towhee VS ai

As another commenter noted, Milvus is overkill and a "bit much" if you're learning/playing.

A good intro to the field with progression towards a full Milvus implementation could be starting with towhee[0] (which is also supported by Milvus).

towhee has an example to do exactly what you want with CLIP[1].

[0] - https://towhee.io/

[1] - https://github.com/towhee-io/examples/tree/main/image/text_i...

The description of this is kind of confusing but I think the easiest way to understand it is that it is a data processing pipeline of sorts. Take unstructured data and apply transformation and computation. A similar project to this is Towhee (https://github.com/towhee-io/towhee). This project tries to simplify unstructured data processing and provides pretrained models and pipelines from their hub.

Milvus also has incredible flexibility when it comes to choosing an indexing strategy, and we also have a library specifically meant to help vectorize a variety of data called Towhee (https://github.com/towhee-io/towhee).

Benchmarking the models with towhee is as simple as:

The project's homepage is https://github.com/towhee-io/towhee, and you can find more about towhee by going through the documents.

I made a tutorial for building an image search engine with python. The code example is as simple as 10 lines of code, using Towhee and Milvus To put images into the search engine:

Traditionally, I've done this through PyTorch by adding a hook, but this requires knowledge of the model itself (i.e. model arch and layer names). I found https://github.com/Hironsan/awesome-embedding-models but it didn't provide many CV-focused open-source projects. There's also https://github.com/towhee-io/towhee which is great but more targeted towards application development.

You can check the result from the tutorial.

The Vercel AI SDK is built for OpenAI APIs and includes a range of tools for utilizing OpenAI APIs.

The AI is calling a function (https://platform.openai.com/docs/guides/function-calling) that is mapped to developer-controlled logic. The easiest thing to do is render specific UIs for every function call, but you can render however you'd like.

We kept the code snippets in the blog post brief, but you can see the full code for the demo here: https://github.com/vercel/ai/tree/main/examples/next-ai-rsc

In this blog post, we'll build a Next.js chatbot that runs on your computer. We'll use Ollama to serve the OpenHermes 2.5 Mistral LLM (large language model) locally, the Vercel AI SDK to handle stream forwarding and rendering, and ModelFusion to integrate Ollama with the Vercel AI SDK. The chatbot will be able to generate responses to user messages in real-time.

I recently set up the Next-Langchain-starter from Vercel, and it is phenomenal: Easy to setup, easy to modify. So far I've only done a few modifications:

Vercel AI SDK Playground Documentation

I used infrastructure as code (IaC) to provision and deploy Vercel's next-openai example. IaC is useful because it applies the same rigor of application code development to infrastructure provisioning. Instead of manual point and click in a cloud console which can be unrepeatable or error-prone, you just store and change all infrastructure configurations as code in source control .

You can use LLM providers other than hugging face such as Anthropic, Langchain adn OpenAI as well. Follow this doc to change the route handler(/api/chat/route.ts) and refer to the section of your chosen LLM provider.

**References: If you got stuck anywhere feel free to reach out. The Vercel documentation is excellent and the Github repo is also easily clonable if you don't have time to code from the start and just want to get stuck in customising.