Ограничение LLM с помощью структурированного вывода: Ollama, Qwen3 и Python или Go

{
  "name": "Model X",
  "supports_thinking": true,
  "max_context_tokens": 200000,
  "languages": ["English", "Chinese", "Spanish"]
}

import json
import ollama

prompt = """
You are a structured data extractor.
Return JSON only.
Text: "Elon Musk is 53 and lives in Austin."
Schema: { "name": string, "age": int, "city": string }
"""

response = ollama.chat(model="qwen3", messages=[{"role": "user", "content": prompt}])
output = response['message']['content']

# Parse JSON
try:
    data = json.loads(output)
    print(data)
except Exception as e:
    print("Error parsing JSON:", e)

{"name": "Elon Musk", "age": 53, "city": "Austin"}

from pydantic import BaseModel

class Person(BaseModel):
    name: str
    age: int
    city: str

# Suppose 'output' is the JSON string from Qwen3
data = Person.model_validate_json(output)
print(data.name, data.age, data.city)

from pydantic import BaseModel
from typing import List
from ollama import chat

class LLMFeatures(BaseModel):
    name: str
    supports_thinking: bool
    max_context_tokens: int
    languages: List[str]

prompt = """
Analyze the following description and return the model’s features in JSON only.
Model description:
'Qwen3 has strong multilingual support (English, Chinese, French, Spanish, Arabic).
It allows reasoning steps (chain-of-thought).
The context window is 128K tokens.'
"""

resp = chat(
    model="qwen3",
    messages=[{"role": "user", "content": prompt}],
    format=LLMFeatures.model_json_schema(),
    options={"temperature": 0},
)

print(resp.message.content)

{
  "name": "Qwen3",
  "supports_thinking": true,
  "max_context_tokens": 128000,
  "languages": ["English", "Chinese", "French", "Spanish", "Arabic"]
}

from typing import List

class ModelComparison(BaseModel):
    models: List[LLMFeatures]

prompt = """
Extract features of each model into JSON.

1. Llama 3.1 supports reasoning. Context window is 128K. Languages: English only.
2. GPT-4 Turbo supports reasoning. Context window is 128K. Languages: English, Japanese.
3. Qwen3 supports reasoning. Context window is 128K. Languages: English, Chinese, French, Spanish, Arabic.
"""

resp = chat(
    model="qwen3",
    messages=[{"role": "user", "content": prompt}],
    format=ModelComparison.model_json_schema(),
    options={"temperature": 0},
)

print(resp.message.content)

{
  "models": [
    {
      "name": "Llama 3.1",
      "supports_thinking": true,
      "max_context_tokens": 128000,
      "languages": ["English"]
    },
    {
      "name": "GPT-4 Turbo",
      "supports_thinking": true,
      "max_context_tokens": 128000,
      "languages": ["English", "Japanese"]
    },
    {
      "name": "Qwen3",
      "supports_thinking": true,
      "max_context_tokens": 128000,
      "languages": ["English", "Chinese", "French", "Spanish", "Arabic"]
    }
  ]
}

from typing import Optional

class FlexibleLLMFeatures(BaseModel):
    name: str
    supports_thinking: Optional[bool]
    max_context_tokens: Optional[int]
    languages: Optional[List[str]]

package main

import (
	"context"
	"encoding/json"
	"fmt"
	"log"

	"github.com/ollama/ollama/api"
)

type LLMFeatures struct {
	Name             string   `json:"name"`
	SupportsThinking bool     `json:"supports_thinking"`
	MaxContextTokens int      `json:"max_context_tokens"`
	Languages        []string `json:"languages"`
}

func main() {
	client, err := api.ClientFromEnvironment()
	if err != nil {
		log.Fatal(err)
	}

	prompt := `
  Analyze the following description and return the model’s features in JSON only.
  Description:
  "Qwen3 has strong multilingual support (English, Chinese, French, Spanish, Arabic).
  It allows reasoning steps (chain-of-thought).
  The context window is 128K tokens."
  `

	// Define the JSON schema for structured output
	formatSchema := map[string]any{
		"type": "object",
		"properties": map[string]any{
			"name": map[string]string{
				"type": "string",
			},
			"supports_thinking": map[string]string{
				"type": "boolean",
			},
			"max_context_tokens": map[string]string{
				"type": "integer",
			},
			"languages": map[string]any{
				"type": "array",
				"items": map[string]string{
					"type": "string",
				},
			},
		},
		"required": []string{"name", "supports_thinking", "max_context_tokens", "languages"},
	}

	// Convert schema to JSON
	formatJSON, err := json.Marshal(formatSchema)
	if err != nil {
		log.Fatal("Failed to marshal format schema:", err)
	}

	req := &api.GenerateRequest{
		Model:   "qwen3:8b",
		Prompt:  prompt,
		Format:  formatJSON,
		Options: map[string]any{"temperature": 0},
	}

	var features LLMFeatures
	var rawResponse string
	err = client.Generate(context.Background(), req, func(response api.GenerateResponse) error {
		// Accumulate content as it streams
		rawResponse += response.Response

		// Only parse when the response is complete
		if response.Done {
			if err := json.Unmarshal([]byte(rawResponse), &features); err != nil {
				return fmt.Errorf("JSON parse error: %v", err)
			}
		}
		return nil
	})
	if err != nil {
		log.Fatal(err)
	}

	fmt.Printf("Parsed struct: %+v\n", features)
}

# initialise module
go mod init ollama-struct
# pull all the dependencise
go mod tidy
# build & execute
go build -o ollama-struct main.go
./ollama-struct

Parsed struct: {Name:Qwen3 SupportsThinking:true MaxContextTokens:128000 Languages:[English Chinese French Spanish Arabic]}

  type ModelComparison struct {
		Models []LLMFeatures `json:"models"`
	}

	prompt = `
	Extract features from the following model descriptions and return as JSON:

	1. PaLM 2: This model has limited reasoning capabilities and focuses on basic language understanding. It supports a context window of 8,000 tokens. It primarily supports English language only.
	2. LLaMA 2: This model has moderate reasoning abilities and can handle some logical tasks. It can process up to 4,000 tokens in its context. It supports English, Spanish, and Italian languages.
	3. Codex: This model has strong reasoning capabilities specifically for programming and code analysis. It has a context window of 16,000 tokens. It supports English, Python, JavaScript, and Java languages.

	Return a JSON object with a "models" array containing all models.
	`

	// Define the JSON schema for model comparison
	comparisonSchema := map[string]any{
		"type": "object",
		"properties": map[string]any{
			"models": map[string]any{
				"type": "array",
				"items": map[string]any{
					"type": "object",
					"properties": map[string]any{
						"name": map[string]string{
							"type": "string",
						},
						"supports_thinking": map[string]string{
							"type": "boolean",
						},
						"max_context_tokens": map[string]string{
							"type": "integer",
						},
						"languages": map[string]any{
							"type": "array",
							"items": map[string]string{
								"type": "string",
							},
						},
					},
					"required": []string{"name", "supports_thinking", "max_context_tokens", "languages"},
				},
			},
		},
		"required": []string{"models"},
	}

	// Convert schema to JSON
	comparisonFormatJSON, err := json.Marshal(comparisonSchema)
	if err != nil {
		log.Fatal("Failed to marshal comparison schema:", err)
	}

	req = &api.GenerateRequest{
		Model:   "qwen3:8b",
		Prompt:  prompt,
		Format:  comparisonFormatJSON,
		Options: map[string]any{"temperature": 0},
	}

	var comp ModelComparison
	var comparisonResponse string
	err = client.Generate(context.Background(), req, func(response api.GenerateResponse) error {
		// Accumulate content as it streams
		comparisonResponse += response.Response

		// Only parse when the response is complete
		if response.Done {
			if err := json.Unmarshal([]byte(comparisonResponse), &comp); err != nil {
				return fmt.Errorf("JSON parse error: %v", err)
			}
		}
		return nil
	})
	if err != nil {
		log.Fatal(err)
	}

	for _, m := range comp.Models {
		fmt.Printf("%s: Context=%d, Languages=%v\n", m.Name, m.MaxContextTokens, m.Languages)
	}

PaLM 2: Context=8000, Languages=[English]
LLaMA 2: Context=4000, Languages=[English Spanish Italian]
Codex: Context=16000, Languages=[English Python JavaScript Java]

from pydantic import BaseModel
from typing import List, Optional

class LLMFeatures(BaseModel):
    name: str
    supports_thinking: bool
    max_context_tokens: int
    languages: List[str]

from ollama import chat

prompt = """
Extract features for each model. Return JSON only matching the schema.
1) Qwen3 supports chain-of-thought; 128K context; English, Chinese, French, Spanish, Arabic.
2) Llama 3.1 supports chain-of-thought; 128K context; English.
3) GPT-4 Turbo supports chain-of-thought; 128K context; English, Japanese.
"""

resp = chat(
    model="qwen3",
    messages=[{"role": "user", "content": prompt}],
    format={"type": "array", "items": LLMFeatures.model_json_schema()},
    options={"temperature": 0}
)

raw_json = resp.message.content  # JSON list of LLMFeatures

from pydantic import TypeAdapter

adapter = TypeAdapter(list[LLMFeatures])
models = adapter.validate_json(raw_json)  # -> list[LLMFeatures]

import pandas as pd

df = pd.DataFrame([m.model_dump() for m in models])
df["languages_count"] = df["languages"].apply(len)
df["languages"] = df["languages"].apply(lambda xs: ", ".join(xs))

# Reorder columns for readability
df = df[["name", "supports_thinking", "max_context_tokens", "languages_count", "languages"]]

# Save as CSV for further use
df.to_csv("llm_feature_comparison.csv", index=False)

import matplotlib.pyplot as plt

plt.figure()
plt.bar(df["name"], df["max_context_tokens"])
plt.title("Max Context Window by Model (tokens)")
plt.xlabel("Model")
plt.ylabel("Max Context Tokens")
plt.xticks(rotation=20, ha="right")
plt.tight_layout()
plt.savefig("max_context_window.png")