privateGPT
langflow
privateGPT | langflow | |
---|---|---|
1 | 28 | |
50,198 | 17,467 | |
- | 12.6% | |
- | 10.0 | |
about 1 month ago | 2 days ago | |
Python | JavaScript | |
Apache License 2.0 | 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.
privateGPT
-
PrivateGPT exploring the Documentation
# install developer tools xcode-select --install # create python sandbox mkdir PrivateGTP cd privateGTP/ python3 -m venv . # actiavte local context source bin/activate # privateGTP uses poetry for python module management privateGTP> pip install poetry # sync privateGTP project privateGTP> git clone https://github.com/imartinez/privateGPT # enable MPS for model loading and processing privateGTP> CMAKE_ARGS="-DLLAMA_METAL=on" pip install --force-reinstall --no-cache-dir llama-cpp-python privateGTP> cd privateGPT # Import configure python dependencies privateGTP> poetry run python3 scripts/setup # launch web interface to confirm operational on default model privateGTP> python3 -m private_gpt # navigate safari browser to http://localhost:8001/ # To bulk import documentation needed to stop the web interface as vector database not in multi-user mode privateGTP> [control] + "C" # import some PDFs privateGTP> curl "https://docs.intersystems.com/irislatest/csp/docbook/pdfs.zip" -o /tmp/pdfs.zip privateGTP> unzip /tmp/pdfs.zip -d /tmp # took a few hours to process privateGTP> make ingest /tmp/pdfs/pdfs/ # launch web interface again for query documentation privateGTP> python3 -m private_gpt
langflow
-
News DataStax just bought our startup Langflow
Hey folks I'm the Head of DevRel @ DataStax here and just wanted to share to the HN community that in conjunction with this big acquisition news, the LF team has shipped 1.0-alpha of Langflow.
It's a simple `pip install` and the team would love any and all feedback!
https://github.com/logspace-ai/langflow/
-
Node-based AutoGen with local LLMs inside ComfyUI
You can also check langflow, a node UI for langchain https://github.com/logspace-ai/langflow
- Show HN: Rivet – open-source AI Agent dev env with real-world applications
-
Using Retrieval Augmented Generation to Clear Our GitHub Backlog
There's a few tools out there like AgentGPT (https://github.com/reworkd/AgentGPT, although it's a more conversational interface), and (https://github.com/logspace-ai/langflow) and others. I think most developers definitely prefer a code-first interface though like a library but haven't found one that's great yet. We've used them in the past but didn't have the best experience so would love to hear if anyone has worked with a library they found really flexible.
- Show HN: ChainForge, a visual tool for prompt engineering and LLM evaluation
-
Anyone know how to get LangFlow working with oobabooga?
I found this thread talking about it here: https://github.com/logspace-ai/langflow/issues/263
-
Found a fun little open source project called Flowise. It's a drag & drop UI to build your customized LLM flow using LangchainJS
also check https://github.com/logspace-ai/langflow
-
What exactly is AutoGPT?
AutoGPT is basically a demo of what you can do with Langchain. If you want to play with Langchain in a drag and drop blueprint environment I suggest Langflow
-
Launch HN: Fastgen (YC W23) – Visual Low-Code Back End Builder
Hi, I like this! I'm curious what drove the decision to use the vertical block builder style you chose. I'm partial to node-based editors and have been building things with React Flow recently. LangFlow [1] is a good example, but there's lots of UIs that use a similar interface (e.g. Blender [2] and Unity [3]).
[1] https://github.com/logspace-ai/langflow
[2] https://docs.blender.org/manual/en/3.5/interface/controls/no...
[3] https://unity.com/features/unity-visual-scripting
-
Having fun testing CanvasGPT - a new project launching soon
Here's an open source version that's very similar LangFlow
What are some alternatives?
localGPT - Chat with your documents on your local device using GPT models. No data leaves your device and 100% private.
Flowise - Drag & drop UI to build your customized LLM flow
anything-llm - The all-in-one Desktop & Docker AI application with full RAG and AI Agent capabilities.
langchain-visualizer - Visualization and debugging tool for LangChain workflows
gpt4all - gpt4all: run open-source LLMs anywhere
private-gpt - Interact with your documents using the power of GPT, 100% privately, no data leaks
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/
Local-LLM-Comparison-Colab-UI - Compare the performance of different LLM that can be deployed locally on consumer hardware. Run yourself with Colab WebUI.
ollama - Get up and running with Llama 3, Mistral, Gemma, and other large language models.
GPTQ-for-LLaMa - 4 bits quantization of LLaMa using GPTQ
langchain - 🦜🔗 Build context-aware reasoning applications
serge - A web interface for chatting with Alpaca through llama.cpp. Fully dockerized, with an easy to use API.