Generation

These Python examples are real runnable files. Edit the source file first; this page is rebuilt from the checked-in example and its metadata header.

Python Typed Generation

Runs a small typed generation program against OpenAI.

Provider: openai
Env: OPENAI_API_KEY, OPENAI_APIKEY
Level: beginner
Run: npm run example -- python src/examples/python/generation/axgen-openai.py
Source: src/examples/python/generation/axgen-openai.py

Python

import json
import os

from axllm import OpenAICompatibleClient, ax


api_key = os.getenv("OPENAI_API_KEY") or os.getenv("OPENAI_APIKEY")
if not api_key:
    raise SystemExit("Set OPENAI_API_KEY or OPENAI_APIKEY to run this example.")

client = OpenAICompatibleClient(
    api_key=api_key,
    model=os.getenv("AX_OPENAI_MODEL", "gpt-5.4-mini"),
    model_config={"temperature": 0},
)
program = ax('question:string -> answer:string')
out = program.forward(client, {"question": "In one sentence, explain Ax as a language-agnostic LLM programming library."})
print(json.dumps(out, indent=2, sort_keys=True))

Python Structured Extraction

Extracts structured fields and labels from support text with OpenAI.

Provider: openai
Env: OPENAI_API_KEY, OPENAI_APIKEY
Level: intermediate
Run: npm run example -- python src/examples/python/generation/structured.py
Source: src/examples/python/generation/structured.py

Python

import json
import os

from axllm import OpenAICompatibleClient, ax


api_key = os.getenv("OPENAI_API_KEY") or os.getenv("OPENAI_APIKEY")
if not api_key:
    raise SystemExit("Set OPENAI_API_KEY or OPENAI_APIKEY to run this example.")

client = OpenAICompatibleClient(
    api_key=api_key,
    model=os.getenv("AX_OPENAI_MODEL", "gpt-5.4-mini"),
    model_config={"temperature": 0},
)
program = ax('ticket:string -> priority:class "high, normal, low", summary:string, labels:string[]')
out = program.forward(client, {"ticket": "Checkout has failed for enterprise customers since 09:00. Support wants a concise summary and tags."})
print(json.dumps(out, indent=2, sort_keys=True))

Python Contextual Generation

Answers from supplied context and returns compact citations with OpenAI.

Provider: openai
Env: OPENAI_API_KEY, OPENAI_APIKEY
Level: advanced
Run: npm run example -- python src/examples/python/generation/context.py
Source: src/examples/python/generation/context.py

Python

import json
import os

from axllm import OpenAICompatibleClient, ax


api_key = os.getenv("OPENAI_API_KEY") or os.getenv("OPENAI_APIKEY")
if not api_key:
    raise SystemExit("Set OPENAI_API_KEY or OPENAI_APIKEY to run this example.")

client = OpenAICompatibleClient(
    api_key=api_key,
    model=os.getenv("AX_OPENAI_MODEL", "gpt-5.4-mini"),
    model_config={"temperature": 0},
)
program = ax('context:string, question:string -> answer:string, citations:string[]')
out = program.forward(client, {"context": "Ax uses signatures, ai(), ax(), agent(), flow(), and optimize() for production LLM programs.", "question": "How should a new developer think about Ax?"})
print(json.dumps(out, indent=2, sort_keys=True))