#vectorstore — Public Fediverse posts

OCI Enterprise AI で作る RAG アプリ入門 〜 Object Storage / Vector Store / file search を試してみてみた
https://qiita.com/shirok/items/42817c3ca57404911d2b?utm_campaign=popular_items&utm_medium=feed&utm_source=popular_items

#qiita #oracle #AI #oraclecloud #rag #VectorStore

New research shows semantic caching can cut LLM inference costs by up to 73%—even when cache hits are misleading. The AdaptiveSemanticCache uses a QueryClassifier and similarity thresholds to decide when to reuse embeddings from a vector_store, dramatically reducing token usage. Curious how this works and how you can apply it to your own models? Read the full breakdown. #SemanticCaching #LLM #VectorStore #EmbeddingModel

🔗 https://aidailypost.com/news/semantic-caching-can-slash-llm-costs-by-73-despite-misleading-cache

New research shows semantic caching can cut LLM inference costs by up to 73%—even when cache hits are misleading. The AdaptiveSemanticCache uses a QueryClassifier and similarity thresholds to decide when to reuse embeddings from a vector_store, dramatically reducing token usage. Curious how this works and how you can apply it to your own models? Read the full breakdown. #SemanticCaching #LLM #VectorStore #EmbeddingModel

🔗 https://aidailypost.com/news/semantic-caching-can-slash-llm-costs-by-73-despite-misleading-cache

Discover how a vector store can act as a model's local memory in our new LLMOps guide. Learn to set up FAISS with LangChain, generate embeddings in Python, and boost your OpenAI workflows. Turn your LLM into a smarter, self‑retrieving system—read the full walkthrough now! #LLMOps #VectorStore #FAISS #LangChain

🔗 https://aidailypost.com/news/llmops-guide-shows-how-vector-store-becomes-models-local-memory

Thought of the day: Instead of chunking a document and generating an embedding for each of those chunks, store a single document with multiple embeddings (for each chunk + summary chunk(s)) and consider all these embeddings when trying to find relevant documents for a particular input... #llm #rag #vectorstore

Thought of the day: Instead of chunking a document and generating an embedding for each of those chunks, store a single document with multiple embeddings (for each chunk + summary chunk(s)) and consider all these embeddings when trying to find relevant documents for a particular input... #llm #rag #vectorstore

[LangChain編] 新リリース Oracle Database 23ai と Cohere で実装するエンタープライズRAG
https://qiita.com/ksonoda/items/d434aca84d6e6dacb3f1?utm_campaign=popular_items&utm_medium=feed&utm_source=popular_items

#qiita #oracle #GenerativeAI #langchain #LLM #VectorStore

新リリース Oracle Database 23ai と Cohere で実装するエンタープライズRAG
https://qiita.com/ksonoda/items/c300e734a5b1bef7b872?utm_campaign=popular_items&utm_medium=feed&utm_source=popular_items

#qiita #OpenAI #rag #LLM #VectorStore #Cohere

⬆️🧵 #AI #Learnathons🧵⬇️

3) 🗼 Berlin, December 14th at the @KNIME Berlin office with Armin Rudd

https://meetup.com/berlin-knime-users/events/296852930/

#lowcodenocode #datascience #machinelearning #vectorstore #knowledgebase #LLM #PromptEngineering #ChatBot #GenerativeAI #dataapps #KNIME

⬆️🧵 #AI #Learnathons🧵⬇️

2) 🏰 Nottingham, November 30th at Nottingham Trent Univeristy with Daphiny Pottmaier and Girinath G. Pillai

https://meetup.com/knime-user-group-uk/events/296716982/

#lowcodenocode #datascience #machinelearning #vectorstore #knowledgebase #LLM #PromptEngineering #ChatBot #GenerativeAI #dataapps

⬆️🧵 #AI #Learnathons🧵⬇️

1) ⚓ Hamburg, November 23rd at
@Kuehne_Nagel

with Alessandro Romano

https://meetup.com/hamburg-knime-meetup/events/296653789/

#lowcodenocode #datascience #machinelearning #vectorstore #knowledgebase #LLM #PromptEngineering #ChatBot #GenerativeAI #dataapps

📣 #KNIME #AI Learnathons are here!

https://knime.com/events?type=888

⬇️🧵⬇️

#lowcodenocode #visualprogramming #datascience #LargeLanguageModel #machinelearning #vectorstore #knowledgebase #LLM #PromptEngineering #ChatBot #GenerativeAI #dataapps

⬆️🧵 #KNIME #DataApp Examples 🧵⬇️

#ChatBot for asking specific questions on a just uploaded #PDF powered by #OpenAI and a #VectorStore

Read more on how to deploy a #CustomLLM into a #DataApp at: https://knime.com/blog/baking-ai-into-apps

#lowcodenocode #datascience #promptengineering #AI

Implemented the changes to bring my own data from #Pinecone #VectorStore to #Azure OpenAI #ChatGPT

https://github.com/microsoft/azurechatgpt/issues/43#issuecomment-1668382534

Implemented the changes to bring my own data from #Pinecone #VectorStore to #Azure OpenAI #ChatGPT

https://github.com/microsoft/azurechatgpt/issues/43#issuecomment-1668382534