Hatun simi modelokunawan (LLM) mana tukukuq sasachakuyqa, mana yachay atina lluqsiyta ruruchiy munasqankum. Allin ruwasqa tapuykuna kaptinpas, LLMkuna sapa kuti suyasqakunamanta karunchakunku, chaymanta lluqsiyninkuta sasata wakmanta llamk'achinapaq utaq llamkana puriykunaman tinkinapaq. Aswan mana allinqa, chay ruwasqakunaqa sapa kutim mana yapamanta ruway atiychu, chaymi sasachakun urayman ruwaypi.

Kay blog qillqapi, estructurasqa meta-tapuyta maskayku , huk técnica mayqinchus dinamicamente JSON esquemakunata solucionkunapaq ruwan manaraq ruwanakuna ruwachkaspa. Kayqa yanapakun aswan wakmanta llamk'achinapaq, atikuq, chaymanta ñawpaqmanta willay atiy tapuykunata ruwayta.

Ukun

Yaqa llapan kunan pacha LLMkuna kunan huk JSON lluqsiy ruwayta qunku, ichaqa ruwasqakuna mana sapa kutichu huk suyasqa esquemaman tupan. Ruwaqkuna sapa kuti mecanismokuna qhaway-hinallataq-watiqmanta ruwayta recurrinku, mayqinkunachus pachata hapinku, chaninniyuq, chaymanta ruwaqpa experiencian p'akinankupaq.

gpt4o kaqwan, OpenAI riqsichirqa estructurasqa lluqsiykunata mayqinkunachus garantizarqanku lluqsiy huk ruwaqpa qusqan JSON esquemaman tupananta. Manaña chiqap detallekuna willasqachu kanku chaypas, kayqa yaqapaschá chayasqa kanman huk combinación decodificación constreñida nisqawan chaymanta pre-muestra logit sesgo nisqawan. Chayhina atiykuna huk yanapakuykunawan qusqa kanku imaynachus pusay, esquemakuna, tikray, CommandR, SGLang. Kay ruwanakuna ruwaqkunata atiyta qun lluqsiykunata JSON esquemakunaman pusanankupaq, sapa sapalla rantinakuyniyuq.

¿Imataq meta-prompting estructurado nisqa?

Estructurado meta-prompting nisqaqa ima técnica nisqapas LLM nisqawanmi llamk'achin, manaraq huk allichayta ruwachkaspa, huk sasachakuymanta estructurasqa willayta dinamicamente ruwananpaq. Kay métodoqa achka ventajakunata qun directa prompting kaqmanta:

1. Dinamico : Lluqsiy estructurakuna purichiy pachapi ruwasqa kanku llamkana willakuykunapi hapipakuspa, aswan sinchi codificado utaq allin allichasqa modelo kaqpi.
2. Adaptable : Ruwasqa esquema runap ñawirinapaq kachkan chaymanta runa utaq wak LLMkuna qhawayta, chiqaqchayta utaq tikrayta atinku.
3. Wakmanta llamk'achiy atiy : Esquema waqaychasqa kanman chaymanta wakmanta llamk'achiy atikunman achka ruwanakunapi, purichiykunapi, makinakunapipas.
4. Predecible : Soluciones nisqakunaqa allin chuyanchasqa estructura nisqamanmi tupanqa, chaymi allin kanqa urayman yupaypaq.

Código

Huk ejemplota purisun maypi meta-prompting estructurado nisqawan yanapachikunchik huk esquema ruwanapaq musuq aswan rantisqa espía thriller novelapaq.

Kay blog qillqapaq tukuy codigoqa kay Colab Cuadernopim kachkan .

1. Huk estructurata paqarichiy

dÑawpaq kaq ruwayqa huk JSON esquema nisqamanta riqsichiymi, chaymi munasqa lluqsiyta willan. Kayta ruwanapaq, huk JSON esquemata ruwasaqku huk JSON esquemapaq — allinta, huk meta-esquema ! Kayqa especificación kaqpa huknin hina qusqa ichaqa wakin tikraykunata ruwanayku tiyan.

1.1 Meta-esquema nisqapi allinchakuy

OpenAI chaymanta Cohere kaqpa ruwasqa lluqsiy APIkuna achka harkaykuna JSON esquemakuna estándar kaqpi churan. Kayqa ancha llakikuypaqmi ichaqa imapas kunankama llamk’ayta atisunman. Meta-esquema nisqatam allichasaqku tupachiyta qhawanapaq:

 from jsonschema import Draft202012Validator def openai_compatible_metaschema(schema: Dict[str, object]): schema["type"] = "object" del schema["allOf"] return schema openai_json_metaschema = openai_compatible_metaschema( copy.deepcopy(Draft202012Validator.META_SCHEMA) )

Qhaway *: Rikukun* inversión mana ima chayhina harkaykunayuqchu chaymanta arbitrario JSON esquemakunata yanapan...ichaqa manaraqmi llapa runaman yaykuy!

1.2 Meta-tapuyninchikman harkakuykunata yapay

Chaymanta, kamachiykunata tapuyman yaykuchiyku chaymanta ruwasqa JSON esquema OpenAI harkayninkunaman hapipakun. Kay hina:

• Llapan chakrakunam mañasqa kanan.
• Imakunapas nido ukhupi, hatun kayninpipas limiteyuqmi.
• Yanapakuq kaqninkunaqa manam saqisqachu kanan ( "additionalProperties": false ).

 system_guidelines = "\n".join( [ "All fields must be required - To use Structured Outputs, all fields or function parameters must be specified as required. NOTE: Although all fields must be required (and the model will return a value for each parameter), it is possible to emulate an optional parameter by using a union type with null." "Objects have limitations on nesting depth and size - A schema may have up to 100 object properties total, with up to 5 levels of nesting.", "Limitations on total string size - In a schema, total string length of all property names, definition names, enum values, and const values cannot exceed 15,000 characters.", "Limitations on enum size - A schema may have up to 500 enum values across all enum properties. For a single enum property with string values, the total string length of all enum values cannot exceed 7,500 characters when there are more than 250 enum values.", "additionalProperties: false must always be set in objects - additionalProperties controls whether it is allowable for an object to contain additional keys / values that were not defined in the JSON Schema. Structured Outputs only supports generating specified keys / values, so we require developers to set additionalProperties: false to opt into Structured Outputs.", "Some type-specific keywords are not yet supported - Notable keywords not supported include: For strings: minLength, maxLength, pattern, format; For numbers: minimum, maximum, multipleOf; For objects: patternProperties, unevaluatedProperties, propertyNames, minProperties, maxProperties; For arrays: unevaluatedItems, contains, minContains, maxContains, minItems, maxItems, uniqueItems", "For anyOf, the nested schemas must each be a valid JSON Schema per this subset", "Definitions are supported - You can use definitions to define subschemas which are referenced throughout your schema. The following is a simple example.", "Recursive schemas are supported - Sample recursive schema using # to indicate root recursion.", ] )

1.3 Meta-tapuyta churay

Kunanqa meta-tapuyta riqsichiyku huk JSON esquema ruwanapaq espía thriller esquemapaq

 from langchain.prompts import ChatPromptTemplate task_description = "Write an outline for a bestselling spy thriller novel" task_guidelines = """ - You must follow one of the six basic story arcs: Rags to riches, Riches to rags, Icarus, Oedipus, Cinderella, Man in a hole - Outputs must include characters, plot points (including exposition, rising action, climax, falling action, and resolution), central conflict, setting, major turning points or "beats," character arcs, and a synopsis of the story; essentially, a detailed breakdown of the key elements that will drive the narrative throughout the novel. """ prompt_messages = ChatPromptTemplate.from_messages( [ ( "system", "You are an expert in creating JSON schemas. You have been asked to generate a detailed JSON schema for the output of a given task based based on a task desciption and some guidelines.", ), ( "system", "Your JSON schema must always adhere to the following system system guidelines for JSON schemas:\n<system_guidelines>\n{system_guidelines}\n</system_guidelines>", ), ( "user", "Use the task description and guidelines below to generate an output JSON schema for the following task based on the guidelines provided.\n\n<task_description>\n{task_description}\n</task_description>\n\n<guidelines>\n{task_guidelines}\n</guidelines>", ), ] )

1.4 Ruwayta paqarichiy

LLM nisqatam waqyayku esquemata ruwanapaq:

 messages = prompt_messages.format_messages( system_guidelines=system_guidelines, task_description=task_description, task_guidelines=task_guidelines ) ## Make sure to set up OPENAI_API_KEY in your Colab Secrets ## https://x.com/GoogleColab/status/1719798406195867814 client = OpenAI(api_key=userdata.get('OPENAI_API_KEY')) model = "gpt-4o" metaprompt_completion = client.beta.chat.completions.parse( model=model, messages=convert_to_penai_messages(messages), response_format={ "type": "json_schema", "json_schema": JSONSchema( name="JsonMetaschema", description="JSON Metaschema for the 2020-12 Draft of the JSON Schema specification that can be used to validate JSON data", schema=openai_json_metaschema, strict=False, ) } ) task_output_schema = json.loads(metaprompt_completion.choices[0].message.content) print(json.dumps(task_output_schema, indent=2))

 { "$schema": "https://json-schema.org/draft/2020-12/schema", "title": "Outline for a Bestselling Spy Thriller Novel", "type": "object", "properties": { "storyArc": { "type": "string", "enum": [ "Rags to riches", "Riches to rags", "Icarus", "Oedipus", "Cinderella", "Man in a hole" ] }, "characters": { "type": "array", "items": { "type": "object", "properties": { "name": { "type": "string" }, "role": { "type": "string" }, "description": { "type": "string" }, "arc": { "type": "string" } }, "required": ["name", "role", "description", "arc"], "additionalProperties": false }, "minItems": 1 }, "plotPoints": { "type": "object", "properties": { "exposition": { "type": "string" }, "risingAction": { "type": "string" }, "climax": { "type": "string" }, "fallingAction": { "type": "string" }, "resolution": { "type": "string" } }, "required": [ "exposition", "risingAction", "climax", "fallingAction", "resolution" ], "additionalProperties": false }, "centralConflict": { "type": "string" }, "setting": { "type": "string" }, "majorTurningPoints": { "type": "array", "items": { "type": "string" }, "minItems": 1 }, "characterArcs": { "type": "object", "properties": { "protagonistArc": { "type": "string" }, "antagonistArc": { "type": "string" }, "supportingCharactersArcs": { "type": "array", "items": { "type": "string" }, "minItems": 0 } }, "required": [ "protagonistArc", "antagonistArc", "supportingCharactersArcs" ], "additionalProperties": false }, "synopsis": { "type": "string" } }, "required": [ "storyArc", "characters", "plotPoints", "centralConflict", "setting", "majorTurningPoints", "characterArcs", "synopsis" ], "additionalProperties": false }

Kunanqa huk esquemayuqmi kayku, chaymi willakun espía thriller novelaykupa bosquejonmanta. Kayqa willañiqipi icha willay tantanapipas takyachisqa kanman.

2. Huk allichayta paqarichiy

2.1 Tapukuy churay

Esquema nisqawanmi novelapa esquema nisqapaq tapuyta riqsichinchik. wakin básica ruway pukllaymanta tapuykunata chaymanta kamachiykunata llamk'achisaqku:

 user_requirements = "Tell a story about counter-intelligence operative working against the clock. The novel should be extremely realistic, slow burn." task_prompt = ChatPromptTemplate.from_messages( [ ( "system", "You are a world-renowned author that has written dozens of bestselling thriller novels. Your task is to create an outline for a new novel based on the user's requirements.", ), ( "user", "Please write a novel outline based strictly on the following requirements <requirements>{requirements}</requirements>", ), ] ) task_completion = client.beta.chat.completions.parse( model=model, messages=convert_to_openai_messages(task_prompt.format_messages(requirements=user_requirements)), response_format={ "type": "json_schema", "json_schema": JSONSchema( ## TODO: You can change this depending your task name="ThrillerNovelOutlineSchema", description="A schema for outlining a new novel", schema=task_output_schema, strict=False, ) } ) task_result = json.loads(task_completion.choices[0].message.content)

Kaypi kachkan qatiqnin espía thrillerniykupaq esquema:

 { "storyArc": "Cinderella", "synopsis": "In 'The Clockwork Veil', Ethan Cross, a savvy counter-intelligence operative, is thrust into a high-pressure scenario where leaked documents threaten national integrity. As he races against time to unmask a mole within the agency, Ethan confronts his personal fears and the boundaries of the meticulous strategies he's known for. This slow-burn thriller follows Ethan's transformation in a world where every second could spell disaster, culminating in a showdown with Lena Grey\u2014a former ally who has turned the clockwork of espionage into her personal vendetta. Through grit and cunning, Ethan must adapt his methods, realizing that in the world of espionage, the most powerful weapon is a well-timed intuition.", "characters": [ { "name": "Ethan Cross", "role": "Protagonist", "description": "A meticulous and resourceful counter-intelligence operative known for his analytical mind and calm demeanor under pressure.", "arc": "Ethan transforms from a methodical planner to a decisive action-taker as he confronts his personal fears and realizes the importance of instinct." }, { "name": "Lena Grey", "role": "Antagonist", "description": "A brilliant but disillusioned former operative now turned mole, seeking vengeance against the agency she believes wronged her.", "arc": "Lena starts with a single-minded focus on revenge but gradually becomes conflicted as old loyalties resurface." }, { "name": "Dr. Julia Ward", "role": "Supporting Character", "description": "An astute psychologist who helps Ethan manage the stress of his demanding role and assists in profiling Lena's psychological state.", "arc": "Julia grows from a secondary advisory role to a key player in helping Ethan unearth Lena's motivations." }, { "name": "Michael Garner", "role": "Supporting Character", "description": "Ethan's trusted field partner and an expert in electronic surveillance, providing vital technical support.", "arc": "Michael's experience is tested as he learns to adapt to unpredictable situations, becoming more versatile in his approach." } ], "plotPoints": { "exposition": "Ethan Cross is tasked with investigating a series of leaked documents that could compromise national security. The leaks point to an insider within the agency.", "risingAction": "As Ethan dives deeper, he uncovers a trail leading to Lena Grey, a former colleague presumed dead. Evidence mounts as Ethan closes in, forcing him to question his long-standing methodologies.", "climax": "Ethan finally confronts Lena, who has rigged a trap to destroy critical evidence. In a tense standoff, Ethan must choose between following protocol or taking a risk to stop her.", "fallingAction": "With quick thinking and a new reliance on intuition, Ethan manages to disarm the trap. Lena, deflated, questions her own motives as old memories of camaraderie surface.", "resolution": "Lena is apprehended, the mole hunt ends, and Ethan reflects on his journey, acknowledging the balance between calculated strategy and spontaneity." }, "centralConflict": "Ethan Cross must identify and capture a mole within the agency who is leaking classified information, while dealing with his own rigid attachment to protocol in a dynamically evolving threat landscape.", "setting": "The story unfolds across various global locations including the bustling intelligence hub of Langley, a remote cabin in the Swiss Alps, and the teeming streets of Berlin, lending an authentic and international scope to the narrative.", "majorTurningPoints": [ "Ethan discovers the identity of the mole as his former colleague Lena Grey.", "Lena executes a series of diversions leading to a crisis within the agency.", "Ethan's adherence to protocol nearly costs him a critical breakthrough.", "Ethan's confrontation with Lena culminates in an uncharacteristic display of intuition that saves the mission." ], "characterArcs": { "protagonistArc": "Ethan evolves from strictly adhering to procedures to embracing a balance between strategy and instinctive decision-making, essential in high-stakes situations.", "antagonistArc": "Lena's journey from spite-fueled revenge to questioning her own motivations reflects a shift from isolation to an internal struggle with her past loyalties.", "supportingCharactersArcs": [ "Julia grows from providing psychological insights to playing an active role in strategizing the final approach to Lena.", "Michael transitions from a technical support role to becoming a crucial element in executing Ethan\u2019s plans, emphasizing adaptability." ] } } d

Kunanqa kay esquemata wakmanta llamk'achiyta atiykuman achka allichaykunata huk gasoductopi paqarichiypaq sinchi garantiakunawan chaymanta lluqsiypi kaq chakrakunamanta.

Conclusion

Estructurasqa meta-tapuyqa atichisunki estructurata phawaypi riqsichiyta, LLM lluqsiykuna aswan atiyniyuq uray ruwaykunapaq ruwaspa. Qatiqnin qillqasqata qhaway, maypi huk técnicas kaqwan estructurasqa meta-tapuyta tinkiyta maskasunchik.