v0.14.1.2

Local chat and embedding, much more accurate RAG with reranking!

If you have any problems when using GGA release, please raise an issue.

In the open source community, we can find that the development of LLM and embedding models has made a great progress, with many excellent models emerging. For individuals, using these open source models can guarantee 100% security of private information and almost close to 90% experience without paying anything extra for it!
As a result, I spent some time researching and testing the usage and effectiveness of these models in order to be able to best adapt them to GGA, which now has integrated support for Ollama and some local embedding models for an optimal experience on the PC.

Ollama SUPPORT !!!

Ollama allows you to run open-source large language models, such as Llama 2, locally, it optimizes setup and configuration details, including CPU and GPU usage.
In order to use Ollama, Following these steps:

1. Download and install Ollama onto the available supported platforms.
2. Run Ollama, and open your CLI(command line) and use <ollama pull qwen:7b-chat> to download the model(best suit for PC both in English and Chinese).
3. Now you can run GGA, enjoy it!

The model qwen:7b-Chat optimally balances performance and speed, and it has 32k context length, making it ideal for RAG. Other chat model will be supported soon.

You can get more details in its repo.

The actual inference time depends on the model size and your hardware performance.

LOCAL EMBEDDING SUPPORT !!!

Embed some big files can cost a considerable mount of money, let's try Bge embedding models.You can find more info in its hugging face blog and Github repo.
In GGA, all you have to do is choose it, and GGA will do all jobs are needed to be done for you.

Rerank SUPPORT!!!

About rerank, you can check this blog. In short, Rerank can offering a straightforward, low-complexity method to refine search outcomes, enabling the integration of semantic relevance into current search systems without significant infrastructural modifications.
In GGA, bge-reranker is the default rerank model.

What's other Changed

• Openai v1.0 and Langchain v0.1 Migration Completed. by @Wannabeasmartguy in #4
• RAG Web Search and better display of knowledge base information by @Wannabeasmartguy in #5

Fix:

• Mixing of different dimensional embedding vectors triggered by switching knowledge bases.
• Typography is messed up when the browser zooms in and out
• Error display for some components

Add:

• RAG Web Search history can be saved locally, which is saved under search_his.
• Re-ranking the similar search results will now be performed by default when doing RAG Q&A, which will significantly improve the accuracy of the search results.The Re-rank model defaults to using Bge-reranker-large, which is saved under '. /embedding model'. You can manually turn it off by checking the box in RAG Basic Setting under RAG Basic Setting in the right column.

Full Changelog: v0.10.1...v0.14.1.2

v0.10.1

Upgrade completed and Dall-E-3, RAG search added

I'm glad to tell you all willing to give attention on this repo that the upgrade to Openai v1.0 and Langchain v0.1 is completed.

Besides, in v0.9.0 I add an Dall-E-3 interface. If you have access to the Azure OpenAI API, it's a waste not to try the Dall-E-3 model to generate images!

In this interface, you can not only generate rich images with Dall-E-3, but also see how ChatGPT can polish your Prompt and improve your Prompt skills.

In v0.10, I upgrade a better display of knowledge base information, which make your information block size fit your display size.

Detail message as below:

Another impressive update is RAG Web Search, which is inspired by search_with_lepton. By harnessing the extensive knowledge of search engines in conjunction with the exceptional capabilities of LLM, you can obtain precise answers and a wide range of references.

Hope you can enjoy it!

---

我很高兴地告诉所有关注这个软件仓库的人，向 Openai v1.0 和 Langchain v0.1 的升级改写已经完成。

此外，我在 v0.9.0 中添加了 Dall-E-3 接口。如果你能访问 Azure OpenAI API，不试试用 Dall-E-3 模型生成图像实在是太浪费了！

在这个界面中，你不仅可以用 Dall-E-3 生成丰富的图像，还能看到 ChatGPT 如何打磨你的 Prompt，提高你的 Prompt 技能。

在 v0.10 版中，我升级了知识库信息的显示方式，使信息块的大小更适合您的显示屏尺寸。

另一个令人印象深刻的更新是RAG 网络搜索，它的灵感来自**search_with_lepton**。通过利用搜索引擎的广泛知识和 LLM 的卓越功能，您可以获得精确的答案和广泛的参考资料。

希望你们能喜欢！

---

Full Changelog: v0.8.0...v0.10.1

v0.8.0

Happy New Year! As you can see, I'm still updating this project. Due to my work, it was temporarily suspended for a while a while ago.

In my following update, I will focus on code refactoring: it is necessary to upgrade the original openai pack from v0.27 to v1.0 for the future of OpenAI's possible multimodal model service and possible integration with Microsoft (and its Azure), and this update is non-sequential, so there will be a lot of work to be done.

As for the README.md haven't updated, I would like to introduce a new function is added in v0.8.0, which description would be added in README soon:
Now, you can see the kownledge contents, as long as you input the kownledge base's path.(Only for chroma)

Hope you enjoy it!

---

新年快乐！如你所见，我仍在更新这个项目。前段时间，由于工作原因，这个项目暂时中止了一段时间。

在接下来的更新中，我将专注于代码重构：有必要将原始的 openai 包从 v0.27 升级到 v1.0，以实现 OpenAI 未来可能的多模态模型服务以及与微软（及其 Azure）的可能集成。

至于还未更新的 README.md，我想介绍一下 v0.8.0 中添加的一个新功能，相关说明将很快添加到 README 中：
现在，只要输入 kownledge base 的路径，就可以看到 kownledge 的内容了。

希望大家喜欢！

Full Changelog: 0.7.3.1...v0.8.0

v0.7.0.1

Full Changelog: v0.6.1...v0.7.0.1

GGA v0.6.1

Inspired by Fooocus, I made a portable version, download it and change .env_sample to .env , fill in your own OpenAI Key and base, then double-click run.bat, the program will start running!

Full Changelog: v0.6.0...v0.6.1