Skip to content
Last updated

Code Examples

Practical implementation examples for common use cases with the Freddy API.

Basic AI Response

from aitronos import Aitronos

client = Aitronos(api_key="your-api-key")

result = client.responses.create_response(
    organization_id="org_your_org_id",
    model="gpt-4o",
    inputs=[{"role": "user", "content": "Explain quantum computing in simple terms."}],
)
print(result.response[0]["text"])

Multi-Turn Conversation

Use thread IDs to maintain conversation history across requests:

from aitronos import Aitronos

client = Aitronos(api_key="your-api-key")

# Start a thread
first = client.responses.create_response(
    organization_id="org_your_org_id",
    model="gpt-4o",
    inputs=[{"role": "user", "content": "I'm building a Python web app."}],
)
thread_id = first.thread_id

# Continue the conversation
followup = client.responses.create_response(
    organization_id="org_your_org_id",
    model="gpt-4o",
    thread_id=thread_id,
    inputs=[{"role": "user", "content": "What framework should I use?"}],
)
print(followup.response[0]["text"])

Using an Assistant

Assistants carry persistent instructions and model configuration:

from aitronos import Aitronos

client = Aitronos(api_key="your-api-key")

result = client.responses.create_response(
    organization_id="org_your_org_id",
    assistant_id="asst_your_assistant_id",
    inputs=[{"role": "user", "content": "What is your return policy?"}],
)
print(result.response[0]["text"])

Streaming Response

For real-time output, set stream=True and iterate the SSE events:

import httpx
import json
import os

api_key = os.environ["FREDDY_API_KEY"]

with httpx.stream(
    "POST",
    "https://api.aitronos.com/v1/model/response",
    headers={"X-API-Key": api_key, "Content-Type": "application/json"},
    json={
        "organization_id": "org_your_org_id",
        "model": "gpt-4o",
        "inputs": [{"role": "user", "content": "Tell me a short story."}],
        "stream": True,
    },
    timeout=60,
) as response:
    for line in response.iter_lines():
        if line.startswith("data: "):
            data = json.loads(line[6:])
            if data.get("event") == "response.delta":
                print(data.get("delta", ""), end="", flush=True)
            elif data.get("event") == "response.completed":
                break

Enable web search to ground responses in real-time information:

from aitronos import Aitronos

client = Aitronos(api_key="your-api-key")

result = client.responses.create_response(
    organization_id="org_your_org_id",
    model="gpt-4o",
    inputs=[{"role": "user", "content": "What happened in tech news today?"}],
    system_tools={"web_search": {"mode": "on"}},
    include=["web_search.sources"],
)
print(result.response[0]["text"])

Function Calling

Define custom tools the model can call:

from aitronos import Aitronos

client = Aitronos(api_key="your-api-key")

tools = [
    {
        "type": "function",
        "name": "get_weather",
        "description": "Get current weather for a city",
        "parameters": {
            "type": "object",
            "properties": {
                "city": {"type": "string", "description": "City name"},
            },
            "required": ["city"],
        },
    }
]

result = client.responses.create_response(
    organization_id="org_your_org_id",
    model="gpt-4o",
    inputs=[{"role": "user", "content": "What's the weather in Berlin?"}],
    tools=tools,
)

# Check if the model wants to call a function
if result.stop_reason == "tool_use":
    for block in result.response:
        if block.get("type") == "tool_use":
            print(f"Calling: {block['name']} with {block['input']}")

File Upload and Reference

Upload a document and use it as context in a response:

from aitronos import Aitronos

client = Aitronos(api_key="your-api-key")

# Upload a file
with open("report.pdf", "rb") as f:
    file_result = client.files.upload_file(
        organization_id="org_your_org_id",
        file=("report.pdf", f, "application/pdf"),
    )
file_id = file_result.file_id

# Reference it in a response
result = client.responses.create_response(
    organization_id="org_your_org_id",
    model="gpt-4o",
    inputs=[{
        "role": "user",
        "content": "Summarize the key findings from this report.",
        "files": [{"file_id": file_id}],
    }],
)
print(result.response[0]["text"])

Create and Query a Vector Store

Store documents for semantic retrieval:

from aitronos import Aitronos

client = Aitronos(api_key="your-api-key")

# Create a vector store
vs = client.vector_stores.create_vector_store(
    organization_id="org_your_org_id",
    name="Product Documentation",
)
vs_id = vs.id

# Add a file (must be uploaded first)
client.vector_store_files.add_file_to_vector_store(
    vector_store_id=vs_id,
    file_id="file_abc123",
)

# Query via responses
result = client.responses.create_response(
    organization_id="org_your_org_id",
    model="gpt-4o",
    vector_store_ids=[vs_id],
    inputs=[{"role": "user", "content": "How do I reset my password?"}],
)
print(result.response[0]["text"])

Structured Output (JSON Mode)

Force the model to return a JSON object:

from aitronos import Aitronos

client = Aitronos(api_key="your-api-key")

result = client.responses.create_response(
    organization_id="org_your_org_id",
    model="gpt-4o",
    inputs=[{
        "role": "user",
        "content": "Extract: name, email, and company from this text: 'Alice Smith, alice@acme.com, Acme Corp'"
    }],
    output_mode="json",
)
import json
data = json.loads(result.response[0]["text"])
print(data)  # {"name": "Alice Smith", "email": "alice@acme.com", "company": "Acme Corp"}

Usage Analytics

Retrieve token usage for your organization:

from aitronos import Aitronos

client = Aitronos(api_key="your-api-key")

summary = client.analytics_usage.get_usage_summary(org_id="org_your_org_id")
print(f"Total synapse usage this month: {summary.total_synapses}")

More Examples

For complete, real-world application walkthroughs see: