qdrddr.bsky.social
@qdrddr.bsky.social
GLiNER-PII - Detect Personal Identifiers #PII / #PHI

Fine-tuned by #NVIDIA based on #Knowledgator #GLiNER model. Link in the first 💬 👇
Nvidia Open Model License

#AI #LLM #SLM #RAG
November 26, 2025 at 2:34 PM
Open #Guardrails Scanner 🛡️ Dynamic #AI safety checks, context-aware detection & multi-modal scanning. Manage custom scanners, proxy mode, text/regex tools.
🔗 Link in first 💬⤵️
📜 Modified Apache 2.0 lic
#LLM #RAG Repost 🔁
November 20, 2025 at 4:53 PM
Port of Context 🧩 Code Execution > MCP tool calls. Improves accuracy, reduces token use.
Executes #TypeScript in a Deno sandbox for accurate, efficient multi-step #LLM workflows
⚙️ Unified code mode replaces tool chaining
📜 MIT lic

🔗 Link in first 💬⤵️
#AI #RAG Repost 🔁
November 12, 2025 at 11:25 PM
HelixDB: Relational, #VectorDB + #GraphDB
Written in Rust for Ultra low latency
Build-in #MCP Server
AGPL 3.0 lic
github.com/HelixDB/heli...
GitHub - HelixDB/helix-db: HelixDB is an open-source graph-vector database built from scratch in Rust.
HelixDB is an open-source graph-vector database built from scratch in Rust. - HelixDB/helix-db
github.com
November 2, 2025 at 9:06 PM
Agentic #RAG debugging with ALTK 🛠️ Fix silent tool fails, hallucinated tool parameters, validate & handle large #JSON, auto-repair
🔗 Link in first 💬⤵️
📜 Apache 2.0 lic
#AI #LLM Repost 🔁
November 1, 2025 at 1:32 PM
#Skill.md Seeker 🤖 Automates converting docs, GitHub repos & PDFs into @anthropic.com #Claude AI Skills — in 20–40 mins!
🔗 Link in first 💬⤵️
📜 MIT Lic
#AI #LLM #Automation Repost 🔁
October 31, 2025 at 4:43 PM
#Microsoft #AI #Agent Lightning ⚡ Open-source RL framework for training & improving prompts. Works with LangChain, AutoGen & OpenAI SDK and others.
🔗 Link in first 💬⤵️
📜 MIT License
#LLM Repost 🔁
October 31, 2025 at 4:19 PM
Save 40% tokens when sending #JSON with TOON to #LLMs that is typically better accuracy vs. raw JSON (depends on the model)
GitHub Repo link in the comment 💬👇
📜 MIT lic
#AI #RAG
October 30, 2025 at 8:33 PM
#OpenAI #OSS #Safeguard 🧠⚙️ Run local #LLM #guardrails with open-source models (120B & 20B). Works with #GGUF, #MLX & Safetensors. Run with @lmstudio-ai.bsky.social @ollamabot.bsky.social

🔗 Link in first 💬⤵️
📜 Apache 2.0 License
#AI #RAG Repost 🔁
openai/gpt-oss-safeguard-120b · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
hf.co
October 29, 2025 at 4:35 PM
#SLM 3B: Single-Cell #Drug Response Model 🧬💊 for #cancer, #gene & #cell studies, adaptable to other domains by #Tahoe #Therapeutics
🔗 Link in first 💬⤵️
📜 Apache 2.0 Lic
#LLM #AI #RAG Repost 🔁
October 25, 2025 at 5:30 PM
🍏 #Apple #Embedding Atlas — visualize & explore embeddings interactively via Notebook, CLI, or Streamlit. 📜MIT lic
🔗 Link in first 💬⤵️

Repost 🔁 #AI #LLM #RAG
October 25, 2025 at 1:52 PM
🧠 SerenDB — serverless #PostgreSQL alternative for #AI & distributed apps. Faster branching, Aurora-compatible. Apache 2.0 lic
🔗 Link in first 💬⤵️

Repost 🔁 #LLM #Database
October 23, 2025 at 10:18 PM
github.com
October 23, 2025 at 9:10 PM
💎 @aha-io.bsky.social’s #Ruby gem for partial #JSON completion in #streaming — keeps parse state & handles truncated data efficiently.
📜 MIT lic
🔗 Link in first 💬⤵️

Repost 🔁 #LLM #AI #Streaming
October 23, 2025 at 6:33 PM
🧠 @arcadedb.bsky.social now runs fully inside #Python with native bindings — no server, Docker, or network calls! Multi-model: graph, doc, vector, time-series. #Gremlin, #Cypher, #GraphQL, #SQL. Needs #JRE. 3 flavors.
🔗 Link in first 💬⤵️

Repost 🔁 #AI #RAG #GraphDatabase #JPype #GraphRAG #GraphDB
October 18, 2025 at 8:53 PM
⚙️ #Helm 4 is here after 6 years — native SSA, #WebAssembly #WASM plugins, #OCI installs & better kstatus! Beta already out.
🔗 Link in first 💬⤵️

Repost 🔁 #DevOps #Kubernetes #CloudNative
October 18, 2025 at 2:28 PM
🧠 GraphQA: Natural language meets graph analytics — built on #NetworkX to turn your #graphs into plain-language insights.
🔗 Link in first 💬⤵️

Repost 🔁 #AI #LLM #KnowledgeGraphs #GraphRAG
October 17, 2025 at 8:21 PM
⚙️ #Google #DeepMind is building #RISC-V NPUs for edge AI — low-power, open, and framework-ready #TensorFlow, #JAX, #PyTorch
🔗 Link in first 💬⤵️

Repost 🔁 #AI #EdgeAI #Hardware
October 17, 2025 at 5:06 PM
#NVIDIA #AI #DGX Spark comparison spreadsheet.

Did you know the accuracy of the same #LLM may vary on different Hardware & even Firmware?
NVIDIA DGX Spark Benchmarks
docs.google.com
October 16, 2025 at 9:37 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
October 16, 2025 at 8:57 PM