: overall_sentiment (str), relevant_emotions_with_arousal (list of dict), relevant_topics_sentiment (dict), and important_words_sentiment (dict).uPDo not wrap the JSON in markdown or add any extra text—only emit the raw JSON.) backgroundstepsoutput_instructions)clientr'r(system_prompt_generator)configN)r rrrr#agent)selfr-r'r(r.r/s r__init__z%BatchReviewSentimentAnalyzer.__init__3s`#8f$Zc !+# <#$;   !!@Bb!bckqr rrreturncTt|}|jj|}|S)z Analyze multiple reviews in a single batch request. Args: reviews: List of review texts to analyze Returns: List of analysis results in the same order as input reviews )r)rr0run)r1r input_dataresults ranalyze_reviewsz,BatchReviewSentimentAnalyzer.analyze_reviewsbs'5WE  + rN)zgpt-4g?) rrrrfloatr2rrr8rrrr&r&2s6-sc-s%-s^tCyT:U5Vrr&N)typingrrpydanticr atomic_agentsrrrr r atomic_agents.contextr r r rrr#r&rrrr>sH [Z``l,( | >>r