i just purged a ton of jank bridgy fed standard.site documents from the vectorstore for pub-search.waow.tech so now the semantic search results are a lot better, which, notably will improve results for anyone using the pub-search MCP -> protopack
pub-search.waow.tech?q=home+cooke...
pub-search.waow.tech?q=home+cooke...
"home cooked meals" - pub search
search results for "home cooked meals"
pub-search.waow.tech
March 1, 2026 at 11:29 PM
i just purged a ton of jank bridgy fed standard.site documents from the vectorstore for pub-search.waow.tech so now the semantic search results are a lot better, which, notably will improve results for anyone using the pub-search MCP -> protopack
pub-search.waow.tech?q=home+cooke...
pub-search.waow.tech?q=home+cooke...
Layer's query API takes nearest_to_id instead of a raw vector: pass stored document ids and rank by their own vectors. The gateway resolves each id from the document cache first, falling back to the namespace's VectorStore on a miss. https://hevlayer.com/docs/api/query
September 23, 2026 at 6:18 PM
Layer's query API takes nearest_to_id instead of a raw vector: pass stored document ids and rank by their own vectors. The gateway resolves each id from the document cache first, falling back to the namespace's VectorStore on a miss. https://hevlayer.com/docs/api/query
It's superb to see the @jetbrains.com Koog 0.8 release adding Spring AI support: github.com/JetBrains/ko....
Release 0.8.0 · JetBrains/koog
0.8.0
Published 10 April 2026
Major Features
Spring AI Integration: Added comprehensive Spring AI support with ChatMemoryRepository and VectorStore integration for seamless persistence and retri...
github.com
April 11, 2026 at 8:02 AM
It's superb to see the @jetbrains.com Koog 0.8 release adding Spring AI support: github.com/JetBrains/ko....
What happens if your vector store data becomes outdated and needs an update? Follow Mario Haarmann as he builds an n8n workflow to do just that!
https://buff.ly/4eRQBUN
#n8n #ai #vectorstore #supabase
https://buff.ly/4eRQBUN
#n8n #ai #vectorstore #supabase
December 2, 2024 at 9:00 PM
What happens if your vector store data becomes outdated and needs an update? Follow Mario Haarmann as he builds an n8n workflow to do just that!
https://buff.ly/4eRQBUN
#n8n #ai #vectorstore #supabase
https://buff.ly/4eRQBUN
#n8n #ai #vectorstore #supabase
however, back in the day we had vectorstore support in marvin and though we later slimmed it down to just structured outputs, i've been maintaining / using the vectorstore / document ingestion utils here for a while now
github.com/zzstoatzz/ra...
github.com/zzstoatzz/ra...
January 9, 2025 at 12:19 PM
however, back in the day we had vectorstore support in marvin and though we later slimmed it down to just structured outputs, i've been maintaining / using the vectorstore / document ingestion utils here for a while now
github.com/zzstoatzz/ra...
github.com/zzstoatzz/ra...
Fast #VectorStore, #VectorSearch, #Clustering saved #NumPy arrays into files.
For #MultiVector and #LateInteraction
#OpenSource MIT lic
#RAG #SemanticSearch #AI #Embeddings
github.com/TusKANNy/tac...
For #MultiVector and #LateInteraction
#OpenSource MIT lic
#RAG #SemanticSearch #AI #Embeddings
github.com/TusKANNy/tac...
GitHub - TusKANNy/tachiom: Official repository of TACHIOM.
Official repository of TACHIOM. Contribute to TusKANNy/tachiom development by creating an account on GitHub.
github.com
June 17, 2026 at 12:43 PM
Fast #VectorStore, #VectorSearch, #Clustering saved #NumPy arrays into files.
For #MultiVector and #LateInteraction
#OpenSource MIT lic
#RAG #SemanticSearch #AI #Embeddings
github.com/TusKANNy/tac...
For #MultiVector and #LateInteraction
#OpenSource MIT lic
#RAG #SemanticSearch #AI #Embeddings
github.com/TusKANNy/tac...
Semantic caching can use any vector store. If you’re already using a vector store such as Qdrant, you can use it to speed up semantically similar requests and reduce token usage without adding another database to your stack.
#SpringAI #Java #SemanticCaching #VectorStore
medium.com/@thetalkinga...
#SpringAI #Java #SemanticCaching #VectorStore
medium.com/@thetalkinga...
June 8, 2026 at 4:04 PM
Semantic caching can use any vector store. If you’re already using a vector store such as Qdrant, you can use it to speed up semantically similar requests and reduce token usage without adding another database to your stack.
#SpringAI #Java #SemanticCaching #VectorStore
medium.com/@thetalkinga...
#SpringAI #Java #SemanticCaching #VectorStore
medium.com/@thetalkinga...
Upgrade alert! 🚀 #KNIME 5.4 is here: enhanced #UI, #KAI on canvas, expanded #LLM connectivity ( #GPT4All, #Databricks), stronger #GenAI governance, simplified #VectorStore management, easier #Box and #Tableau file access, and more!
📌 #READ → medium.com/low-code-for...
📌 #READ → medium.com/low-code-for...
What’s New in KNIME Analytics Platform 5.4
KNIME Analytics Platform 5.4 is now available to download
medium.com
January 22, 2025 at 9:28 AM
Upgrade alert! 🚀 #KNIME 5.4 is here: enhanced #UI, #KAI on canvas, expanded #LLM connectivity ( #GPT4All, #Databricks), stronger #GenAI governance, simplified #VectorStore management, easier #Box and #Tableau file access, and more!
📌 #READ → medium.com/low-code-for...
📌 #READ → medium.com/low-code-for...
Reminder: We're joining Qdrant for an exciting webinar on deploying AI agents using n8n’s low-code tools and Qdrant’s powerful vector database. Your hosts are Max Tkacz from n8n and Jenny Sukhodolskaya from Qdrant.
Save your spot: https://buff.ly/49lrOal
#llm #vectorstore #ai #lowcode
Save your spot: https://buff.ly/49lrOal
#llm #vectorstore #ai #lowcode
December 4, 2024 at 4:00 PM
Reminder: We're joining Qdrant for an exciting webinar on deploying AI agents using n8n’s low-code tools and Qdrant’s powerful vector database. Your hosts are Max Tkacz from n8n and Jenny Sukhodolskaya from Qdrant.
Save your spot: https://buff.ly/49lrOal
#llm #vectorstore #ai #lowcode
Save your spot: https://buff.ly/49lrOal
#llm #vectorstore #ai #lowcode
WeKnora v0.4.0 💣
Semantic search beyond text. VectorStore CRUD API gives full control, Notion connector indexes your workspace, WeChat reaches users at scale. Production #RAG in #golang ready now.
→ releaseport.com/t/GN
Semantic search beyond text. VectorStore CRUD API gives full control, Notion connector indexes your workspace, WeChat reaches users at scale. Production #RAG in #golang ready now.
→ releaseport.com/t/GN
WeKnora v0.4.0
VectorStore infrastructure
releaseport.com
April 17, 2026 at 4:20 AM
Pinecone is great, although I have moved to a vectorstore which can be saved locally so I use faiss now.
November 27, 2024 at 7:16 AM
Pinecone is great, although I have moved to a vectorstore which can be saved locally so I use faiss now.
oh ok i think i interpreted the question more broadly (using LLMs in general) but as far as controlflow I think the only vectorstore support is an implementation detail of memory so I suspect that section might be old / LLM hallucinated 🙂
but @jlowin.dev might correct me
but @jlowin.dev might correct me
January 9, 2025 at 12:19 PM
oh ok i think i interpreted the question more broadly (using LLMs in general) but as far as controlflow I think the only vectorstore support is an implementation detail of memory so I suspect that section might be old / LLM hallucinated 🙂
but @jlowin.dev might correct me
but @jlowin.dev might correct me
🧠 Singlebase.cloud #Vectorstore: Multi-model #VectorEmbeddings from #OpenAI, #VertexAI & more! Unleash #AI potential with seamless integration. Build smarter apps faster! 🚀 #AI #Backend #WebDev #Innovation #Developers
September 19, 2025 at 2:45 PM
🧠 Singlebase.cloud #Vectorstore: Multi-model #VectorEmbeddings from #OpenAI, #VertexAI & more! Unleash #AI potential with seamless integration. Build smarter apps faster! 🚀 #AI #Backend #WebDev #Innovation #Developers
GPT long term memory RAG with embeddings and SQLite as Vectorstore
youtu.be/N1pbjFoePcs
youtu.be/N1pbjFoePcs
GPT long term memory RAG with embeddings and SQLite as Vectorstore
In this video we will learn about how we can implement theoretically infinite memory(long term memory) using sqlite implemented vector store retrievalCode fi...
youtu.be
February 17, 2024 at 7:48 AM
GPT long term memory RAG with embeddings and SQLite as Vectorstore
youtu.be/N1pbjFoePcs
youtu.be/N1pbjFoePcs
🧠 @tur.so: Embedded (𝐈𝐧-𝐏𝐫𝐨𝐜𝐞𝐬𝐬) #SQL + #VectorStore for #AI Apps
⚡ 575× faster than #SQLite, native similarity search, multithreading, JS/Rust/Go/Py
👉 Discuss in Discord: linktr.ee/qdrddr
#VectorDB #LLM #RAG #Turso
⚡ 575× faster than #SQLite, native similarity search, multithreading, JS/Rust/Go/Py
👉 Discuss in Discord: linktr.ee/qdrddr
#VectorDB #LLM #RAG #Turso
GitHub - tursodatabase/turso: Turso Database is a project to build the next evolution of SQLite.
Turso Database is a project to build the next evolution of SQLite. - tursodatabase/turso
github.com
July 30, 2025 at 1:32 PM
🧠 @tur.so: Embedded (𝐈𝐧-𝐏𝐫𝐨𝐜𝐞𝐬𝐬) #SQL + #VectorStore for #AI Apps
⚡ 575× faster than #SQLite, native similarity search, multithreading, JS/Rust/Go/Py
👉 Discuss in Discord: linktr.ee/qdrddr
#VectorDB #LLM #RAG #Turso
⚡ 575× faster than #SQLite, native similarity search, multithreading, JS/Rust/Go/Py
👉 Discuss in Discord: linktr.ee/qdrddr
#VectorDB #LLM #RAG #Turso
📊 RaBitQ by #LanceDB cuts storage up to 32× with only ~5% recall loss — boosting speed & efficiency for #AI workloads.
🔗 Link in first 💬⤵️
Repost 🔁 #RAG #VectorDB #VectorStore #SemanticSearch
🔗 Link in first 💬⤵️
Repost 🔁 #RAG #VectorDB #VectorStore #SemanticSearch
October 16, 2025 at 8:57 PM
📊 RaBitQ by #LanceDB cuts storage up to 32× with only ~5% recall loss — boosting speed & efficiency for #AI workloads.
🔗 Link in first 💬⤵️
Repost 🔁 #RAG #VectorDB #VectorStore #SemanticSearch
🔗 Link in first 💬⤵️
Repost 🔁 #RAG #VectorDB #VectorStore #SemanticSearch
🧠 Singlebase.cloud #Vectorstore: Multi-model #VectorEmbeddings from #OpenAI, #VertexAI & more! Unleash #AI potential with seamless integration. Build smarter apps faster! 🚀 #Backend #WebDev #Innovation #Developers
March 10, 2025 at 4:32 PM
🧠 Singlebase.cloud #Vectorstore: Multi-model #VectorEmbeddings from #OpenAI, #VertexAI & more! Unleash #AI potential with seamless integration. Build smarter apps faster! 🚀 #Backend #WebDev #Innovation #Developers
🧠 Boost your app with lightning-fast, AI-powered semantic search!
Singlebase.cloud: Vectorstore finds contextually relevant matches using vector embeddings—perfect for recommendations & insights! 🚀
#AI #VectorDB #Singlebasecloud #Dev #Developer
Singlebase.cloud: Vectorstore finds contextually relevant matches using vector embeddings—perfect for recommendations & insights! 🚀
#AI #VectorDB #Singlebasecloud #Dev #Developer
July 24, 2025 at 1:28 PM
🧠 Boost your app with lightning-fast, AI-powered semantic search!
Singlebase.cloud: Vectorstore finds contextually relevant matches using vector embeddings—perfect for recommendations & insights! 🚀
#AI #VectorDB #Singlebasecloud #Dev #Developer
Singlebase.cloud: Vectorstore finds contextually relevant matches using vector embeddings—perfect for recommendations & insights! 🚀
#AI #VectorDB #Singlebasecloud #Dev #Developer
The architecture:
- HandleLoader fetches posts via ATProto API
- Each post becomes a Document with formatted text + metadata
- Documents get indexed in TurboPuffer vectorstore
- Semantic search finds relevant posts
Now you can query your entire post history!
- HandleLoader fetches posts via ATProto API
- Each post becomes a Document with formatted text + metadata
- Documents get indexed in TurboPuffer vectorstore
- Semantic search finds relevant posts
Now you can query your entire post history!
August 31, 2025 at 6:21 PM
The architecture:
- HandleLoader fetches posts via ATProto API
- Each post becomes a Document with formatted text + metadata
- Documents get indexed in TurboPuffer vectorstore
- Semantic search finds relevant posts
Now you can query your entire post history!
- HandleLoader fetches posts via ATProto API
- Each post becomes a Document with formatted text + metadata
- Documents get indexed in TurboPuffer vectorstore
- Semantic search finds relevant posts
Now you can query your entire post history!
🔍 Power up your AI with Singlebase.cloud #Vectorstore! Combine vector search with generation models for super-accurate, ultra-relevant content creation. Perfect for #RAG (Retrieval-Augmented Generation) workflows. #AI #Backend #WebDev #Innovation
March 5, 2025 at 6:20 PM
🔍 Power up your AI with Singlebase.cloud #Vectorstore! Combine vector search with generation models for super-accurate, ultra-relevant content creation. Perfect for #RAG (Retrieval-Augmented Generation) workflows. #AI #Backend #WebDev #Innovation
1/2
Vectorstore cost optimization: retention and tiering strategies:
- Keep ephemeral embeddings for short-lived sessions and purge regularly.
- Tier long-term vectors to cheaper storage with periodic reheating.
- Use sampling and deduplication to limit index growth.
Vectorstore cost optimization: retention and tiering strategies:
- Keep ephemeral embeddings for short-lived sessions and purge regularly.
- Tier long-term vectors to cheaper storage with periodic reheating.
- Use sampling and deduplication to limit index growth.
January 30, 2026 at 4:00 AM
1/2
Vectorstore cost optimization: retention and tiering strategies:
- Keep ephemeral embeddings for short-lived sessions and purge regularly.
- Tier long-term vectors to cheaper storage with periodic reheating.
- Use sampling and deduplication to limit index growth.
Vectorstore cost optimization: retention and tiering strategies:
- Keep ephemeral embeddings for short-lived sessions and purge regularly.
- Tier long-term vectors to cheaper storage with periodic reheating.
- Use sampling and deduplication to limit index growth.
⚡️ Unlock lightning-fast semantic search with Singlebase #Vectorstore. Encode content into vectors to surface contextually relevant results, and deep insights. Built for scale and real-time discovery so your apps feel smarter instantly. Explore → Singlebase.Cloud 🚀 #AI #Backend #WebDev #Developers
October 12, 2025 at 11:02 AM
⚡️ Unlock lightning-fast semantic search with Singlebase #Vectorstore. Encode content into vectors to surface contextually relevant results, and deep insights. Built for scale and real-time discovery so your apps feel smarter instantly. Explore → Singlebase.Cloud 🚀 #AI #Backend #WebDev #Developers
Some nice aspects are:
- flexible choice of VectorStore
- own model routing
- multi-language support using multiple stores
- flexible authentication options
- SSL cert supported
- backend can be swapped, if needed.
- SpeechRecognition
Plus, I wrote a customer-branded WebUI
- flexible choice of VectorStore
- own model routing
- multi-language support using multiple stores
- flexible authentication options
- SSL cert supported
- backend can be swapped, if needed.
- SpeechRecognition
Plus, I wrote a customer-branded WebUI
November 3, 2025 at 7:11 PM
Some nice aspects are:
- flexible choice of VectorStore
- own model routing
- multi-language support using multiple stores
- flexible authentication options
- SSL cert supported
- backend can be swapped, if needed.
- SpeechRecognition
Plus, I wrote a customer-branded WebUI
- flexible choice of VectorStore
- own model routing
- multi-language support using multiple stores
- flexible authentication options
- SSL cert supported
- backend can be swapped, if needed.
- SpeechRecognition
Plus, I wrote a customer-branded WebUI
🔍 Power up your AI with Singlebase.cloud #Vectorstore! Combine vector search with generation models for super-accurate, ultra-relevant content creation. Perfect for #RAG (Retrieval-Augmented Generation) workflows. #AI #Backend #WebDev #Innovation
December 30, 2024 at 7:08 PM
🔍 Power up your AI with Singlebase.cloud #Vectorstore! Combine vector search with generation models for super-accurate, ultra-relevant content creation. Perfect for #RAG (Retrieval-Augmented Generation) workflows. #AI #Backend #WebDev #Innovation
Microsoft offers guide to pirating Harry Potter series for LLM training | Discussion
LangChain Integration for Vector Support for SQL-based AI applications - Azure SQL Devs’ Corner
LangChain Integration for Vector Support for Azure SQL and SQL database in Microsoft Fabric Microsoft SQL now supports native vector search capabilities in Azure SQL and SQL database in Microsoft Fabric. We also released the langchain-sqlserver package, enabling the management of SQL Server as a Vectorstore in LangChain. In this step-by-step tutorial, we will show […]
devblogs.microsoft.com
February 19, 2026 at 12:00 AM
Microsoft offers guide to pirating Harry Potter series for LLM training | Discussion