mirror of
https://github.com/infiniflow/ragflow.git
synced 2026-06-29 15:31:05 +08:00
Docs: Added v0.26.2 release notes. (#16373)
This commit is contained in:
@@ -9,14 +9,54 @@ sidebar_custom_props: {
|
||||
|
||||
Key features, improvements and bug fixes in the latest releases.
|
||||
|
||||
## v0.26.2
|
||||
|
||||
Released on June 26, 2026.
|
||||
|
||||
### New features
|
||||
|
||||
- Chat channels:
|
||||
- Integrates WhatsApp via a QR code scan. [#16238](https://github.com/infiniflow/ragflow/pull/16238)
|
||||
- Integrates DingTalk via bot API credentials. [#16183](https://github.com/infiniflow/ragflow/pull/16183)
|
||||
- Integrates WeCom via WebSocket connection. [#16175](https://github.com/infiniflow/ragflow/pull/16175)
|
||||
- File parsing: Adds fallback logic for PP-OCRv6 and similar text recognition models, and integrates image parsing within the PaddleOCR pipeline. [#16150](https://github.com/infiniflow/ragflow/pull/16150)
|
||||
|
||||
### Improvements
|
||||
|
||||
- Datasets
|
||||
- Adds an edge-case check to the file ingestion logic to safely link empty folders to a dataset. [#16296](https://github.com/infiniflow/ragflow/pull/16296)
|
||||
- Adds pagination to the `get_flatted_meta_by_kbs()` method to prevent CRUD failures relating to datasets with more than 10,000 documents. [#16095](https://github.com/infiniflow/ragflow/pull/16095)
|
||||
- Chat channels: Ensures end-user conversation histories persist across restarts but still separate when a channel is bound to a new dialog. [#16274](https://github.com/infiniflow/ragflow/pull/16274)
|
||||
|
||||
### i18n
|
||||
|
||||
- Expands i18n coverage and refines translations for the Korean UI. [#16203](https://github.com/infiniflow/ragflow/pull/16203);
|
||||
- Adds missing French translations for chat channels, username validation, and model editing. [#16217](https://github.com/infiniflow/ragflow/pull/16217)
|
||||
|
||||
### Bug fixes
|
||||
|
||||
- File parsing:
|
||||
- A `ValueError` was raised during `.docx` parsing on 'Heading' styles. [#16284](https://github.com/infiniflow/ragflow/pull/16284)
|
||||
- Tables in `.docx` files were silently removed by the laws document parser. [#16155](https://github.com/infiniflow/ragflow/pull/16155)
|
||||
- Lone Markdown headers were separated from their subsequent sections when a DeepDoc delimiter was set. [#16109](https://github.com/infiniflow/ragflow/pull/16109)
|
||||
- Markdown tables appeared twice in chunk results, once as a standalone chunk and again within a regular text chunk. [#16143](https://github.com/infiniflow/ragflow/pull/16143)
|
||||
- MCP
|
||||
- The MCP server hung indefinitely when encountering empty document pages; the final page of documents was silently dropped due to flawed pagination. [#16285](https://github.com/infiniflow/ragflow/pull/16285)
|
||||
- The MCP connection and dataset discovery process failed because the server's hardcoded fetch limit exceeded the introduced `page_size` restriction. [#16148](https://github.com/infiniflow/ragflow/pull/16148)
|
||||
- Dataflow
|
||||
- Restores the dataflow rerun endpoint and ensures the ingestion response includes the DSL payload to reliably render the timeline and parser views. [#16292](https://github.com/infiniflow/ragflow/pull/16292)
|
||||
- Restores dataflow parser defaults and returns the actual SSE payload, ensuring pipeline runs correctly surface message IDs and log updates. [#16290](https://github.com/infiniflow/ragflow/pull/16290)
|
||||
- LLM: Failed to use the new `gemini-3.5-flash` model via the Google Cloud (Vertex AI) provider using `eu` or `us` region endpoint. This is resolved by explicitly multi-region routing requests to the required `aiplatform.<region>.rep.googleapis.com` domains instead of synthesized `<region>-aiplatform.googleapis.com` hosts. [#15990](https://github.com/infiniflow/ragflow/pull/15990)
|
||||
- UI/UX: The metadata add modal sent empty values to the backend. [#15229](https://github.com/infiniflow/ragflow/pull/15229)
|
||||
|
||||
## v0.26.1
|
||||
|
||||
Released on June 17, 2026.
|
||||
|
||||
### New features
|
||||
|
||||
- **Model provider**: Allows users to modify the model type of existing model configurations. [#16029](https://github.com/infiniflow/ragflow/pull/16029)
|
||||
- **Chat channel**: Enables users to deploy RAGFlow assistants as chatbots within external messaging platforms like Discord and Feishu. [#15850](https://github.com/infiniflow/ragflow/pull/15850)
|
||||
- **Model providers**: Allows users to modify the model type of existing model configurations. [#16029](https://github.com/infiniflow/ragflow/pull/16029)
|
||||
- **Chat channels**: Enables users to deploy RAGFlow assistants as chatbots within external messaging platforms like Discord and Feishu. [#15850](https://github.com/infiniflow/ragflow/pull/15850)
|
||||
- **Observability**: Groups multi-turn chat traces by session within Langfuse to facilitate conversation debugging and replay. [#15679](https://github.com/infiniflow/ragflow/pull/15679)
|
||||
|
||||
### i18n
|
||||
|
||||
Reference in New Issue
Block a user