local_llama
zep
local_llama | zep | |
---|---|---|
10 | 15 | |
179 | 1,978 | |
- | 9.0% | |
6.6 | 9.0 | |
10 days ago | 7 days ago | |
Python | Go | |
Apache License 2.0 | 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.
local_llama
-
Discussion: Biggest Roadblocks to Deploy LLMs to Production
I work with AWS daily, terraform, Python and java creating and maintaining enterprise solutions. I have played with sagemaker but it is so expensive I hate to leave it up for longer than a day. I downloaded and created a chat with your docs (entirely in airplane mode) here point being that I’ve hosted models both locally and in the cloud. But just ended up sticking to API calls as it’s so cheap
-
You can now chat with your documents privately!
I posted the speed of mine in the readme https://github.com/jlonge4/local_llama
-
Textgen webui for gpt_chatwithPDF
I would like to use this tool https://github.com/jlonge4/gpt_chatwithPDF/blob/main/gpt_chat_api.py but unfortunately the local version (https://github.com/jlonge4/local_llama) is bound to the CPU and thus quiet slow. Is there any way i could get textgenwebui working with the above stated tool?
-
Is there a way to ask questions about ç multiple PDF files?
This is what you want https://github.com/jlonge4/local_llama it’s fully offline with no third parties, but the setup is a bit involved
-
Newbie here. Need help with choosing a llm model for pdf ingestion and summarization locally
Or try this https://github.com/jlonge4/local_llama
- Local GPT (completely offline and no OpenAI!)
- Local GPT (completely offline and no OpenAI!) [P]
-
Offline llama
Code here if interested
zep
- Zep: Fast, scalable building blocks for production LLM apps
-
ICYMI August: Zep Vector DB, User Store, LangChain collabs & more!
I've read that many of you have started to look beyond LangChain for more advanced functionality and enhanced performance. Zep recently integrated with LlamaIndex and improved our Python and TypeScript SDKs to make it easier and faster to build apps without utilizing frameworks.
- Show HN: Zep – pgvector-based memory store for LLM apps
- Zep: A fast, async memory store for LLM applications
-
Handling chat histories that are longer than the context length?
Ultimately, a comprehensive solution will need to pull out only the relevant pieces of chat (using vector proximity search) and ensure that whatever is used ultimately fits into the prompt. The zep project looks promising. It's Apache 2 and it appears that the primary contributor has been working over the last several months on how to tackle this issue.
-
Zep Memory Store - New Features: JWT Authentication, Azure OpenAI APIs, & Configurable Hard Deletion
Great! Let me know if you have any difficulty doing so. Also, you can find our docs here: https://docs.getzep.com/
-
Discussion: Biggest Roadblocks to Deploy LLMs to Production
Thanks for sharing. Can you confirm that you're looking at Zep's documentation? https://docs.getzep.com/
- getzep/zep: Zep: A long-term memory store for LLM / Chatbot applications
- Zep: A long-term memory store for LLM apps, written in Go
- Has anyone had any success with making a Chain for a chatbot that stores conversations into Pinecone?
What are some alternatives?
h2ogpt - Private chat with local GPT with document, images, video, etc. 100% private, Apache 2.0. Supports oLLaMa, Mixtral, llama.cpp, and more. Demo: https://gpt.h2o.ai/ https://codellama.h2o.ai/
langchaingo - LangChain for Go, the easiest way to write LLM-based programs in Go
private-gpt - Interact with your documents using the power of GPT, 100% privately, no data leaks
zep-js - Zep - Long-Term Memory for AI Assistants (TypeScript Client)
EmbedAI - An app to interact privately with your documents using the power of GPT, 100% privately, no data leaks
getlang - Natural language detection package in pure Go
chatdocs - Chat with your documents offline using AI.
verbaflow - Neural Language Model for Go
LocalAI - :robot: The free, Open Source OpenAI alternative. Self-hosted, community-driven and local-first. Drop-in replacement for OpenAI running on consumer-grade hardware. No GPU required. Runs gguf, transformers, diffusers and many more models architectures. It allows to generate Text, Audio, Video, Images. Also with voice cloning capabilities.
zep-python - Zep: Long-Term Memory for AI Assistants (Python Client)
mychatGPT - GPT chat with your docs!
lingo - package lingo provides the data structures and algorithms required for natural language processing