> ## Documentation Index
> Fetch the complete documentation index at: https://docs.abv.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# API & Data Platform

ABV is designed to be open, extensible, and flexible. The platform provides programmatic access to all your LLM observability data, enabling custom workflows, integrations, and analytics beyond the built-in dashboard.

<Tabs>
  <Tab title="Open Data Architecture" icon="database">
    Your LLM observability data belongs to you. ABV never locks you into proprietary formats or restricts access to your own data. Every trace, score, and metric is accessible through APIs, SDKs, and export mechanisms.

    Build exactly the workflows your organization needs: custom billing systems, data warehouse integration, specialized analytics, or compliance reporting. Your data, your way.
  </Tab>

  <Tab title="Flexible Export Options" icon="download">
    Different use cases require different export approaches. Export individual traces from the UI for quick analysis, bulk export datasets for fine-tuning, stream data to blob storage for data warehouse integration, or query data programmatically via SDKs and APIs.

    Choose the export mechanism that fits your workflow, whether it's one-time analysis or continuous data synchronization.
  </Tab>

  <Tab title="Full API Access" icon="code">
    The same data powering ABV's dashboard is available through comprehensive APIs. Query traces, scores, datasets, and prompts programmatically. Create, update, and delete resources. Build custom tools and integrations without limitations.

    APIs use standard REST patterns with clear documentation, making integration straightforward for any team.
  </Tab>
</Tabs>

# How the Data Platform Works

Understanding the architecture helps you choose the right access pattern:

<Steps>
  <Step title="Data capture and storage" icon="database">
    As your LLM application runs, ABV captures complete observability data: inputs, outputs, model parameters, costs, latency, user information, tags, and custom metadata. Evaluation scores and human annotations get associated with traces.

    All this data is stored in ABV's managed infrastructure with retention policies you configure.
  </Step>

  <Step title="Structured data models" icon="sitemap">
    ABV organizes data into clear, documented models:

    * **Traces**: Individual LLM requests with full context
    * **Observations**: Steps within traces (LLM calls, tool uses, retrieval)
    * **Scores**: Quality evaluations attached to traces
    * **Datasets**: Curated collections for evaluation and fine-tuning
    * **Prompts**: Versioned prompt templates with metadata

    These models provide consistent structure across all access methods.
  </Step>

  <Step title="Multiple access patterns" icon="arrows-split">
    Access the same data through different interfaces depending on your needs:

    * **UI export**: Download traces, datasets, or fine-tuning data directly from the dashboard
    * **Public API**: RESTful API for querying, creating, and managing all resources
    * **SDKs**: Python and TypeScript/JavaScript SDKs with native language support
    * **Blob storage export**: Continuous export to S3, GCS, or Azure Blob Storage for data warehouse integration

    Mix and match approaches based on the specific workflow.
  </Step>

  <Step title="Integration and workflows" icon="puzzle-piece">
    Once you have data access, build custom workflows:

    * **Billing systems**: Extract cost data for customer invoicing or cost allocation
    * **External dashboards**: Feed LLM metrics into your existing BI tools
    * **Data warehouse**: Combine LLM observability with other business data
    * **Fine-tuning pipelines**: Export high-quality traces to improve model performance
    * **Compliance reporting**: Generate audit trails and compliance documentation
    * **Custom alerting**: Build specialized monitoring beyond standard metrics

    The platform adapts to your infrastructure and processes.
  </Step>
</Steps>

# Common Use Cases

Organizations use the data platform for diverse workflows:

<AccordionGroup>
  <Accordion title="Usage-Based Billing" icon="receipt">
    Track LLM costs by customer or tenant to implement accurate usage-based billing. Query the API to extract per-customer costs, broken down by time period or feature. Generate invoices, implement quota enforcement, or create cost allocation reports.

    **Pattern**: Scheduled API queries extract cost metrics for billing periods, feeding into your invoicing system. Custom dashboards show customers their usage trends.
  </Accordion>

  <Accordion title="Data Warehouse Integration" icon="warehouse">
    Combine LLM observability data with broader business metrics in your data warehouse. Export traces to S3/GCS/Azure, then ingest into Snowflake, BigQuery, or Databricks. Correlate LLM performance with user behavior, business outcomes, and product metrics.

    **Pattern**: Continuous blob storage export feeds your ETL pipeline. Join trace data with customer data, product events, and business metrics for comprehensive analytics.
  </Accordion>

  <Accordion title="Fine-Tuning Data Preparation" icon="brain">
    Extract high-quality LLM interactions for fine-tuning. Filter traces by score thresholds, export in OpenAI fine-tuning format, and use them to improve model performance on your specific use cases.

    **Pattern**: Query API for highly-rated traces, transform to fine-tuning format, upload to model training pipeline. Iterate based on fine-tuned model performance.
  </Accordion>

  <Accordion title="Custom Reporting and Dashboards" icon="chart-line">
    Build specialized dashboards in tools your team already uses (Looker, Tableau, Grafana). Query metrics via API, combine with other data sources, and create executive reports tailored to your organization.

    **Pattern**: Scheduled API queries populate external dashboards. Custom views show LLM metrics alongside business KPIs in unified reports.
  </Accordion>

  <Accordion title="Compliance and Audit Trails" icon="clipboard-check">
    Generate compliance documentation showing LLM usage, content filtering, and quality controls. Export audit logs, trace histories, and evaluation results to demonstrate regulatory compliance.

    **Pattern**: Periodic exports to secure storage create immutable audit trails. API queries generate reports for auditors showing content safety measures and quality controls.
  </Accordion>

  <Accordion title="Cross-System Correlation" icon="chart-network">
    Analyze how LLM behavior correlates with downstream outcomes. Export trace data, join with application logs, user behavior events, and business metrics to understand the full impact of your LLM features.

    **Pattern**: Trace IDs flow through your entire system. Join trace data with application database to analyze conversion rates, user satisfaction, and business impact of LLM interactions.
  </Accordion>
</AccordionGroup>

# Access Methods

ABV provides multiple ways to access your data, each suited to different needs:

<AccordionGroup>
  <Accordion title="Public API" icon="code">
    RESTful API providing programmatic access to all ABV resources. Query traces, scores, datasets, and prompts. Create annotations, trigger evaluations, and manage configurations.

    **Best for**: Custom integrations, automated workflows, real-time queries, building custom tools

    **Authentication**: API keys scoped to specific projects with role-based access control

    [Learn more about the Public API →](/developer/platform/api-data-platform/public-api)
  </Accordion>

  <Accordion title="SDKs for Data Queries" icon="code-bracket">
    Python and TypeScript/JavaScript SDKs provide native language support for querying ABV data. Type-safe interfaces, async support, and automatic pagination make integration straightforward.

    **Best for**: Application integration, Jupyter notebooks for analysis, programmatic data exploration

    **Capabilities**: Query traces with filtering, fetch datasets, retrieve scores, access prompts

    [Learn more about querying via SDKs →](/developer/platform/api-data-platform/query-data-via-sdks)
  </Accordion>

  <Accordion title="UI Export" icon="download">
    Export data directly from the ABV dashboard for quick analysis or one-time exports. Select traces, datasets, or fine-tuning data, choose format (JSON, CSV, JSONL), and download.

    **Best for**: Ad-hoc analysis, sharing specific traces, manual data review, one-time exports

    **Formats**: JSON for full fidelity, CSV for spreadsheet analysis, JSONL for line-based processing

    [Learn more about UI export →](/developer/platform/api-data-platform/export-data-from-ui)
  </Accordion>

  <Accordion title="Fine-Tuning Export" icon="brain">
    Specialized export format optimized for LLM fine-tuning. Filter traces by quality scores, export in formats compatible with OpenAI, Anthropic, or custom training pipelines.

    **Best for**: Model improvement through fine-tuning on production interactions, creating training datasets

    **Formats**: OpenAI fine-tuning format (JSONL), custom formats for other providers

    [Learn more about fine-tuning export →](/developer/platform/api-data-platform/export-for-fine-tuning)
  </Accordion>

  <Accordion title="Blob Storage Export" icon="cloud">
    Continuous export to S3, Google Cloud Storage, or Azure Blob Storage for data warehouse integration. ABV automatically exports new traces, scores, and metadata as they're created.

    **Best for**: Data warehouse integration, long-term archival, large-scale analytics, compliance storage

    **Supported providers**: AWS S3, Google Cloud Storage, Azure Blob Storage

    [Learn more about blob storage export →](/developer/platform/api-data-platform/export-via-blob-storage)
  </Accordion>
</AccordionGroup>

# Example Workflows

## Usage-Based Billing Implementation

<Steps>
  <Step title="Configure cost tracking" icon="tag">
    Add `userId` or `customerId` to all traces to track usage per customer. Optionally tag traces by feature or service tier for granular billing.
  </Step>

  <Step title="Query cost metrics" icon="code">
    Use the Metrics API to extract per-customer costs for billing periods. Group by user, filter by time range, aggregate total costs.
  </Step>

  <Step title="Generate invoices" icon="receipt">
    Feed cost data into your billing system. Generate line items for LLM usage, apply pricing tiers, create customer invoices.
  </Step>

  <Step title="Provide customer dashboards" icon="chart-line">
    Build customer-facing dashboards showing their LLM usage, costs, and trends using the Public API or SDK queries.
  </Step>
</Steps>

## Data Warehouse Integration

<Steps>
  <Step title="Configure blob storage export" icon="cloud">
    Set up continuous export to your cloud storage (S3/GCS/Azure). ABV exports traces, scores, and metadata as newline-delimited JSON.
  </Step>

  <Step title="ETL pipeline ingestion" icon="gears">
    Your ETL pipeline (Fivetran, Airbyte, custom) monitors the storage location and ingests new files into your data warehouse.
  </Step>

  <Step title="Schema definition" icon="table">
    Define schemas in your warehouse for traces, observations, and scores. Join with existing customer, product, and business tables.
  </Step>

  <Step title="Analysis and reporting" icon="magnifying-glass-chart">
    Run SQL queries joining LLM data with business metrics. Build BI dashboards correlating LLM performance with user behavior and business outcomes.
  </Step>
</Steps>

# Data Models and Schema

All access methods return data in consistent formats based on ABV's core data models:

**Traces**: Complete LLM interactions with inputs, outputs, costs, latency, and metadata

**Observations**: Individual steps within traces (LLM calls, retrievals, tool uses)

**Scores**: Quality evaluations attached to traces (user feedback, model-based scores, human annotations)

**Datasets**: Curated collections of traces for evaluation or fine-tuning

**Prompts**: Versioned prompt templates with metadata and change history

For detailed schema documentation, see the API reference for each resource type.

# Security and Access Control

<AccordionGroup>
  <Accordion title="API Key Authentication" icon="key">
    All API access requires API keys scoped to specific projects. Keys inherit the access level of the project they're associated with. Rotate keys regularly, use different keys for different systems, and monitor key usage in audit logs.
  </Accordion>

  <Accordion title="Role-Based Access Control" icon="shield">
    API access respects the same role-based permissions as the dashboard. Viewer roles have read-only access, Members can create resources, Admins can manage configurations. Control what different teams and systems can access.

    [Learn more about RBAC →](/developer/platform/administration/role-based-access-controls)
  </Accordion>

  <Accordion title="Data Retention" icon="clock">
    Configure retention policies controlling how long ABV stores your data. Automatic deletion after retention periods helps with compliance requirements (GDPR, data minimization).

    [Learn more about data retention →](/developer/platform/administration/data-retention)
  </Accordion>

  <Accordion title="Audit Logs" icon="file-shield">
    All API access, exports, and data modifications are logged. Review who accessed what data when for security auditing and compliance verification.

    [Learn more about audit logs →](/developer/platform/administration/audit-logs)
  </Accordion>
</AccordionGroup>

# Next Steps

<CardGroup cols={2}>
  <Card title="Public API" icon="code" href="/developer/platform/api-data-platform/public-api">
    Comprehensive API reference for all ABV resources and endpoints
  </Card>

  <Card title="Query Data via SDKs" icon="code-bracket" href="/developer/platform/api-data-platform/query-data-via-sdks">
    Use Python or TypeScript/JavaScript SDKs to query your observability data
  </Card>

  <Card title="Export from UI" icon="download" href="/developer/platform/api-data-platform/export-data-from-ui">
    Download traces, datasets, and fine-tuning data directly from the dashboard
  </Card>

  <Card title="Blob Storage Export" icon="cloud" href="/developer/platform/api-data-platform/export-via-blob-storage">
    Set up continuous export to S3, GCS, or Azure for data warehouse integration
  </Card>

  <Card title="Fine-Tuning Export" icon="brain" href="/developer/platform/api-data-platform/export-for-fine-tuning">
    Export high-quality traces in formats optimized for model fine-tuning
  </Card>

  <Card title="Metrics API" icon="chart-line" href="/developer/platform/metrics/metrics-api">
    Query aggregated metrics programmatically for billing and reporting
  </Card>
</CardGroup>