Pastāvīgs izaicinājums lieliem valodu modeļiem (LLM) ir to tendence radīt neparedzamu rezultātu. Neraugoties uz rūpīgi izstrādātajiem norādījumiem, LLM bieži atšķiras no cerībām, padarot to rezultātus grūti atkārtoti izmantot vai integrēt darbplūsmās. Vēl sliktāk, rezultāti bieži vien nav atkārtojami, kas sarežģī pakārtoto apstrādi.

Šajā emuāra ziņojumā mēs izpētām strukturētu meta uzvedni — paņēmienu, kas dinamiski ģenerē JSON shēmas risinājumiem pirms uzdevumu veikšanas. Tas palīdz izveidot vairāk atkārtoti lietojamu, uzticamāku un paredzamāku uzvedņu.

Fons

Lielākā daļa mūsdienu LLM tagad piedāvā JSON izvades režīmu, taču rezultāti ne vienmēr atbilst paredzamajai shēmai. Izstrādātāji bieži izmanto pārbaudes un atkārtošanas mehānismus, kas ir laikietilpīgi, dārgi un var sabojāt lietotāja pieredzi.

Izmantojot gpt4o , OpenAI ieviesa strukturētas izvades, kas garantēja, ka izvade atbilst lietotāja nodrošinātajai JSON shēmai. Lai gan precīza informācija netiek atklāta, tas, visticamāk, tiek panākts, apvienojot ierobežotu dekodēšanu un pirmsizlases loga novirzi. Līdzīgas iespējas piedāvā citi rīki, piemēram, norādījumi, kontūras, inversija, CommandR, SGLang. Šīs pieejas ļauj izstrādātājiem virzīt izvades JSON shēmās, katrai no kurām ir unikāls kompromiss.

Kas ir strukturēta meta pamudināšana?

Strukturēta meta-uzvedne ir jebkura tehnika, kas izmanto LLM, lai dinamiski izveidotu strukturētu problēmas aprakstu pirms risinājuma izstrādes. Šai metodei ir vairākas priekšrocības salīdzinājumā ar tiešo pamudinājumu:

1. Dinamiska : izvades struktūras tiek ģenerētas izpildlaikā, pamatojoties uz uzdevumu aprakstiem, nevis tiek kodētas vai precīzi pielāgotas modelī.
2. Pielāgojama : ģenerētā shēma ir cilvēkiem lasāma, un cilvēki vai citi LLM to var pārbaudīt, pārbaudīt vai pārveidot.
3. Atkārtoti lietojams : shēmu var saglabāt un atkārtoti izmantot vairākos uzdevumos, darbos un iekārtās.
4. Paredzams : risinājumi atbildīs labi definētai struktūrai, padarot tos piemērotus pakārtotajiem aprēķiniem.

Kods

Apskatīsim piemēru, kurā mēs izmantojam strukturētu meta pamudinājumu, lai izveidotu kontūru jaunam visvairāk pārdotajam spiegu trillera romānam.

Viss šīs emuāra ziņas kods ir pieejams šajā Colab piezīmju grāmatiņā .

1. Struktūras ģenerēšana

dPirmais solis ir definēt JSON shēmu, kas apraksta vēlamo izvadi. Lai to izdarītu, mēs izveidosim JSON shēmu JSON shēmai — faktiski metashēmu ! Tas ir sniegts kā daļa no specifikācijas, taču mums ir jāveic dažas izmaiņas.

1.1. Meta shēmas pielāgošana

OpenAI un Cohere strukturētās izvades API nosaka vairākus ierobežojumus standarta JSON shēmām. Tas ir diezgan nožēlojami, taču pagaidām mēs varam to apiet. Mēs izlabosim metashēmu, lai nodrošinātu saderību:

 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) )

Piezīme *: Acīmredzot* inversijai nav šādu ierobežojumu, un tā atbalsta patvaļīgas JSON shēmas, taču vēl nav publiskas piekļuves!

1.2. Ierobežojumu pievienošana mūsu meta-uzvednei

Pēc tam mēs uzvednē iekļaujam vadlīnijas, lai nodrošinātu, ka iegūtā JSON shēma atbilst OpenAI ierobežojumiem. Piemēram:

• Jāaizpilda visi lauki.
• Objektiem ir ierobežojumi ligzdošanas dziļumam un izmēram.
• Papildu rekvizīti ir jāaizliedz ( "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 uzvednes iestatīšana

Tagad mēs definējam meta uzvedni, lai ģenerētu JSON shēmu spiegu trillera izklāstam

 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 Struktūras ģenerēšana

Mēs izsaucam LLM, lai izveidotu shēmu:

 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 }

Tagad mums ir shēma, kas apraksta mūsu spiegu trillera romāna izklāstu. To var saglabāt failā vai datu bāzē.

2. Risinājuma ģenerēšana

2.1. Ātra iestatīšana

Izmantojot shēmu, mēs definējam uzvedni jaunajam kontūram. mēs izmantosim dažus pamata lomu spēles pamudinājumus un vadlīnijas:

 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)

Lūk, mūsu nākamā spiegu trillera izklāsts:

 { "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

Tagad mēs varam atkārtoti izmantot šo shēmu, lai ģenerētu vairākus risinājumus, nodrošinot stingras garantijas par laukiem, ko satur izvade.

Secinājums

Strukturēta meta-uzvedne ļauj definēt struktūru lidojuma laikā, padarot LLM izvadus uzticamākus pakārtotajiem procesiem. Sekojiet līdzi nākamajam ierakstam, kurā mēs izpētīsim strukturētu meta-uzvedņu apvienošanu ar citām metodēm.