SSE Debugging

Server-Sent Events (SSE) is a real-time communication technology built upon the HTTP protocol, enabling servers to push updates to clients over a persistent, one-way connection. SSE is commonly used for streaming AI model responses, live notifications, and real-time data feeds.

With SSE, users can instantly see the thought process of reasoning models and generated content as it streams from the server.

Prerequisites

Apidog version 2.3.10 or later

An HTTP endpoint that returns Content-Type: text/event-stream

Initiating an SSE Connection

Create a New Endpoint

In Apidog, create a new HTTP project, add a new endpoint, and enter the URL for the AI model's endpoint or SSE server.

Send the Request

Upon sending the request, if the response header Content-Type includes text/event-stream, Apidog automatically parses the returned data as SSE events.

View Real-time Responses

View real-time messages in the Timeline view of the response panel, where content is displayed in natural language format.

Auto-Merge Messages

Version Requirement

Apidog version 2.7.14 or later required for auto-merge functionality.

Apidog includes built-in support for popular AI models and automatically recognizes and merges streaming responses in the following formats:

Format	Description
OpenAI API Compatible	Used by the vast majority of AI model providers
Gemini API Compatible	Google's Gemini model format
Claude API Compatible	Anthropic's Claude model format
Ollama API Compatible	JSON Streaming (NDJSON) format for locally deployed AI models

When the AI model's response matches any of these formats, Apidog automatically merges message fragments into a complete reply, with content previewed in Markdown format.

Reasoning Model Support

For certain models, such as DeepSeek R1, Apidog displays the model's thought process in the timeline, providing a clearer, more intuitive view of AI reasoning.

Customizing Merge Rules

If the Auto-Merge feature does not work properly, you can configure custom extraction rules based on your specific use case.

Configure JSONPath Extraction Rules

When SSE returns JSON content that doesn't conform to built-in recognition rules (OpenAI, Gemini, Claude, etc.), manually configure JSONPath to extract the required content.

Example SSE Response:

data: {"choices":[{"index":0,"message":{"role":"assistant","content":"H"},"logprobs":null,"finish_reason":"stop"}]}

data: {"choices":[{"index":0,"message":{"role":"assistant","content":"i"},"logprobs":null,"finish_reason":"stop"}]}

JSONPath Configuration:

To extract the content field, use:

$.choices[0].message.content

JSONPath Breakdown:

Component	Description
`$`	Root of the JSON object
`choices[0]`	First element of the `choices` array
`message.content`	`content` attribute under the `message` object

Extracted Result:

Hi

Use Post Processor Scripts

For non-JSON SSE messages, you can:

Use post processor scripts to manually handle the data

Contact technical support to provide feedback on the model format you're using for potential built-in support

FAQ

What to do if the SSE timeline does not display messages?

This issue usually occurs when the server's response doesn't follow SSE format guidelines. The standard SSE message format requires:

Message content must come after data:

Each message must be separated by two newline characters (a blank line between messages)

For more details on the SSE message format, refer to the MDN documentation - Using Server-Sent Events.

Learn More

How to Use the Deepseek API (R1 & V3)？

A complete guide to obtaining the DeepSeek API key and debugging the API.

Prerequisites#

Initiating an SSE Connection#

Auto-Merge Messages#

Reasoning Model Support#

Customizing Merge Rules#

Configure JSONPath Extraction Rules#

Use Post Processor Scripts#

FAQ#

Learn More#

Prerequisites

Initiating an SSE Connection

Auto-Merge Messages

Reasoning Model Support

Customizing Merge Rules

Configure JSONPath Extraction Rules

Use Post Processor Scripts

FAQ

Learn More