openrouter-runner
llm
openrouter-runner | llm | |
---|---|---|
12 | 28 | |
413 | 3,268 | |
20.6% | - | |
9.4 | 9.3 | |
about 2 months ago | 15 days ago | |
Python | Python | |
MIT License | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
openrouter-runner
-
Show HN: Route your prompts to the best LLM
I've bumped into a few of these. I use https://openrouter.ai as a model abstraction, but not as a router. https://withmartian.com does the same thing but with a more enterprise feel. Also https://www.braintrustdata.com/ though it's less clear how committed they are to that feature.
That said, while I've really enjoyed the LLM abstraction (making it easy for me to test different models without changing my code), I haven't felt any desire for a router. I _do_ have some prompts that I send to gpt-3.5-turbo, and could potentially use other models, but it's kind of niche.
In part this is because I try to do as much in a single prompt as I can, meaning I want to use a model that's able to handle the hardest parts of the prompt and then the easy parts come along with. As a result there's not many "easy" prompts. The easy prompts are usually text fixup and routing.
My "routing" prompts are at a different level of abstraction, usually routing some input or activity to one of several prompts (each of which has its own context, and the sum of all contexts across those prompts is too large, hence the routing). I don't know if there's some meaningful crossover between these two routing concepts.
Another issue I have with LLM portability is the use of tools/functions/structured output. Opus and Gemini Pro 1.5 have kind of implemented this OK, but until recently GPT was the only halfway decent implementation of this. This seems to be an "advanced" feature, yet it's also a feature I use even more with smaller prompts, as those small prompts are often inside some larger algorithm and I don't want the fuss of text parsing and exceptions from ad hoc output.
But in the end I'm not price sensitive in my work, so I always come back to the newest GPT model. If I make a switch to Opus it definitely won't be to save money! And I'm probably not going to want to fiddle, but instead make a thoughtful choice and switch the default model in my code.
- Openrouter
- Integra múltiples APIs de IA en una sola plataforma
-
Collection of notebooks showcasing some fun and effective ways of using Claude
Why not use something like http://openrouter.ai? Pay as you go and you can select any model you want. Heaven!
-
World_SIM: LLM prompted to act as a sentient CLI universe simulator
teknium / Nous released Mistral finetunes (Hermes) that are quite great, and even published the datasets used for training.
But for the worldsim I think they are really using Claude (probably Haiku or Sonnet) via openrouter (https://openrouter.ai/).
-
Show HN: Plandex – an AI coding engine for complex tasks
Not affiliated with the project but you could use something like OpenRouter to give users a massive list of models to choose from with fairly minimal effort
https://openrouter.ai/
-
The Next Generation of Claude (Claude 3)
> I hate that they require a phone number
https://openrouter.ai/ lets you make one account and get API access to a bunch of different models. They also provide access to hosted versions of a bunch of open models.
Useful if you want to compare 15 different models without bothering to create 15 different accounts or download 15 x 20GB of models :)
-
The killer app of Gemini Pro 1.5 is video
You sure can! NeuroEngine[1] hosts some nice free demos of what are basically the state of the art in unfiltered models, and if you need API access, OpenRouter[2] has dozens of unfiltered models to choose from.
[1] https://www.neuroengine.ai/
[2] https://openrouter.ai/
-
OpenAI has Text to Speech Support now!
However, this needs to be changed as other providers like OpenRouter can also start supporting this feature in the future.
-
How to narrow down interest and where to begin?
Great resources for me are - The LangChain Blog: Very technical but great graphics of complex topics. Gives you a good understanding of what is currently possible and what the hot topics are - Product Hunt: Great resource to see what others are building with AI - Replicate and OpenRouter for custom made / fine tuned models - AI Twitter
llm
-
Show HN: PDF to Podcast – Convert Any PDF into a Podcast Episode
I run MacWhisper on my laptop, and often dump podcast MP3s into it, extract the Whisper transcript and then feed that through a long context model like Claude 3 Haiku/Opus or Gemini Pro 1.5/Gemini Flash using my https://llm.datasette.io/ tool to answer questions against that transcript.
- Access LLMs from the Command Line
-
iTerm2 and AI Hype Overload
Access LLMs from the command line: https://github.com/simonw/llm
-
Show HN: Interactive Graph by LLM (GPT-4o)
- *Description*: The `llm` command-line tool leverages large language models, such as OpenAI's GPT-3, to make it easier to incorporate AI functionalities into your command-line tasks. You can use it to generate text, answer questions, and assist with coding or other language-based tasks directly from your terminal.
- **Link**: [llm on GitHub](https://github.com/simonw/llm)
-
GPT-4o
Slight off-topic, but I noticed you've updated your llm CLI app to work with the 4o model (plus bunch of other APIs through plugins). Kudos for working extremely fast. I'm really grateful for your tool; I tried many others, but for some reason none clicked as much as your.
Link in case other readers are curious: https://llm.datasette.io
- FLaNK AI-April 22, 2024
-
Show HN: I made a tool to clean and convert any webpage to Markdown
That's a great use case, you might be able to do this if you've got a copy and paste on the command line with
https://github.com/simonw/llm
In between. An alias like pdfwtf translating to "paste | llm command | copy"
-
Command R+: A Scalable LLM Built for Business
I added support for this model to my LLM CLI tool via a new plugin: https://github.com/simonw/llm-command-r
So now you can do this:
pipx install llm
-
The Next Generation of Claude (Claude 3)
If you're willing to use the CLI, Simon Willison's llm library[0] should do the trick.
[0] https://github.com/simonw/llm
- Show HN: I made an app to use local AI as daily driver
What are some alternatives?
plandex - AI driven development in your terminal. Designed for large, real-world tasks.
ollama - Get up and running with Llama 3, Mistral, Gemma, and other large language models.
llm-claude-3 - LLM plugin for interacting with the Claude 3 family of models
langroid - Harness LLMs with Multi-Agent Programming
exllama - A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.
multi-gpt - A Clojure interface into the GPT API with advanced tools like conversational memory, task management, and more
jehuty - Fluent API to interact with chat based GPT model
llm-replicate - LLM plugin for models hosted on Replicate
aipl - Array-Inspired Pipeline Language
ad-llama - Structured inference with Llama 2 in your browser
simpleaichat - Python package for easily interfacing with chat apps, with robust features and minimal code complexity.
onprem - A tool for running on-premises large language models with non-public data