# Overview

Complete SDK documentation and REST API reference for Fiddler AI Observability Platform.

## 🐍 Python Client SDK

### [Python Client SDK](https://docs.fiddler.ai/api/fiddler-python-client-sdk/python-client)

Official Python SDK for comprehensive ML and LLM observability - monitor traditional ML models and LLM applications.

**Key Features:**

* Model onboarding and schema definition
* Production event publishing (batch and streaming)
* Baseline dataset management
* Alert configuration
* Custom metrics and segments

**Use Cases:**

* ML model monitoring (drift, performance, data quality)
* Production data ingestion
* Creating monitoring dashboards
* Configuring alerts for model issues

[**View Full Documentation →**](https://docs.fiddler.ai/api/fiddler-python-client-sdk/python-client)

[**View Usage Guides →**](https://app.gitbook.com/s/jZC6ysdlGhDKECaPCjwm/client-library-reference/installation-and-setup)

***

## 🎯 Agentic AI SDKs

SDKs for monitoring, evaluating, and testing LLM applications and AI agents.

### [Fiddler Evals SDK](https://docs.fiddler.ai/api/fiddler-evals-sdk/evals)

Evaluate and test LLM outputs with built-in and custom metrics.

**Key Features:**

* Pre-built evaluators (faithfulness, toxicity, coherence, etc.)
* Custom evaluation functions
* Experiment tracking and comparison
* Dataset management for test sets

**Use Cases:**

* LLM output quality assessment
* A/B testing prompts and models
* Regression testing for LLM changes
* Custom evaluation metrics

**Quick Start:**

```python
import fiddler as fdl

# Initialize evaluator
evaluator = fdl.AnswerRelevance()

# Run evaluation
result = evaluator.evaluate(
    question="What is Fiddler?",
    answer="Fiddler is an AI observability platform."
)
```

[**View Full Documentation →**](https://docs.fiddler.ai/api/fiddler-evals-sdk/evals)

***

### [Fiddler LangGraph SDK](https://docs.fiddler.ai/api/fiddler-langgraph-sdk/langgraph)

[![PyPI](https://img.shields.io/pypi/v/fiddler-langgraph)](https://pypi.org/project/fiddler-langgraph/)

Monitor LangGraph agents with distributed tracing and observability.

**Key Features:**

* Automatic LangGraph instrumentation
* Distributed tracing for agent workflows
* Span attributes for nodes and edges
* Conversation and session tracking

**Use Cases:**

* Debugging multi-step agent workflows
* Performance analysis of agent chains
* Monitoring production LangGraph applications
* Understanding agent decision paths

**Quick Start:**

```python
from fiddler.langchain import LangGraphInstrumentor

# Instrument your LangGraph app
instrumentor = LangGraphInstrumentor()
instrumentor.instrument()

# Your LangGraph code runs normally
# Traces are automatically sent to Fiddler
```

[**View Full Documentation →**](https://docs.fiddler.ai/api/fiddler-langgraph-sdk/langgraph)

***

### [Fiddler Strands SDK](https://docs.fiddler.ai/api/fiddler-strands-agents-sdk/strands)

[![PyPI](https://img.shields.io/pypi/v/fiddler-strands)](https://pypi.org/project/fiddler-strands/)

Monitor Strands Agents with native instrumentation.

**Key Features:**

* Strands Agent instrumentation
* Session and conversation tracking
* Span attributes for agent actions
* Integration with Fiddler platform

**Use Cases:**

* Monitoring Strands production agents
* Debugging Strands Agent workflows
* Tracking agent performance metrics
* Session-based analysis

**Quick Start:**

```python
from fiddler.strands import StrandsAgentInstrumentor

# Instrument Strands Agent
instrumentor = StrandsAgentInstrumentor(
    model_id="my-strands-agent"
)
instrumentor.instrument()
```

[**View Full Documentation →**](https://docs.fiddler.ai/api/fiddler-strands-agents-sdk/strands)

***

## 🌐 REST API

### [REST API Reference](https://docs.fiddler.ai/api/rest-api/rest-api)

Complete HTTP API documentation for programmatic access to the Fiddler platform.

**Use Cases:**

* Non-Python integrations (Java, Go, JavaScript, etc.)
* Custom CI/CD pipelines
* Integration with existing monitoring systems
* Webhook-based automation

**Quick Start (cURL):**

```bash
# Publish events to Fiddler
curl -X POST https://app.fiddler.ai/api/v1/events \
  -H "Authorization: Bearer fid_..." \
  -H "Content-Type: application/json" \
  -d '{
    "project": "fraud-detection",
    "model": "fraud_model_v1",
    "events": [...]
  }'
```

[**View Full REST API Documentation →**](https://docs.fiddler.ai/api/rest-api/rest-api)

**API Guides:**

* [Environments](https://docs.fiddler.ai/api/rest-api/rest-api/environment) - Environment management
* [Jobs](https://docs.fiddler.ai/api/rest-api/rest-api/jobs) - Async job tracking
* [Model API](https://docs.fiddler.ai/api/rest-api/rest-api/model) - Model management
* [Custom Metrics](https://docs.fiddler.ai/api/rest-api/rest-api/custom-metrics) - Metric definitions
* [Explainability](https://docs.fiddler.ai/api/rest-api/rest-api/explainability) - SHAP explanations
* [File Upload](https://docs.fiddler.ai/api/rest-api/rest-api/file-upload) - Baseline and artifact uploads
* [Projects](https://docs.fiddler.ai/api/rest-api/rest-api/projects) - Project management
* [Baselines](https://docs.fiddler.ai/api/rest-api/rest-api/baseline) - Baseline datasets
* [Alert Rules](https://docs.fiddler.ai/api/rest-api/rest-api/alert-rules) - Alert configuration
* [Segments](https://docs.fiddler.ai/api/rest-api/rest-api/segments) - Segment management
* [Events](https://docs.fiddler.ai/api/rest-api/rest-api/events) - Event publishing

### [Guardrails API Reference](https://docs.fiddler.ai/api/rest-api/guardrails-api-reference)

API endpoints for Fiddler Trust Service guardrails.

***

## 🚀 Getting Started

### Choose Your SDK

| Your Use Case                         | Recommended SDK                                                                          |
| ------------------------------------- | ---------------------------------------------------------------------------------------- |
| **Monitor ML/LLM and platform admin** | [Python Client SDK](https://docs.fiddler.ai/api/fiddler-python-client-sdk/python-client) |
| **Evaluate LLM outputs**              | [Fiddler Evals SDK](https://docs.fiddler.ai/api/fiddler-evals-sdk/evals)                 |
| **Monitor LangGraph agents**          | [Fiddler LangGraph SDK](https://docs.fiddler.ai/api/fiddler-langgraph-sdk/langgraph)     |
| **Monitor Strands Agents**            | [Fiddler Strands SDK](https://docs.fiddler.ai/api/fiddler-strands-agents-sdk/strands)    |
| **Non-Python integration**            | [REST API](https://docs.fiddler.ai/api/rest-api/rest-api)                                |

### Installation

**Python SDKs:**

```bash
# Python Client SDK
pip install fiddler-client

# Evals SDK
pip install fiddler-evals

# LangGraph SDK (https://pypi.org/project/fiddler-langgraph/)
pip install fiddler-langgraph

# Strands SDK (https://pypi.org/project/fiddler-strands/)
pip install fiddler-strands
```

**REST API:** No installation required - use any HTTP client.

***

## 📚 Related Documentation

* [**Developer Guides**](https://app.gitbook.com/s/jZC6ysdlGhDKECaPCjwm/platform/get-started-in-less-than-10-minutes) - Quick starts and tutorials
* [**Integrations**](https://app.gitbook.com/o/MIMFsmMfRqhAZbzV2AtV/s/kcq97TxAnbTVaNJOQHbQ/) - Connect with your ML stack
* [**Product Documentation**](https://app.gitbook.com/o/MIMFsmMfRqhAZbzV2AtV/s/82RHcnYWV62fvrxMeeBB/) - Platform features and concepts

***

## 💡 Common Workflows

### ML Model & LLM App Monitoring Workflow

1. Install [Python Client SDK](https://docs.fiddler.ai/api/fiddler-python-client-sdk/python-client)
2. Define [model schema](https://docs.fiddler.ai/api/fiddler-python-client-sdk/schemas/model-schema)
3. Upload [baseline dataset](https://docs.fiddler.ai/api/fiddler-python-client-sdk/entities/baseline)
4. [Publish production events](https://docs.fiddler.ai/api/rest-api/rest-api/events)
5. Configure [alerts](https://docs.fiddler.ai/api/fiddler-python-client-sdk/entities/alert-rule)

### LLM Experiments Workflow

1. Install [Fiddler Evals SDK](https://docs.fiddler.ai/api/fiddler-evals-sdk/evals)
2. Create a test dataset with the [Dataset API](https://docs.fiddler.ai/api/fiddler-evals-sdk/entities/dataset)
3. Define evaluators ([built-in](https://docs.fiddler.ai/api/fiddler-evals-sdk/evals#evaluators) or [custom](https://docs.fiddler.ai/api/fiddler-evals-sdk/evaluators/eval-fn))
4. Run [experiments](https://docs.fiddler.ai/api/fiddler-evals-sdk/entities/experiment) and analyze results

### Agent Monitoring Workflow

1. Install [LangGraph SDK](https://docs.fiddler.ai/api/fiddler-langgraph-sdk/langgraph) or [Strands SDK](https://docs.fiddler.ai/api/fiddler-strands-agents-sdk/strands)
2. Instrument your agent application
3. Deploy to production
4. View traces and analytics in the Fiddler platform

***

## 📖 Additional Resources

* [**GitHub Examples**](https://github.com/fiddler-labs/fiddler-examples) - Sample code and notebooks
* [**SDK Changelog**](https://app.gitbook.com/s/zZiGARdlnXHf9T9LX6r5/release-notes/python-sdk) - Latest SDK updates
* [**Support Portal**](mailto:support@fiddler.ai) - Enterprise support
* [**Community**](https://fiddler-community.slack.com) - Join our Slack community