Special shout out to Cohere’s
@itsSandraKublik
for being an amazing host to kickoff the event today! And a special thank you to @langchain & @weaviate_io for their participation in this unique event.
@cohere
-
Cohere Hosts Major AI Event with LangChain and Weaviate
By
–
-
Enterprise AI Hackathon: 25 Teams Build Solutions with Cohere
By
–
And we’re off! The Enterprise AI Hackathon hosted by Cohere and @NYSE has officially started. 25 teams have 2 weeks to build innovative solutions! Looking forward to seeing what the participants do with Command and Embed leveraging our chat API and RAG capabilities!
-
Cohere NYSE Hackathon Launches with AI Industry Partners
By
–
Tomorrow marks the beginning of the Cohere x @NYSE hackathon. Thanks to the NYSE for collaborating with us and with our AI partners at @weaviate_io
, @langchain
, and @lablabai for their contributions to the event. We can't wait to see the innovative projects that will come out! -
Oracle Cloud Integrates Generative AI Models for Enterprise
By
–
See the latest in our partnership with @OracleCloud
, supporting the Oracle Cloud Infrastructure Generative AI service. This service seamlessly integrates our models with OCI to help enterprises take advantage of cutting-edge advancements in AI. Learn more: -
Improving Language Model Plasticity via Active Forgetting
By
–
Applying language models to a new language can be difficult. This is a barrier to making their capabilities universally accessible.
— Cohere (@cohere) 22 janvier 2024
Here’s Kelly Marchisio @cheeesio explaining “Improving Language Plasticity via Pretraining with Active Forgetting” at #NeurIPS2023. The method… pic.twitter.com/9tfS3lLpPbApplying language models to a new language can be difficult. This is a barrier to making their capabilities universally accessible. Here’s Kelly Marchisio @cheeesio explaining “Improving Language Plasticity via Pretraining with Active Forgetting” at #NeurIPS2023. The method
-
Fine-tuning Chat Models with Cohere Python SDK
By
–
Learn about fine-tuning a model for Chat to improve its performance at a specific task. This article includes practical code examples using Cohere's Python SDK. Learn more about it now.
-
Pinecone Serverless Vector Database Launches with Cohere
By
–
Congrats to @pinecone for launching their new Serverless vector database! With Pinecone serverless and Cohere Embed, it’s easier to scale RAG and semantic search systems. Check out our blog on how they come together to reduce the need to manage clusters, optimize batches,
-
Patrick Lewis RAG Research Augments Language Models Retrieval
By
–
Research on RAG over corpora of documents by Patrick Lewis has profoundly impacted the NLP field. At Cohere, Patrick leads the modeling team effort to augment language models with access to retrieval systems and tools.
— Cohere (@cohere) 14 janvier 2024
Learn more on Chat with RAG: https://t.co/OR1VCAcnX8 pic.twitter.com/SCyxbccI9oResearch on RAG over corpora of documents by Patrick Lewis has profoundly impacted the NLP field. At Cohere, Patrick leads the modeling team effort to augment language models with access to retrieval systems and tools. Learn more on Chat with RAG: https://
txt.cohere.com/chat-with-rag/ -
Reranking Optimization: Improving Search Relevance with NLP
By
–
Using reranking in a search system pipeline changes the order of results to optimize their relevance and greatly increase search performance. Watch NLP Expert @JayAlammar explain how reranking works.
— Cohere (@cohere) 13 janvier 2024
Learn more about Cohere's Rerank: https://t.co/ANpUYmpx5z. pic.twitter.com/2MtISMfyqZUsing reranking in a search system pipeline changes the order of results to optimize their relevance and greatly increase search performance. Watch NLP Expert @JayAlammar explain how reranking works. Learn more about Cohere's Rerank: https://
txt.cohere.com/rerank/. -
RAG Technology Explained: Retrieval-Augmented Generation with Coral
By
–
Retrieval-augmented generation supports a language model with access to external tools and source data like search engines or documentation.
— Cohere (@cohere) 11 janvier 2024
Watch NLP expert @itsSandraKublik explain RAG and how it works with Coral, our conversational AI demo. Try it at https://t.co/GhYd5BwAOU. pic.twitter.com/ERzhgBTRwRRetrieval-augmented generation supports a language model with access to external tools and source data like search engines or documentation. Watch NLP expert @itsSandraKublik explain RAG and how it works with Coral, our conversational AI demo. Try it at http://
cohere.com/coral.