langgenius / dify

Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting you quickly go from prototype to production.
https://dify.ai
Other
53.37k stars 7.8k forks source link

chore: bump version to 0.12.0 #11056

Closed laipz8200 closed 6 days ago

laipz8200 commented 6 days ago

✨ What’s New in v0.12.0? ✨

[!Important]

Heads up! Starting with this version, we'll no longer support Python 3.10. Make sure to upgrade to Python 3.11 or 3.12 to stay current with our updates.

Hey everyone! We’ve been busy fine-tuning the platform and packing in some new features in version 0.12.0. Let’s see what’s new and improved:

🚀 Enhanced File Support for Workflow/Chatflow LLM Node and Chat/Agent

We’re excited to introduce the new file support capabilities for LLM Node and Basic Chat/Agent! This update significantly enhances multi-modal capabilities and smart document processing, providing more flexibility and power for your application development. Here are the key highlights:

File Variable Support in LLM Node

InsightFlow__begin InsightFlow__result

LLM Node now supports directly referencing File and Array File variables in Prompts, unlocking greater possibilities for developers. For example, you can upload multiple file variables (such as PDFs and images) and have the model collaboratively handle complex tasks, like summarizing report content or extracting key data. Multi-file support makes workflow design more efficient and seamless!

[!Tip]

  1. File Support Scope: The file types supported by the model may be more limited than the types allowed for upload. Be sure to read your model provider's official documentation to ensure that uploaded files can be processed correctly.
  2. Document Handling in Unsupported Models: If the model does not natively support processing document files, you will still need to use the Document Extractor for extracting content.
  3. Filtering Unsupported Files: To handle unsupported file types, consider using List Filter or IF-ELSE to screen them, ensuring smooth workflows.
  4. Relation to Vision Features: File support operates independently of the Vision toggle. As long as the model supports Vision capabilities, you can use files as input.

New Document-Type Support for Basic Chat and Agent

MarketSense AI

Basic Chat and Agent now include a Document toggle. If the model supports processing document-type files, you can enable this feature. For instance, you can upload a PDF report and let the Agent automatically analyze market data or assess content value, making such workflows simpler and smarter.

Enhanced Multi-Modal Capabilities

Sentiment Analysis

The new version extends support for multi-modal tasks. For example, you can upload audio files and have the model perform emotional analysis. This combination of text, audio, and file processing capabilities allows you to build more diverse and rich application scenarios.

⚙️ Improvements

That’s the scoop for v0.12.0! Until next time, keep exploring and innovating! 🌟

yihong0618 commented 6 days ago

ci failed may be caused by https://github.com/langgenius/dify/pull/11038 will try to figure out why too.

yihong0618 commented 6 days ago

@laipz8200 seems this need to be change too?

docker-compose.yaml
172:  CHROMA_AUTH_PROVIDER: ${CHROMA_AUTH_PROVIDER:-chromadb.auth.token_authn.TokenAuthClientProvider}
607:  chroma:
608:    image: ghcr.io/chroma-core/chroma:0.5.1 -> image: ghcr.io/chroma-core/chroma:0.5.20
bowenliang123 commented 6 days ago

11038 never runs or passes the vdb tests. It's a mistake. also cc @crazywoola

I would suggest to raise a separate PR to ensuring chroma vdb tests run against the corresponding chroma image. @yihong0618

yihong0618 commented 6 days ago

11038 never runs or passes the vdb tests. It's a mistake. also cc @crazywoola I would suggest to raise a separate PR to ensuring chroma vdb tests run against the corresponding chroma image. @yihong0618

11038 never runs or passes the vdb tests. It's a mistake. also cc @crazywoola I would suggest to raise a separate PR to ensuring chroma vdb tests run against the corresponding chroma image. @yihong0618

will do it now, thanks

laipz8200 commented 6 days ago

11038 never runs or passes the vdb tests. It's a mistake. also cc @crazywoola I would suggest to raise a separate PR to ensuring chroma vdb tests run against the corresponding chroma image. @yihong0618

These tests should run when pyproject.toml or the code related to vdb is changed. I missed including pyproject.toml in #10354.

yihong0618 commented 6 days ago

11038 never runs or passes the vdb tests. It's a mistake. also cc @crazywoola I would suggest to raise a separate PR to ensuring chroma vdb tests run against the corresponding chroma image. @yihong0618

These tests should run when pyproject.toml or the code related to vdb is changed. I missed including pyproject.toml in #10354.

fixed in https://github.com/langgenius/dify/pull/11057 @bowenliang123 can you also help to review?

bowenliang123 commented 6 days ago

11038 never runs or passes the vdb tests. It's a mistake. also cc @crazywoola I would suggest to raise a separate PR to ensuring chroma vdb tests run against the corresponding chroma image. @yihong0618

These tests should run when pyproject.toml or the code related to vdb is changed. I missed including pyproject.toml in #10354.

Never mind. And please make sure the poetry lockfile is included for running vdb test as well. The minor and even patch version is important, especially for Chroma.

yihong0618 commented 6 days ago

11038 never runs or passes the vdb tests. It's a mistake. also cc @crazywoola I would suggest to raise a separate PR to ensuring chroma vdb tests run against the corresponding chroma image. @yihong0618

These tests should run when pyproject.toml or the code related to vdb is changed. I missed including pyproject.toml in #10354.

Never mind. And please make sure the poetry lockfile is included for running vdb test as well. The minor and even patch version is important, especially for Chroma.

added already

bowenliang123 commented 6 days ago

Well noticed. Thanks.