Go: add Jina chat completions support by jakearmstrong59 · Pull Request #14935 · infiniflow/ragflow

jakearmstrong59 · 2026-05-14T16:15:42Z

What problem does this PR solve?

This PR adds non-streaming chat support for the Jina Go model provider.

The Jina provider was added with embedding, rerank, model listing, and connection checking, but ChatWithMessages still returned a not-implemented error even though Jina exposes an OpenAI-compatible /v1/chat/completions endpoint.

Closes #14933

The following functionalities are now supported:

Jina:

Implementation details:

Implements JinaModel.ChatWithMessages
Sends Authorization: Bearer <api-key> and JSON chat completion requests
Validates API key, model name, messages, and configured region before making requests
Forwards supported chat config fields: max_tokens, temperature, top_p, and stop
Parses the first chat completion choice into ChatResponse.Answer
Adds jina-ai/jina-vlm as a chat-capable model in conf/models/jina.json
Adds focused unit tests for request construction, auth, response parsing, validation errors, provider errors, and region handling

Verification:

docker run --rm -v $PWD:/repo -w /repo golang:1.25 sh -c '/usr/local/go/bin/gofmt -w internal/entity/models/jina.go internal/entity/models/jina_test.go && /usr/local/go/bin/go test -vet=off ./internal/entity/models -run TestJina -count=1'
ok  	ragflow/internal/entity/models	0.037s

Note: go test ./internal/entity/models -run TestJina -count=1 currently hits unrelated existing vet findings in other provider files, so the focused Jina tests were run with -vet=off.

Type of change

Bug Fix (non-breaking change which fixes an issue)
New Feature (non-breaking change which adds functionality)
Documentation Update
Refactoring
Performance Improvement
Other (please describe):

coderabbitai · 2026-05-14T16:16:00Z

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info

⚙️ Run configuration

Configuration used: Organization UI

Review profile: CHILL

Plan: Pro

Run ID: 3db32ced-9311-4b4c-9940-95809a41df15

📥 Commits

Reviewing files that changed from the base of the PR and between 9afd25a and 9628353.

📒 Files selected for processing (2)

conf/models/jina.json
internal/entity/models/jina_test.go

✅ Files skipped from review due to trivial changes (1)

conf/models/jina.json

🚧 Files skipped from review as they are similar to previous changes (1)

internal/entity/models/jina_test.go

📝 Walkthrough

Walkthrough

Implements JinaModel.ChatWithMessages (synchronous chat completions) with region-aware base URL lookup, request validation, JSON request construction including optional chat params, timed HTTP POST with Bearer auth, response parsing to return the first choice's content, adds jina-vlm model entry, and adds comprehensive unit tests.

Changes

Jina Chat Support

Layer / File(s)	Summary
Model configuration `conf/models/jina.json`	Registers `jina-vlm` as a chat-capable model with `max_tokens: 32768` and updates JSON closing brace position.
Chat request implementation `internal/entity/models/jina.go`	Adds `baseURLForRegion` and implements `ChatWithMessages` with input validation (apiConfig, apiKey, modelName, non-empty messages), region-based URL selection, request construction (model, messages, optional `max_tokens`, `temperature`, `top_p`, `stop`), JSON marshaling, timeout context POST, HTTP 200 check, and parsing first choice message into `ChatResponse`. Imports `context` for timeout handling.
Test infrastructure and validation `internal/entity/models/jina_test.go`	Adds `newJinaServer` httptest helper, `newJinaForTest`, and tests: happy-path, chat config propagation, validation errors (missing API config/key/model/messages), upstream HTTP 401 propagation, malformed response rejection, unknown region error, and default-region fallback.

Sequence Diagram

sequenceDiagram
  participant Client
  participant ChatWithMessages
  participant baseURLForRegion
  participant HTTP
  participant ResponseParser
  Client->>ChatWithMessages: Call ChatWithMessages(model, messages, apiConfig, chatModelConfig)
  ChatWithMessages->>ChatWithMessages: Validate inputs (apiKey, model, messages)
  ChatWithMessages->>baseURLForRegion: Resolve base URL for region
  baseURLForRegion-->>ChatWithMessages: Return base URL or error
  ChatWithMessages->>HTTP: POST /v1/chat/completions with JSON body + Authorization
  HTTP-->>ChatWithMessages: Return JSON response (status 200)
  ChatWithMessages->>ResponseParser: Parse JSON -> choices[0].message.content
  ResponseParser-->>ChatWithMessages: Extracted content
  ChatWithMessages-->>Client: Return ChatResponse{Answer: content, ReasonContent: ""}

Estimated code review effort

🎯 3 (Moderate) | ⏱️ ~25 minutes

Possibly related PRs

infiniflow/ragflow#14838: Foundational Jina provider integration that this change builds upon.

Suggested labels

💞 feature

"i hop through bytes and tiny logs,
a bearer token upon my paws.
regions map like hidden paths,
I stitch the chat where jina draws.
pong returns — a carrot applause." 🐇✨

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title clearly and concisely describes the main change: adding Jina chat completions support to the Go model provider.
Description check	✅ Passed	The description covers the problem statement, implementation details, type of change, and includes verification steps. All required template sections are completed.
Linked Issues check	✅ Passed	The PR fully implements all coding requirements from issue `#14933`: ChatWithMessages implementation, auth header, validation, request construction, response parsing, model config, and unit tests.
Out of Scope Changes check	✅ Passed	All changes are scoped to implementing ChatWithMessages for Jina: config model entry, implementation, and tests. No unrelated changes detected.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

Tip

💬 Introducing Slack Agent: The best way for teams to turn conversations into code.

Slack Agent is built on CodeRabbit's deep understanding of your code, so your team can collaborate across the entire SDLC without losing context.

Generate code and open pull requests
Plan features and break down work
Investigate incidents and troubleshoot customer tickets together
Automate recurring tasks and respond to alerts with triggers
Summarize progress and report instantly

Built for teams:

Shared memory across your entire org—no repeating context
Per-thread sandboxes to safely plan and execute work
Governance built-in—scoped access, auditability, and budget controls

One agent for your entire SDLC. Right inside Slack.

👉 Get started

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

jakearmstrong59 · 2026-05-14T20:24:55Z

@Haruko386 @JinHai-CN
Please review my PR and let me know what else is needed to update.
Thanks.

Haruko386

@jakearmstrong59, If you’ve found the Jina Chat API documentation, please let me know.

jakearmstrong59 · 2026-05-15T15:13:32Z

@Haruko386 Thanks for your check.

I tested the Jina chat endpoint with a real API key.

Docs/source:

https://api.jina.ai/docs#/
https://api.jina.ai/openapi.json includes /v1/chat/completions.

Live API result:

POST https://api.jina.ai/v1/chat/completions with model jina-vlm returns 200 OK.
The same endpoint supports multimodal text+image content.
jina-ai/jina-vlm returns model-not-found on the chat endpoint.

I updated the PR config and tests to use jina-vlm.

Go: add Jina chat completions support

9afd25a

dosubot Bot added the size:L This PR changes 100-499 lines, ignoring generated files. label May 14, 2026

Haruko386 suggested changes May 14, 2026

View reviewed changes

JinHai-CN added the invalid This doesn't seem right label May 15, 2026

jakearmstrong59 marked this pull request as draft May 15, 2026 03:08

fix: use valid Jina chat model id

9628353

jakearmstrong59 marked this pull request as ready for review May 15, 2026 15:13

jakearmstrong59 requested a review from Haruko386 May 15, 2026 15:14

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Go: add Jina chat completions support#14935

Go: add Jina chat completions support#14935
jakearmstrong59 wants to merge 2 commits into
infiniflow:mainfrom
jakearmstrong59:feature/jina-go-chat-completions

jakearmstrong59 commented May 14, 2026

Uh oh!

coderabbitai Bot commented May 14, 2026 •

edited

Loading

Walkthrough

Changes

Sequence Diagram

Estimated code review effort

Possibly related PRs

Suggested labels

Uh oh!

jakearmstrong59 commented May 14, 2026

Uh oh!

Haruko386 left a comment

Uh oh!

jakearmstrong59 commented May 15, 2026 •

edited

Loading

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

Conversation

jakearmstrong59 commented May 14, 2026

What problem does this PR solve?

Jina:

Implementation details:

Type of change

Uh oh!

coderabbitai Bot commented May 14, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Walkthrough

Changes

Sequence Diagram

Estimated code review effort

Possibly related PRs

Suggested labels

Uh oh!

jakearmstrong59 commented May 14, 2026

Uh oh!

Haruko386 left a comment

Choose a reason for hiding this comment

Uh oh!

jakearmstrong59 commented May 15, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

coderabbitai Bot commented May 14, 2026 •

edited

Loading

jakearmstrong59 commented May 15, 2026 •

edited

Loading