Almost – there's no Ajax, it's baked into the rendering of the page, but it pulls from a SQLite table pre-populated with top-ten by similarity scores It's explained in detail here
SOFTWARE
-
Running Small Language Models Locally for RAG and Tool Use
By
–
I'm really excited about the growing potential to run small models on my own laptop (like Llama 3 8B or Phi-3) that don't "know" much but are capable of tool usage and summarization – then I can use them for things like local RAG as well
-
Tracking upstream changes in open source library forks
By
–
I use a similar trick for my asgi-gzip library, which I extracted from Starlette but need to keep track on changes they make to their implementation https://
simonwillison.net/2022/Apr/28/is
sue-on-changes/
… -
LLM Updates: Llama 3, Cohere, VoyageAI Embeddings Released
By
–
6/ Enhancement More improvements on other nodes from the community! – UnstructuredIO update
– Llama 3, Cohere on AWS Bedrock
– VoyageAI Embedding
– Custom Dimension OpenAI Embedding
– Confluence PAT support
– many more.. Check out our release page – -
Flowise Native Buffer Memory Support with Session ID
By
–
3/ Buffer Memory SessionId If you don't want additional dependency of using external database to store/retrieve messages.. We now have native support for buffer memory nodes! Messages will be stored/retrieved from Flowise database with session ID. https://
docs.flowiseai.com/integrations/l
angchain/memory#separate-conversations-for-multiple-users
… -
Flowise Migrates File Storage to Blob Storage and S3
By
–
4/Storage Files that are uploaded on Flowise used to store as base64 string on a local file path. This caused limitation and huge burden on database. We've migrated the logic to support blob storage. You can specify a folder path or use S3:
-
Flowise Enables Dynamic Model Selection via JSON Configuration
By
–
2/ Models {JSON} You can now specify the model you want to use in a JSON file. Previously users have to wait till next release to use latest model. Now, it's automatically fetched from a specified path: https://
raw.githubusercontent.com/FlowiseAI/Flow
ise/main/packages/components/models.json
… Learn more at -
Using AI Embeddings to Document CLI Tools
By
–
The "Related" feature on my TILs (powered by OpenAI embeddings) pulled up this one from 2021 – apparently I'm in the habit of using TILs to write documentation for under-documented CLI tools
-
Running Whisper-cpp on macOS via Homebrew and Hugging Face
By
–
Thanks to @slhck I also now have a recipe for running CLI whisper-cpp on macOS via Homebrew and a model file downloaded from Hugging Face – detailed notes on that here (including converting mp3 to wav using ffmpeg):
-
LangChain Upstage Integration: Layout Analysis and LLM Chat
By
–
Super excited to have the @langchain @upstageai integration package including Layout Analysis, Text Embedding, #solarllm Chat, and Groundedness Check! Simply get your key at https://
console.upstage.ai, and LangChain will take care of the rest. Enjoy langchain_upstage!