JSON serialization and deserialization overhead limits throughput in high-volume machine-to-machine communications. Utilizing binary formats such as Protobuf, MessagePack, Avro, or FlatBuffers significantly reduces payload size and increases processing speed. Optimal architecture employs JSON for human-readable public APIs and binary formats for internal service communication and data pipelines.
* JSON: public-facing readability
* Protobuf: efficient service communication
* MessagePack: schema-less binary encoding
* Avro: scalable event streaming
* FlatBuffers: zero-copy performance
* JSON: public-facing readability
* Protobuf: efficient service communication
* MessagePack: schema-less binary encoding
* Avro: scalable event streaming
* FlatBuffers: zero-copy performance
Cloudflare is now returning RFC 9457-compliant structured Markdown and JSON error payloads to AI agents, replacing verbose HTML error pages with machine-readable instructions. This significantly reduces payload size and token usage – by over 98% in measured tests – which is crucial for cost-effective AI agent operation. The new responses include actionable guidance, allowing agents to understand *why* an error occurred and *how* to proceed, whether that means retrying with backoff, escalating the issue, or stopping altogether.
This is a network-wide change, automatically available without any site owner configuration.
- `Accept: text/markdown` returns a yaml header and human readable markdown
- `Accept: application/json` returns JSON
- `Accept: application/problem+json` returns JSON with the `application/problem+json` content type.
This is a network-wide change, automatically available without any site owner configuration.
- `Accept: text/markdown` returns a yaml header and human readable markdown
- `Accept: application/json` returns JSON
- `Accept: application/problem+json` returns JSON with the `application/problem+json` content type.
RFC 9457 defines a standardized format for communicating error details in HTTP API responses, known as "problem details."
- Supersedes RFC 7807,
- Core fields include 'type', 'title', 'detail' and 'instance'.
- Generally paired with 4xx/5xx HTTP status codes.
- Content types `application/problem+xml`, `application/problem+json`
Example:
```
{
"type": "https://example.com/probs/invalid-input",
"title": "Invalid Input",
"status": 400,
"detail": "The provided 'age' value must be a positive integer.",
"instance": "/users/123",
"age": -5
}
```
- Supersedes RFC 7807,
- Core fields include 'type', 'title', 'detail' and 'instance'.
- Generally paired with 4xx/5xx HTTP status codes.
- Content types `application/problem+xml`, `application/problem+json`
Example:
```
{
"type": "https://example.com/probs/invalid-input",
"title": "Invalid Input",
"status": 400,
"detail": "The provided 'age' value must be a positive integer.",
"instance": "/users/123",
"age": -5
}
```
Agoda engineers developed API Agent, a system with zero code and zero deployments that enables a single Model Context Protocol (MCP) server to connect to internal REST or GraphQL APIs. The system is designed to reduce the operational overhead of managing multiple APIs with distinct schemas and authentication methods, allowing teams to query services through AI assistants without building individual MCP servers for each API.
An overview of popular techniques to confine LLMs' output to a predefined schema, covering API providers, prompting/reprompting strategies, and constrained decoding.
GitHub Models now allows developers to retrieve structured JSON responses from models directly in the UI, improving integration with applications and workflows. Supported models include OpenAI (except for o1-mini and o1-preview) and Mistral models.
