Metadata-Version: 2.4
Name: carrot-ai
Version: 0.2.1
Summary: Carrot AI Python SDK — automatic tracing for LLM calls
Project-URL: Homepage, https://carrotlabs.ai
Project-URL: Platform, https://platform.carrotlabs.ai
Project-URL: Documentation, https://carrotlabs.ai
Project-URL: Bug Tracker, https://github.com/carrotlabs/carrot-ai-python/issues
Project-URL: Repository, https://github.com/carrotlabs/carrot-ai-python
Author-email: Christopher Acker <chris@carrotlabs.ai>
License-Expression: MIT
License-File: LICENSE
Keywords: ai,anthropic,litellm,llm,logging,monitoring,observability,openai,tracing
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Classifier: Topic :: System :: Logging
Classifier: Typing :: Typed
Requires-Python: >=3.9
Provides-Extra: anthropic
Requires-Dist: anthropic; extra == 'anthropic'
Provides-Extra: dev
Requires-Dist: anthropic; extra == 'dev'
Requires-Dist: openai; extra == 'dev'
Requires-Dist: pytest>=7.0.0; extra == 'dev'
Provides-Extra: openai
Requires-Dist: openai; extra == 'openai'
Description-Content-Type: text/markdown

# Carrot AI Python SDK

Automatic tracing for LLM calls. Wrap your OpenAI or Anthropic client — or patch litellm — and every call is captured as a structured trace in the Carrot platform with zero changes to your application code.

## Installation

```bash
pip install carrot-ai
```

Or install from source (in the `sdk/python/` directory):

```bash
pip install -e .
```

## Quick Start

### 1. Wrap your client (one line)

```python
import carrot_ai
from openai import OpenAI

carrot_ai.init(api_key="sk-...")  # your Carrot API key

client = carrot_ai.wrap(OpenAI())

# Use the client exactly as normal — traces are captured automatically
response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)
```

That's it. Every `create()` call through the wrapped client is captured as a trace with the full request, response, token counts, and latency.

### 2. Works with Anthropic too

```python
import carrot_ai
from anthropic import Anthropic

carrot_ai.init(api_key="sk-...")

client = carrot_ai.wrap(Anthropic())

response = client.messages.create(
    model="claude-sonnet-4-20250514",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello!"}],
)
```

### 3. Streaming works transparently

```python
client = carrot_ai.wrap(OpenAI())

stream = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Tell me a story"}],
    stream=True,
)

for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)

# Trace is submitted automatically when the stream finishes
```

### 4. LiteLLM support

If you use [litellm](https://github.com/BerriAI/litellm) to call 100+ LLM providers through a single interface, one call patches everything:

```python
import carrot_ai
import litellm

carrot_ai.init(api_key="sk-...")
carrot_ai.patch_litellm()

# Every litellm.completion() / litellm.acompletion() is now traced
response = litellm.completion(
    model="openai/gpt-4o",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

Streaming, token counts, and `@trace` nesting all work the same way as with `wrap()`.

### 5. Custom trace names

By default, auto-traced calls use the API resource name (e.g. `"chat.completions"`). You can set a custom name to identify traces from a specific service or client:

```python
client = carrot_ai.wrap(OpenAI(), name="my-chatbot")

carrot_ai.patch_litellm(name="summarizer-service")
```

This is useful when you have multiple services sending traces and want to distinguish them in the dashboard.

## `@trace` Decorator

For multi-step pipelines (RAG, agents, chains), use the `@trace` decorator to capture the full workflow as a single trace. Any wrapped LLM calls inside the function are automatically linked as children.

```python
import carrot_ai
from openai import OpenAI

carrot_ai.init(api_key="sk-...")
client = carrot_ai.wrap(OpenAI())


@carrot_ai.trace
def answer_question(question: str) -> str:
    # Step 1: retrieve context
    docs = search_knowledge_base(question)

    # Step 2: LLM call (auto-traced as a child)
    response = client.chat.completions.create(
        model="gpt-4o",
        messages=[
            {"role": "system", "content": f"Context:\n{docs}"},
            {"role": "user", "content": question},
        ],
    )

    return response.choices[0].message.content


# The decorator creates a parent trace for the full function,
# and the LLM call inside creates a child trace linked via parent_trace_id
result = answer_question("How do I reset my password?")
```

### Decorator variants

```python
# Bare decorator
@carrot_ai.trace
def my_function():
    ...

# With a custom name
@carrot_ai.trace("my-pipeline")
def my_function():
    ...

# With tags and metadata
@carrot_ai.trace(name="my-pipeline", tags=["production"], metadata={"version": "2"})
def my_function():
    ...
```

### Async support

Both `wrap()` and `@trace` work with async clients and async functions:

```python
from openai import AsyncOpenAI

client = carrot_ai.wrap(AsyncOpenAI())


@carrot_ai.trace
async def answer_question(question: str) -> str:
    response = await client.chat.completions.create(
        model="gpt-4o",
        messages=[{"role": "user", "content": question}],
    )
    return response.choices[0].message.content
```

## Configuration

### `carrot_ai.init()`

| Parameter | Type | Default | Description |
|-----------|------|---------|-------------|
| `api_key` | `str` | `CARROT_API_KEY` env var | Your Carrot API key |
| `base_url` | `str` | `https://api.carrotlabs.ai` | API endpoint (override for self-hosted) |
| `flush_interval` | `float` | `5.0` | Seconds between background batch flushes |
| `batch_size` | `int` | `50` | Max traces per batch POST |

### Environment variables

| Variable | Description |
|----------|-------------|
| `CARROT_API_KEY` | API key (used if not passed to `init()`) |
| `CARROT_BASE_URL` | API base URL override |

If `CARROT_API_KEY` is set, `init()` is called automatically on first use — you can skip the explicit `init()` call.

### `carrot_ai.wrap()`

| Parameter | Type | Default | Description |
|-----------|------|---------|-------------|
| `client` | `OpenAI \| Anthropic` | required | The LLM client to wrap |
| `name` | `str` | `None` | Override the default trace name (derived from the API resource, e.g. `"chat.completions"`) |
| `tags` | `list[str]` | `None` | Default tags added to every trace from this client |

### `carrot_ai.patch_litellm()`

| Parameter | Type | Default | Description |
|-----------|------|---------|-------------|
| `name` | `str` | `None` | Override the default trace name (`"chat.completions"`) |
| `tags` | `list[str]` | `None` | Default tags added to every trace from litellm calls |

Patches `litellm.completion` and `litellm.acompletion` in-place. Safe to call multiple times (only patches once).

### `carrot_ai.flush()`

Force-flush any pending traces to the server. Useful before process exit in short-lived scripts:

```python
carrot_ai.flush()
```

An `atexit` handler also flushes automatically on normal interpreter shutdown.

## Proxy Header (Alternative)

If you already route inference through the Carrot proxy, you can capture traces without the SDK by adding a header:

```python
from openai import OpenAI

client = OpenAI(
    base_url="https://api.carrotlabs.ai/v1",
    api_key="sk-...",  # your Carrot API key
    default_headers={"X-Carrot-Trace": "true"},
)

# Traces are captured automatically by the proxy
response = client.chat.completions.create(
    model="my-model",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

This only works for requests routed through the Carrot proxy. Use the SDK `wrap()` approach for calls sent directly to OpenAI, Anthropic, or any other provider.

## Publishing to PyPI

1. Bump the version in both `pyproject.toml` and `src/carrot_ai/__init__.py`.
2. Update `CHANGELOG.md` with the new entry.
3. Run tests: `python3 -m pytest tests/ -v`
4. Build: `rm -rf dist/ && python3 -m build`
5. Publish:

```bash
source .env
uv publish --token "$UV_PUBLISH_TOKEN"
```

Store your PyPI API token in `sdk/python/.env` (gitignored):

```
UV_PUBLISH_TOKEN=pypi-...
```

## What Gets Captured

Each trace includes:

| Field | Description |
|-------|-------------|
| `input` | Messages, model, temperature, and other request params |
| `output.message` | Assistant response (content + tool calls) |
| `metadata.provider` | `"openai"`, `"anthropic"`, or `"litellm"` |
| `metadata.model` | Model name used |
| `metadata.input_tokens` | Prompt token count |
| `metadata.output_tokens` | Completion token count |
| `metadata.latency_ms` | End-to-end call duration |
| `metadata.source` | `"sdk"`, `"decorator"`, or `"proxy"` |
| `metadata.parent_trace_id` | Links child LLM calls to `@trace` parent |
| `status` | `"success"` or `"error"` |
| `started_at` / `ended_at` | ISO 8601 timestamps |
