Tantangan yang terus-menerus dengan model bahasa besar (LLM) adalah kecenderungannya untuk menghasilkan keluaran yang tidak dapat diprediksi. Meskipun petunjuknya dibuat dengan saksama, LLM sering kali menyimpang dari harapan, sehingga keluarannya sulit digunakan kembali atau diintegrasikan ke dalam alur kerja. Lebih buruk lagi, hasilnya sering kali tidak dapat diulang, sehingga mempersulit pemrosesan hilir.

Dalam posting blog ini, kami membahas meta-prompting terstruktur , sebuah teknik yang secara dinamis menghasilkan skema JSON untuk solusi sebelum menjalankan tugas. Ini membantu menciptakan prompt yang lebih dapat digunakan kembali, andal, dan terprediksi.

Latar belakang

Sebagian besar LLM modern kini menawarkan mode keluaran JSON, tetapi hasilnya tidak selalu sesuai dengan skema yang diharapkan. Pengembang sering kali menggunakan mekanisme periksa dan coba lagi, yang memakan waktu, mahal, dan rentan merusak pengalaman pengguna.

Dengan gpt4o , OpenAI memperkenalkan output terstruktur yang menjamin bahwa output akan sesuai dengan skema JSON yang disediakan pengguna. Meskipun detail pastinya tidak diungkapkan, hal ini kemungkinan dicapai melalui kombinasi decoding terbatas dan bias logit pra-sampel. Kemampuan serupa ditawarkan oleh alat lain seperti panduan, outlines, inversion, CommandR, SGLang. Pendekatan ini memberdayakan pengembang untuk memandu output ke dalam skema JSON, masing-masing dengan kelebihan dan kekurangan yang unik.

Apa itu meta-prompting terstruktur?

Meta-prompting terstruktur adalah teknik apa pun yang menggunakan LLM untuk membuat deskripsi terstruktur tentang suatu masalah secara dinamis sebelum menghasilkan solusi. Metode ini menawarkan beberapa keuntungan dibandingkan prompting langsung:

1. Dinamis : Struktur keluaran dihasilkan pada waktu proses berdasarkan deskripsi tugas, dan bukan dikodekan secara kaku atau disetel secara khusus ke dalam model.
2. Dapat beradaptasi : Skema yang dihasilkan dapat dibaca manusia dan dapat diperiksa, diverifikasi, atau dimodifikasi oleh manusia atau LLM lain.
3. Dapat digunakan kembali : Skema dapat disimpan dan digunakan kembali di berbagai tugas, proses, dan mesin.
4. Dapat diprediksi : Solusi akan sesuai dengan struktur yang terdefinisi dengan baik, membuatnya cocok untuk komputasi hilir.

Kode

Mari kita lihat contoh penggunaan meta-prompting terstruktur untuk membuat kerangka novel thriller mata-mata terlaris.

Semua kode untuk postingan blog ini tersedia di Buku Catatan Colab ini.

1. Menghasilkan struktur

Langkah pertama adalah menentukan skema JSON yang menggambarkan output yang diinginkan. Untuk melakukannya, kita akan membuat skema JSON untuk skema JSON — secara efektif, meta-skema ! Ini disediakan sebagai bagian dari spesifikasi tetapi kita perlu membuat beberapa perubahan.

1.1 Mengubah meta-skema

API keluaran terstruktur OpenAI dan Cohere memberlakukan beberapa pembatasan pada skema JSON standar. Hal ini cukup disayangkan, tetapi ada sesuatu yang dapat kita atasi untuk saat ini. Kita akan mengubah meta-skema untuk memastikan kompatibilitas:

 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) )

Catatan *: Rupanya* inversi tidak memiliki batasan seperti itu dan mendukung skema JSON yang sembarangan…tetapi belum ada akses publik!

1.2 Menambahkan batasan pada meta-prompt kita

Selanjutnya, kami memasukkan panduan ke dalam prompt untuk memastikan skema JSON yang dihasilkan mematuhi batasan OpenAI. Misalnya:

• Semua kolom harus diisi.
• Objek memiliki batas pada kedalaman dan ukuran bersarang.
• Properti tambahan harus ditolak ( "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 Menyiapkan meta-prompt

Sekarang kita mendefinisikan meta-prompt untuk menghasilkan skema JSON untuk garis besar cerita mata-mata

 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 Membuat struktur

Kami memanggil LLM untuk membuat skema:

 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 }

Sekarang kita memiliki skema yang menggambarkan garis besar novel mata-mata kita. Ini dapat disimpan dalam sebuah berkas atau dalam basis data.

2. Menghasilkan solusi

2.1 Pengaturan cepat

Dengan menggunakan skema tersebut, kami mendefinisikan sebuah petunjuk untuk kerangka novel. Kami akan menggunakan beberapa petunjuk dan pedoman permainan peran dasar:

 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)

Berikut garis besar cerita mata-mata kita berikutnya:

 { "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

Sekarang kita dapat menggunakan kembali skema ini untuk menghasilkan beberapa solusi dalam satu jalur dengan jaminan kuat tentang bidang yang terdapat dalam output.

Kesimpulan

Meta-prompting terstruktur memungkinkan Anda menentukan struktur dengan cepat, sehingga keluaran LLM lebih andal untuk proses hilir. Nantikan postingan berikutnya, di mana kita akan membahas penggabungan meta-prompting terstruktur dengan teknik lain.