The best Hacker News stories from Show from the past day
Latest posts:
Show HN: Servicer, pm2 alternative built on Rust and systemd
Servicer is a CLI to create and manage services on systemd. I have used pm2 in production and find it easy to use. However a lot of its functionality is specific to node.js, and I would prefer not to run my rust server as a fork of a node process. Systemd on the other hand has most of the things I need, but I found it cumbersome to use. There are a bunch of different commands and configurations- the .service file, systemctl to view status, journald to view logs which make systemd more complex to setup. I had to google for the a template and commands every time.<p>Servicer abstracts this setup behind an easy to use CLI, for instance you can use `ser create index.js --interpreter node --enable --start` to create a `.service` file, enable it on boot and start it. Servicer will also help if you wish to write your own custom `.service` files. Run `ser edit foo --editor vi` to create a service file in Vim. Servicer will provide a starting template so you don't need to google it. There are additional utilities like `ser which index.js` to view the path of the service and unit file.<p>```
Paths for index.js.ser.service:
+--------------+-----------------------------------------------------------+
| name | path |
+--------------+-----------------------------------------------------------+
| Service file | /etc/systemd/system/index.js.ser.service |
+--------------+-----------------------------------------------------------+
| Unit file | /org/freedesktop/systemd1/unit/index_2ejs_2eser_2eservice |
+--------------+-----------------------------------------------------------+
```<p>Servicer is daemonless and does not run in the background. It simply sets up systemd and gets out of the way. There are no forked services, everything is natively set up on systemd. You don't need to worry about resource consumption or servicer going down which will cause your app to stop.<p>Do give it a spin and review the codebase. The code is open source and MIT licensed- <a href="https://github.com/servicer-labs/servicer">https://github.com/servicer-labs/servicer</a>
Show HN: Lottielab – Create product animations in the browser easily
Hi HN! Today we are releasing Lottielab, a web-based animation tool, to the public as an open beta. The main tool for editing and exporting Lottie animations today is Adobe After Effects, a 30-year-old visual effects tool that’s not fit for this purpose, has a steep learning curve, and requires a patchwork of error-prone plugins. With Lottielab, we are aiming to reduce the friction of creating and editing product animations by providing an easy-to-use editor with out-of-the-box support for import and export of the Lottie format and many others. Feel free to play around with the tool and let me know what you think - I'm here to answer your questions. Happy animating!
Show HN: Lottielab – Create product animations in the browser easily
Hi HN! Today we are releasing Lottielab, a web-based animation tool, to the public as an open beta. The main tool for editing and exporting Lottie animations today is Adobe After Effects, a 30-year-old visual effects tool that’s not fit for this purpose, has a steep learning curve, and requires a patchwork of error-prone plugins. With Lottielab, we are aiming to reduce the friction of creating and editing product animations by providing an easy-to-use editor with out-of-the-box support for import and export of the Lottie format and many others. Feel free to play around with the tool and let me know what you think - I'm here to answer your questions. Happy animating!
Show HN: Lottielab – Create product animations in the browser easily
Hi HN! Today we are releasing Lottielab, a web-based animation tool, to the public as an open beta. The main tool for editing and exporting Lottie animations today is Adobe After Effects, a 30-year-old visual effects tool that’s not fit for this purpose, has a steep learning curve, and requires a patchwork of error-prone plugins. With Lottielab, we are aiming to reduce the friction of creating and editing product animations by providing an easy-to-use editor with out-of-the-box support for import and export of the Lottie format and many others. Feel free to play around with the tool and let me know what you think - I'm here to answer your questions. Happy animating!
Show HN: Llama2 Embeddings FastAPI Server
Author here. I just wanted a quick and easy way to easily submit strings to a REST API and get back the embedding vectors in JSON using Llama2 and other similar LLMs, so I put this together over the past couple days. It's very quick and easy to set up and totally self-contained and self-hosted. You can easily add new models to it by simply adding the HuggingFace URL to the GGML format model weights. Two models are included by default, and these are automatically downloaded the first time it's run.<p>It lets you not only submit text strings and get back the embeddings, but also to compare two strings and get back their similarity score (i.e., the cosine similarity of their embedding vectors). You can also upload a plaintext file or PDF and get back all the embeddings for every sentence in the file as a zipped JSON file (and you can specify the layout of this JSON file).<p>Each time an embedding is computed for a given string with a given LLM, that vector is stored in the SQlite database and can be returned immediately. You can also search across all stored vectors easily using a query string; this uses FAISS which is integrated.<p>There are lots of nice performance enhancements, including parallel inference, db write queue, fully async everything, and even a RAM Disk feature to speed up model loading.<p>I’m working now on adding additional API endpoints for easily generating sentiment scores using presets for different focus areas, but that’s still work-in-progress (the code for this so far is in the repo though).
Show HN: Llama2 Embeddings FastAPI Server
Author here. I just wanted a quick and easy way to easily submit strings to a REST API and get back the embedding vectors in JSON using Llama2 and other similar LLMs, so I put this together over the past couple days. It's very quick and easy to set up and totally self-contained and self-hosted. You can easily add new models to it by simply adding the HuggingFace URL to the GGML format model weights. Two models are included by default, and these are automatically downloaded the first time it's run.<p>It lets you not only submit text strings and get back the embeddings, but also to compare two strings and get back their similarity score (i.e., the cosine similarity of their embedding vectors). You can also upload a plaintext file or PDF and get back all the embeddings for every sentence in the file as a zipped JSON file (and you can specify the layout of this JSON file).<p>Each time an embedding is computed for a given string with a given LLM, that vector is stored in the SQlite database and can be returned immediately. You can also search across all stored vectors easily using a query string; this uses FAISS which is integrated.<p>There are lots of nice performance enhancements, including parallel inference, db write queue, fully async everything, and even a RAM Disk feature to speed up model loading.<p>I’m working now on adding additional API endpoints for easily generating sentiment scores using presets for different focus areas, but that’s still work-in-progress (the code for this so far is in the repo though).
Show HN: Llama2 Embeddings FastAPI Server
Author here. I just wanted a quick and easy way to easily submit strings to a REST API and get back the embedding vectors in JSON using Llama2 and other similar LLMs, so I put this together over the past couple days. It's very quick and easy to set up and totally self-contained and self-hosted. You can easily add new models to it by simply adding the HuggingFace URL to the GGML format model weights. Two models are included by default, and these are automatically downloaded the first time it's run.<p>It lets you not only submit text strings and get back the embeddings, but also to compare two strings and get back their similarity score (i.e., the cosine similarity of their embedding vectors). You can also upload a plaintext file or PDF and get back all the embeddings for every sentence in the file as a zipped JSON file (and you can specify the layout of this JSON file).<p>Each time an embedding is computed for a given string with a given LLM, that vector is stored in the SQlite database and can be returned immediately. You can also search across all stored vectors easily using a query string; this uses FAISS which is integrated.<p>There are lots of nice performance enhancements, including parallel inference, db write queue, fully async everything, and even a RAM Disk feature to speed up model loading.<p>I’m working now on adding additional API endpoints for easily generating sentiment scores using presets for different focus areas, but that’s still work-in-progress (the code for this so far is in the repo though).
CSS Selectors: A Visual Guide
Show HN: AI-town, run your own custom AI world SIM with JavaScript
Hi HN community! We want to share AI-town, a deployable starter kit for building and customizing your own version of AI simulation - a virtual town where AI characters live, chat and socialize.<p>Inspired by great work from the Stanford Generative Agent paper (<a href="https://arxiv.org/abs/2304.03442" rel="nofollow noreferrer">https://arxiv.org/abs/2304.03442</a>).<p>A few features:
- Includes a convex.dev backed server-side game engine that handles global state
- Multiplayer ready. Deployment ready
- 100% Typescript
- Easily customizable. You can fork it, change character memories, add new sprites/tiles and you have a custom AI simulation<p>The goal is to democratize building your own simulation environment with AI agents. Would love to see the community build more complex interactions on top of this. Let us know what you think!<p>Demo: <a href="https://www.convex.dev/ai-town" rel="nofollow noreferrer">https://www.convex.dev/ai-town</a><p>I made a world Cat Town to demonstrate how to customize AI town. Using C(h)atGPT :)<p>Demo: <a href="https://cat-town.fly.dev/" rel="nofollow noreferrer">https://cat-town.fly.dev/</a>
Code: <a href="https://github.com/ykhli/cat-town">https://github.com/ykhli/cat-town</a>
Show HN: AI-town, run your own custom AI world SIM with JavaScript
Hi HN community! We want to share AI-town, a deployable starter kit for building and customizing your own version of AI simulation - a virtual town where AI characters live, chat and socialize.<p>Inspired by great work from the Stanford Generative Agent paper (<a href="https://arxiv.org/abs/2304.03442" rel="nofollow noreferrer">https://arxiv.org/abs/2304.03442</a>).<p>A few features:
- Includes a convex.dev backed server-side game engine that handles global state
- Multiplayer ready. Deployment ready
- 100% Typescript
- Easily customizable. You can fork it, change character memories, add new sprites/tiles and you have a custom AI simulation<p>The goal is to democratize building your own simulation environment with AI agents. Would love to see the community build more complex interactions on top of this. Let us know what you think!<p>Demo: <a href="https://www.convex.dev/ai-town" rel="nofollow noreferrer">https://www.convex.dev/ai-town</a><p>I made a world Cat Town to demonstrate how to customize AI town. Using C(h)atGPT :)<p>Demo: <a href="https://cat-town.fly.dev/" rel="nofollow noreferrer">https://cat-town.fly.dev/</a>
Code: <a href="https://github.com/ykhli/cat-town">https://github.com/ykhli/cat-town</a>
Show HN: AI-town, run your own custom AI world SIM with JavaScript
Hi HN community! We want to share AI-town, a deployable starter kit for building and customizing your own version of AI simulation - a virtual town where AI characters live, chat and socialize.<p>Inspired by great work from the Stanford Generative Agent paper (<a href="https://arxiv.org/abs/2304.03442" rel="nofollow noreferrer">https://arxiv.org/abs/2304.03442</a>).<p>A few features:
- Includes a convex.dev backed server-side game engine that handles global state
- Multiplayer ready. Deployment ready
- 100% Typescript
- Easily customizable. You can fork it, change character memories, add new sprites/tiles and you have a custom AI simulation<p>The goal is to democratize building your own simulation environment with AI agents. Would love to see the community build more complex interactions on top of this. Let us know what you think!<p>Demo: <a href="https://www.convex.dev/ai-town" rel="nofollow noreferrer">https://www.convex.dev/ai-town</a><p>I made a world Cat Town to demonstrate how to customize AI town. Using C(h)atGPT :)<p>Demo: <a href="https://cat-town.fly.dev/" rel="nofollow noreferrer">https://cat-town.fly.dev/</a>
Code: <a href="https://github.com/ykhli/cat-town">https://github.com/ykhli/cat-town</a>
Show HN: User Persona Generator
I hate talking to people.<p>So I made ChatGPT do it for me.
Show HN: Epsilla – Open-source vector database with low query latency
Hey HN! We are building Epsilla (<a href="https://github.com/epsilla-cloud/vectordb">https://github.com/epsilla-cloud/vectordb</a>), an open-source, self-hostable vector database for semantic similarity search that specializes in low query latency.<p>When do we need a vector database? For example, GPT-3.5 has a 16k context window limit. If we want to let it answer a question about a 300 page book, we cannot put the whole book content into the context. We have to choose the sections of the book that are most relevant to the question. Vector database is specialized at ranking and picking the most relevant content from a large pool of documents based on their semantic similarity.<p>Most vector databases utilize hierarchical navigational small world (HNSW) for indexing the vectors for high precision vector search, and its latency significantly degrades when the precision target is higher than 95%.<p>At a previous company, we worked on building the parallel graph traversal engine. We realized that the bottleneck of HNSW performance is because there are too many sequential traversal steps that don't fully leverage multi-core CPU computation resources. After some research, we found that there are algorithms such as SpeedANN that are targeting this problem, which is not leveraged by industry yet. So we built the Epsilla vector database to turn the research into a production system.<p>With Epsilla, we shoot for 10x lower vector search latency compared to HNSW based vector databases. We did an initial benchmark against the top open source vector databases: <a href="https://medium.com/@richard_50832/benchmarking-epsilla-with-some-of-the-top-vector-databases-543e2b7708e5" rel="nofollow noreferrer">https://medium.com/@richard_50832/benchmarking-epsilla-with-...</a><p>We provide a Docker image for you to install Epsilla backend locally, and provide a Python client and a JavaScript client to connect and interact with it.<p>Quickstart:<p><pre><code> docker pull epsilla/vectordb
docker run --pull=always -d -p 8888:8888 epsilla/vectordb
pip install pyepsilla
git clone https://github.com/epsilla-cloud/epsilla-python-client.git
cd examples
python hello_epsilla.py
</code></pre>
We just started a month ago. We'd love to hear what you think, and more importantly, what you wish to see in the future. We are thinking about a serverless vector database on cloud with a consumption based pricing model, and we are eager to get your feedback.
Show HN: Epsilla – Open-source vector database with low query latency
Hey HN! We are building Epsilla (<a href="https://github.com/epsilla-cloud/vectordb">https://github.com/epsilla-cloud/vectordb</a>), an open-source, self-hostable vector database for semantic similarity search that specializes in low query latency.<p>When do we need a vector database? For example, GPT-3.5 has a 16k context window limit. If we want to let it answer a question about a 300 page book, we cannot put the whole book content into the context. We have to choose the sections of the book that are most relevant to the question. Vector database is specialized at ranking and picking the most relevant content from a large pool of documents based on their semantic similarity.<p>Most vector databases utilize hierarchical navigational small world (HNSW) for indexing the vectors for high precision vector search, and its latency significantly degrades when the precision target is higher than 95%.<p>At a previous company, we worked on building the parallel graph traversal engine. We realized that the bottleneck of HNSW performance is because there are too many sequential traversal steps that don't fully leverage multi-core CPU computation resources. After some research, we found that there are algorithms such as SpeedANN that are targeting this problem, which is not leveraged by industry yet. So we built the Epsilla vector database to turn the research into a production system.<p>With Epsilla, we shoot for 10x lower vector search latency compared to HNSW based vector databases. We did an initial benchmark against the top open source vector databases: <a href="https://medium.com/@richard_50832/benchmarking-epsilla-with-some-of-the-top-vector-databases-543e2b7708e5" rel="nofollow noreferrer">https://medium.com/@richard_50832/benchmarking-epsilla-with-...</a><p>We provide a Docker image for you to install Epsilla backend locally, and provide a Python client and a JavaScript client to connect and interact with it.<p>Quickstart:<p><pre><code> docker pull epsilla/vectordb
docker run --pull=always -d -p 8888:8888 epsilla/vectordb
pip install pyepsilla
git clone https://github.com/epsilla-cloud/epsilla-python-client.git
cd examples
python hello_epsilla.py
</code></pre>
We just started a month ago. We'd love to hear what you think, and more importantly, what you wish to see in the future. We are thinking about a serverless vector database on cloud with a consumption based pricing model, and we are eager to get your feedback.
Show HN: Epsilla – Open-source vector database with low query latency
Hey HN! We are building Epsilla (<a href="https://github.com/epsilla-cloud/vectordb">https://github.com/epsilla-cloud/vectordb</a>), an open-source, self-hostable vector database for semantic similarity search that specializes in low query latency.<p>When do we need a vector database? For example, GPT-3.5 has a 16k context window limit. If we want to let it answer a question about a 300 page book, we cannot put the whole book content into the context. We have to choose the sections of the book that are most relevant to the question. Vector database is specialized at ranking and picking the most relevant content from a large pool of documents based on their semantic similarity.<p>Most vector databases utilize hierarchical navigational small world (HNSW) for indexing the vectors for high precision vector search, and its latency significantly degrades when the precision target is higher than 95%.<p>At a previous company, we worked on building the parallel graph traversal engine. We realized that the bottleneck of HNSW performance is because there are too many sequential traversal steps that don't fully leverage multi-core CPU computation resources. After some research, we found that there are algorithms such as SpeedANN that are targeting this problem, which is not leveraged by industry yet. So we built the Epsilla vector database to turn the research into a production system.<p>With Epsilla, we shoot for 10x lower vector search latency compared to HNSW based vector databases. We did an initial benchmark against the top open source vector databases: <a href="https://medium.com/@richard_50832/benchmarking-epsilla-with-some-of-the-top-vector-databases-543e2b7708e5" rel="nofollow noreferrer">https://medium.com/@richard_50832/benchmarking-epsilla-with-...</a><p>We provide a Docker image for you to install Epsilla backend locally, and provide a Python client and a JavaScript client to connect and interact with it.<p>Quickstart:<p><pre><code> docker pull epsilla/vectordb
docker run --pull=always -d -p 8888:8888 epsilla/vectordb
pip install pyepsilla
git clone https://github.com/epsilla-cloud/epsilla-python-client.git
cd examples
python hello_epsilla.py
</code></pre>
We just started a month ago. We'd love to hear what you think, and more importantly, what you wish to see in the future. We are thinking about a serverless vector database on cloud with a consumption based pricing model, and we are eager to get your feedback.
Show HN: Little Rat – Chrome extension monitors network calls of all extensions
Hi HN<p>I needed a way to monitor network calls made by chrome extensions so I made a small extension.<p>You can install it by dropping the zip or crx into the extensions page. It'll be on the chrome store whenever/if it gets through the review.<p>Hopefully it's useful to others.<p><a href="https://github.com/dnakov/little-rat">https://github.com/dnakov/little-rat</a><p><a href="https://twitter.com/dnak0v" rel="nofollow noreferrer">https://twitter.com/dnak0v</a>
Show HN: Little Rat – Chrome extension monitors network calls of all extensions
Hi HN<p>I needed a way to monitor network calls made by chrome extensions so I made a small extension.<p>You can install it by dropping the zip or crx into the extensions page. It'll be on the chrome store whenever/if it gets through the review.<p>Hopefully it's useful to others.<p><a href="https://github.com/dnakov/little-rat">https://github.com/dnakov/little-rat</a><p><a href="https://twitter.com/dnak0v" rel="nofollow noreferrer">https://twitter.com/dnak0v</a>
Show HN: Little Rat – Chrome extension monitors network calls of all extensions
Hi HN<p>I needed a way to monitor network calls made by chrome extensions so I made a small extension.<p>You can install it by dropping the zip or crx into the extensions page. It'll be on the chrome store whenever/if it gets through the review.<p>Hopefully it's useful to others.<p><a href="https://github.com/dnakov/little-rat">https://github.com/dnakov/little-rat</a><p><a href="https://twitter.com/dnak0v" rel="nofollow noreferrer">https://twitter.com/dnak0v</a>
Show HN: Little Rat – Chrome extension monitors network calls of all extensions
Hi HN<p>I needed a way to monitor network calls made by chrome extensions so I made a small extension.<p>You can install it by dropping the zip or crx into the extensions page. It'll be on the chrome store whenever/if it gets through the review.<p>Hopefully it's useful to others.<p><a href="https://github.com/dnakov/little-rat">https://github.com/dnakov/little-rat</a><p><a href="https://twitter.com/dnak0v" rel="nofollow noreferrer">https://twitter.com/dnak0v</a>
Show HN: LLMs can generate valid JSON 100% of the time
Outlines is a Python library that focuses on text generation with large language models. Brandon and I are not LLM experts and started the project a few months ago because we wanted to understand better how the generation process works. Our original background is probabilistic, relational and symbolic programming.<p>Recently we came up with a fast way to generate text that matches a regex (<a href="https://blog.normalcomputing.ai/posts/2023-07-27-regex-guided-generation/regex-guided-generation.html" rel="nofollow noreferrer">https://blog.normalcomputing.ai/posts/2023-07-27-regex-guide...</a>). The basic idea is simple: regular expressions have an equivalent Deterministic-Finite Automaton (DFA) representation. We can transform this DFA into a generative model: in each state we get a list of symbols which correspond to completions that partially match the regular expression. We mask the other symbols in the logits returned by a large language model, sample a new symbol and move to the next state. The subtelty is that language models work with tokens, not symbols, so we derive a new FSM whose alphabet is the model's vocabulary. We can do this in only one pass over the vocabulary.<p>Generating the token masks thus only requires a dictionary lookup at each state. Our method blows other libraries like Microsoft's guidance out of the water.<p>From there it was only a small leap to be able to generate text that follows a JSON schema (<a href="https://json-schema.org/" rel="nofollow noreferrer">https://json-schema.org/</a>), or is parseable into a Pydantic model (<a href="https://docs.pydantic.dev/latest/usage/models/" rel="nofollow noreferrer">https://docs.pydantic.dev/latest/usage/models/</a>). The method works with union types, optional types, nested schemas, arrays, everything. It is guaranteed that the output is parseable.<p>I think it's cool, and I've spent a lot of time watching even tiny models output valid JSON over the weekend. Hope you will too.<p>I look forward to feedback, bug reports, feature requests and discussions!<p>Edit: Link to our pre-print explaining the method and how this can be extended to generate text that follows a Context-Free Grammar <a href="https://arxiv.org/abs/2307.09702" rel="nofollow noreferrer">https://arxiv.org/abs/2307.09702</a>