And others! Updates to @CohereAI wrappers There were a few updates/fixes to the Cohere wrappers from @ephe_meral and @bair82 Fix to conversational agent
Docs update @zurawiki Expose memory key name in entity memory class
CODE
-
Cohere AI Wrappers Updates and Conversational Agent Fixes
By
–
-
VectorDB QA Chain Now Supports Max Marginal Relevance Search
By
–
Allowing different types of search in the vector DB chain Previously, the VectorDB QA chain only used similarity search to fetch documents You can now configure this to use `mmr`: max marginal relevance https://
github.com/hwchase17/lang
chain/blob/b9045f7e0df357d608700e91dc3039433f652d61/langchain/chains/vector_db_qa/base.py#L44
… -
TensorFlow Hub Embeddings Support Added to LangChain
By
–
TensorflowHub embeddings There's now support for another embedding type – Tensorflow Hub embeddings! Ryohei Kuroki Docs: https://
langchain.readthedocs.io/en/latest/modu
les/utils/combine_docs_examples/embeddings.html#tensorflowhub
… -
Enhanced Agent Initialization with Advanced Parameters
By
–
More complete initialization of agents Thanks to @jxnlco you can now more completely initialize agents by specifying `agent_kwargs` This allows for passing of more complex parameters to the agent class https://
github.com/hwchase17/lang
chain/blob/b9045f7e0df357d608700e91dc3039433f652d61/langchain/agents/initialize.py#L17
… -
LangChain v0.0.75 Release: Agents, Embeddings, SQL Steps
By
–
Another big release! v0.0.75 Pin LangChainHub version (
@roywilliamsiii
)
TensorflowHub embeddings (Ryohei Kuroki)
Returning intermediate SQL steps
Better initialization of agents (
@jxnlco
)
Using MMR search in the vector DB QA chain And more! -
LangChainHub Now Supports Git Commit Version Pinning
By
–
Pin LangChainHub version Thanks to @roywilliamsiii you can now load artifacts from LangChainHub from a specific git commit, effectively pinning the version Docs: https://
langchain.readthedocs.io/en/latest/modu
les/agents/examples/load_from_hub.html#pinning-dependencies
… Check out the Hub here: -
GPT-3 Combined with No-Code Tools for AI Development
By
–
This looks great Prashant GPT-3 + Nocode =
-
Training a Pothole Detector Using YOLOv8 on Custom Dataset
By
–
🚀Blog-tastic Tuesdays
— Satya Mallick (@LearnOpenCV) 31 janvier 2023
Potholes have become a menace for drivers in cities and towns alike! So today, We are training a pothole detector. We use the state-of-the-art model YOLOv8!https://t.co/l9JUDdcJkD#yolov8 #dataset #objectdetection #customdataset #computervision #ai pic.twitter.com/6LKQkLSPCGBlog-tastic Tuesdays
Potholes have become a menace for drivers in cities and towns alike! So today, We are training a pothole detector. We use the state-of-the-art model YOLOv8! https://
learnopencv.com/train-yolov8-o
n-custom-dataset/
… #yolov8 #dataset #objectdetection #customdataset #computervision #ai -
BLIP-2: Powerful Multimodal AI Tool for Vision Tasks
By
–
Creedme que esta es una de esas herramientas que llegan sin hacer demasiado ruido (como Whisper) y luego resultan ser muy útiles para construir muchas cosas interesantes. Podéis utilizar BLIP-2 a través de la librería LAVIS de Salesforce. Ya estoy arrancándolo en Google Colab.
-
Complete Comparison of Code Assistants: Copilot, Tabnine, Ghostwriter, Codeium
By
–
Love this comprehensive comparison from @_anshulr on Copilot vs Tabnine vs Ghostwriter vs @codeiumdev https://codeium.com/blog/code-assistant-comparison-copilot-tabnine-ghostwriter-codeium 3 axes of comparison: Features/Price, Latency, Quality.