compress-gpt
llama_index
| compress-gpt | llama_index | |
|---|---|---|
| 2 | 75 | |
| 218 | 31,837 | |
| - | 6.6% | |
| 4.0 | 10.0 | |
| about 1 year ago | about 11 hours ago | |
| Python | Python | |
| - | MIT License |
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.
compress-gpt
-
Ask HN: Have you seen an effective method for compressing GPT prompts?
I'm interested in something that can take frequently used system prompts of mine and compress them in a way that still gets the same results with different user messages.
Does this exist?
Things I've seen:
https://github.com/yasyf/compress-gpt
https://news.ycombinator.com/item?id=35626433
https://news.ycombinator.com/item?id=35488291
- Ask HN: Bypassing GPT-4 8k tokens limit
llama_index
- LlamaIndex: A data framework for your LLM applications
- FLaNK AI - 01 April 2024
-
Show HN: Ragdoll Studio (fka Arthas.AI) is the FOSS alternative to character.ai
For anyone curious llamaindex's "prompt mixins", they're actually dead simple: https://github.com/run-llama/llama_index/blob/8a8324008764a7... - and maybe no longer supported.
I basically reinvented this wheel in ragdoll but made it more dynamic: https://github.com/bennyschmidt/ragdoll/blob/master/src/util...
- LlamaIndex is a data framework for your LLM applications
- How to verify that a snippet of Python code doesn't access protected members
-
🆓 Local & Open Source AI: a kind ollama & LlamaIndex intro
Being able to plug third party frameworks (Langchain, LlamaIndex) so you can build complex projects
-
I made an app that runs Mistral 7B 0.2 LLM locally on iPhone Pros
Mistral Instruct does use a system prompt.
You can see the raw format here: https://www.promptingguide.ai/models/mistral-7b#chat-templat... and you can see how LllamaIndex uses it here (as an example): https://github.com/run-llama/llama_index/blob/1d861a9440cdc9...
-
Top 5 Vector Database Videos of 2023 🎥
Learn how to use Milvus as persistent vector storage with LlamaIndex in under 5 minutes.
-
What's going on in the Zilliz Universe? December 2023
▶️ Read Blog 📷 Watch Demo 🦙 Notebook using Pipelines inside LlamaIndex
-
First 15 Open Source Advent projects
15. LlamaIndex | Github | tutorial
What are some alternatives?
flash-attention - Fast and memory-efficient exact attention
langchain - ⚡ Building applications with LLMs through composability ⚡ [Moved to: https://github.com/langchain-ai/langchain]
Text_summary
langchain - 🦜🔗 Build context-aware reasoning applications
private-gpt - Interact with your documents using the power of GPT, 100% privately, no data leaks
chatgpt-retrieval-plugin - The ChatGPT Retrieval Plugin lets you easily find personal or work documents by asking questions in natural language.
text-generation-webui - A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.
gpt-llama.cpp - A llama.cpp drop-in replacement for OpenAI's GPT endpoints, allowing GPT-powered apps to run off local llama.cpp models instead of OpenAI.
localGPT - Chat with your documents on your local device using GPT models. No data leaves your device and 100% private.
Redis - Redis is an in-memory database that persists on disk. The data model is key-value, but many different kind of values are supported: Strings, Lists, Sets, Sorted Sets, Hashes, Streams, HyperLogLogs, Bitmaps.
Open-Assistant - OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.