Ofer Mendelevitch
@ofermend.bsky.social
Developer Relations @ Vectara
Working on generative AI
Working on generative AI
Glad to share this upcoming event for anyone interested to learn more about hallucinations.
Event: Hallucinations by hand, with Prof Tom Yeh
RSVP: luma.com/1kc8iqu9
Event: Hallucinations by hand, with Prof Tom Yeh
RSVP: luma.com/1kc8iqu9
Keynote Lecture: Hallucination by Hand ✍️ (sponsored by Vectara) · Zoom · Luma
I will teach you an advanced AI topic by hand ✍️, not taught anywhere else!
Title: Hallucination by Hand ✍️
LLMs don’t just make mistakes—they hallucinate with…
luma.com
November 7, 2025 at 9:26 PM
Glad to share this upcoming event for anyone interested to learn more about hallucinations.
Event: Hallucinations by hand, with Prof Tom Yeh
RSVP: luma.com/1kc8iqu9
Event: Hallucinations by hand, with Prof Tom Yeh
RSVP: luma.com/1kc8iqu9
Reposted by Ofer Mendelevitch
Your Copilot is not Enough
Does anyone see good results from Microsoft Copilot?
I've tested this a bit and seems pretty much like many first-gen microsoft products...
www.vectara.com/blog/your-co...
Does anyone see good results from Microsoft Copilot?
I've tested this a bit and seems pretty much like many first-gen microsoft products...
www.vectara.com/blog/your-co...
Your Copilot is Not Enough
Why Microsoft’s Copilot is to GenAI like Windows-95 is to operating systems.
www.vectara.com
November 6, 2025 at 1:05 AM
Your Copilot is not Enough
Does anyone see good results from Microsoft Copilot?
I've tested this a bit and seems pretty much like many first-gen microsoft products...
www.vectara.com/blog/your-co...
Does anyone see good results from Microsoft Copilot?
I've tested this a bit and seems pretty much like many first-gen microsoft products...
www.vectara.com/blog/your-co...
Your Copilot is not Enough
Does anyone see good results from Microsoft Copilot?
I've tested this a bit and seems pretty much like many first-gen microsoft products...
www.vectara.com/blog/your-co...
Does anyone see good results from Microsoft Copilot?
I've tested this a bit and seems pretty much like many first-gen microsoft products...
www.vectara.com/blog/your-co...
Your Copilot is Not Enough
Why Microsoft’s Copilot is to GenAI like Windows-95 is to operating systems.
www.vectara.com
November 6, 2025 at 1:05 AM
Your Copilot is not Enough
Does anyone see good results from Microsoft Copilot?
I've tested this a bit and seems pretty much like many first-gen microsoft products...
www.vectara.com/blog/your-co...
Does anyone see good results from Microsoft Copilot?
I've tested this a bit and seems pretty much like many first-gen microsoft products...
www.vectara.com/blog/your-co...
Can AI write books people actually want to read?
I’ve been testing that through my side project "AI Explains" - concise 100–150 page ebooks, written with AI & curated by humans.
Most recent book about Adult ADHD, with Carmen Enciso-Steinberg www.amazon.com/AI-Explains-....
I’ve been testing that through my side project "AI Explains" - concise 100–150 page ebooks, written with AI & curated by humans.
Most recent book about Adult ADHD, with Carmen Enciso-Steinberg www.amazon.com/AI-Explains-....
AI Explains: ADHD for Adults
Amazon.com: AI Explains: ADHD for Adults eBook : Enciso-Steinberg, Carmen, Piani, Alexis: Kindle Store
www.amazon.com
October 29, 2025 at 6:50 PM
Can AI write books people actually want to read?
I’ve been testing that through my side project "AI Explains" - concise 100–150 page ebooks, written with AI & curated by humans.
Most recent book about Adult ADHD, with Carmen Enciso-Steinberg www.amazon.com/AI-Explains-....
I’ve been testing that through my side project "AI Explains" - concise 100–150 page ebooks, written with AI & curated by humans.
Most recent book about Adult ADHD, with Carmen Enciso-Steinberg www.amazon.com/AI-Explains-....
I'm excited to share our new episode of the "Generation AI" podcast, with our special guest Matt Abrams - a great discussion about AI and Trust, AI regulation and how to gain the benefits of AI without losing empathy.
Enjoy!
t.co/BQZNjRRDEB
Enjoy!
t.co/BQZNjRRDEB
https://open.spotify.com/episode/0yFM5btEo819gC7ZW2jEUF
t.co
September 25, 2025 at 8:59 PM
I'm excited to share our new episode of the "Generation AI" podcast, with our special guest Matt Abrams - a great discussion about AI and Trust, AI regulation and how to gain the benefits of AI without losing empathy.
Enjoy!
t.co/BQZNjRRDEB
Enjoy!
t.co/BQZNjRRDEB
If you have built AI agents in the last 6+ months you know they are (unfortunately) quite fragile and can easily fail in production and at scale.
Agents can misinterpret the task, choose the wrong tools, hallucinate in their response, etc.
Agents can misinterpret the task, choose the wrong tools, hallucinate in their response, etc.
GitHub - vectara/awesome-agent-failures: A community curated collection of AI agent failure modes and battle-tested solutions.
A community curated collection of AI agent failure modes and battle-tested solutions. - vectara/awesome-agent-failures
github.com
September 3, 2025 at 2:27 PM
If you have built AI agents in the last 6+ months you know they are (unfortunately) quite fragile and can easily fail in production and at scale.
Agents can misinterpret the task, choose the wrong tools, hallucinate in their response, etc.
Agents can misinterpret the task, choose the wrong tools, hallucinate in their response, etc.
Super excited to share the news: RFPs no longer take days and weeks, but with @vectara.bsky.social enterprise deep research it's quick and easy.
www.vectara.com/blog/respond...
www.vectara.com/blog/respond...
Responding to RFPs with Enterprise Deep Research
www.vectara.com
July 22, 2025 at 8:21 PM
Super excited to share the news: RFPs no longer take days and weeks, but with @vectara.bsky.social enterprise deep research it's quick and easy.
www.vectara.com/blog/respond...
www.vectara.com/blog/respond...
Enterprise Deep Research = the agentic AI killer app for business. It's like "consumer" Deep Research, but grounded in your own private data. There are so many valuable use-cases: compliance monitoring, sales enablement, onboarding, etc..
See our recent blog post: www.vectara.com/blog/introdu...
See our recent blog post: www.vectara.com/blog/introdu...
Introducing Enterprise Deep Research
www.vectara.com
July 17, 2025 at 2:31 PM
Enterprise Deep Research = the agentic AI killer app for business. It's like "consumer" Deep Research, but grounded in your own private data. There are so many valuable use-cases: compliance monitoring, sales enablement, onboarding, etc..
See our recent blog post: www.vectara.com/blog/introdu...
See our recent blog post: www.vectara.com/blog/introdu...
LLM context windows grew from 8K tokens to 1M in the span of 1-2 years. But there is a problem: they don't work very well at longer context.
This makes "context engineering" important for RAG and agentic workflows.
www.vectara.com/blog/context...
This makes "context engineering" important for RAG and agentic workflows.
www.vectara.com/blog/context...
Context Engineering: Can you trust long context?
www.vectara.com
July 15, 2025 at 4:03 PM
LLM context windows grew from 8K tokens to 1M in the span of 1-2 years. But there is a problem: they don't work very well at longer context.
This makes "context engineering" important for RAG and agentic workflows.
www.vectara.com/blog/context...
This makes "context engineering" important for RAG and agentic workflows.
www.vectara.com/blog/context...
Does your RAG return consistent results?
Consistency in RAG is a mandatory requirement for regulated industries. I'm glad to share the new "consistency score" in Open-RAG-Eval.
blog: vectara.com/blog/is-your...
Consistency in RAG is a mandatory requirement for regulated industries. I'm glad to share the new "consistency score" in Open-RAG-Eval.
blog: vectara.com/blog/is-your...
Is Your RAG Consistent?
vectara.com
July 9, 2025 at 9:18 PM
Does your RAG return consistent results?
Consistency in RAG is a mandatory requirement for regulated industries. I'm glad to share the new "consistency score" in Open-RAG-Eval.
blog: vectara.com/blog/is-your...
Consistency in RAG is a mandatory requirement for regulated industries. I'm glad to share the new "consistency score" in Open-RAG-Eval.
blog: vectara.com/blog/is-your...
Reposted by Ofer Mendelevitch
Announcing @vectara.bsky.social Hallucination Correction. This is truly ground-breaking for enterprise RAG.
www.vectara.com/blog/vectara...
www.vectara.com/blog/vectara...
Vectara's Hallucination Corrector
AI hallucinations create significant business risks and erode user trust. Vectara's Hallucination Corrector (VHC) identifies inaccuracies, suggests fixes, and provides essential guardrails for your AI...
www.vectara.com
May 13, 2025 at 3:11 PM
Announcing @vectara.bsky.social Hallucination Correction. This is truly ground-breaking for enterprise RAG.
www.vectara.com/blog/vectara...
www.vectara.com/blog/vectara...
LLM Joke:
Why did the transformer go to therapy?
It needed more attention.
Why did the transformer go to therapy?
It needed more attention.
June 11, 2025 at 3:46 PM
LLM Joke:
Why did the transformer go to therapy?
It needed more attention.
Why did the transformer go to therapy?
It needed more attention.
Having fun in Day 2 of AI Engineer World Fair in SF.
Check out my online talk about @vectara.bsky.social's open-rag-eval and how to do RAG evaluation w/o golden answers:
www.youtube.com/watch?v=1cQl...
Check out my online talk about @vectara.bsky.social's open-rag-eval and how to do RAG evaluation w/o golden answers:
www.youtube.com/watch?v=1cQl...
open-rag-eval: RAG Evaluation without "golden" answers — Ofer Mendelevitch, Vectara
YouTube video by AI Engineer
www.youtube.com
June 4, 2025 at 6:26 PM
Having fun in Day 2 of AI Engineer World Fair in SF.
Check out my online talk about @vectara.bsky.social's open-rag-eval and how to do RAG evaluation w/o golden answers:
www.youtube.com/watch?v=1cQl...
Check out my online talk about @vectara.bsky.social's open-rag-eval and how to do RAG evaluation w/o golden answers:
www.youtube.com/watch?v=1cQl...
Announcing @vectara.bsky.social Hallucination Correction. This is truly ground-breaking for enterprise RAG.
www.vectara.com/blog/vectara...
www.vectara.com/blog/vectara...
Vectara's Hallucination Corrector
AI hallucinations create significant business risks and erode user trust. Vectara's Hallucination Corrector (VHC) identifies inaccuracies, suggests fixes, and provides essential guardrails for your AI...
www.vectara.com
May 13, 2025 at 3:11 PM
Announcing @vectara.bsky.social Hallucination Correction. This is truly ground-breaking for enterprise RAG.
www.vectara.com/blog/vectara...
www.vectara.com/blog/vectara...
Sharing the latest release of open-rag-eval 0.1.5 with connectors to @vectara.bsky.social @langchain.bsky.social and @llamaindex.bsky.social
github.com/vectara/open...
github.com/vectara/open...
GitHub - vectara/open-rag-eval: Open source RAG evaluation package
Open source RAG evaluation package. Contribute to vectara/open-rag-eval development by creating an account on GitHub.
github.com
May 13, 2025 at 2:58 AM
Sharing the latest release of open-rag-eval 0.1.5 with connectors to @vectara.bsky.social @langchain.bsky.social and @llamaindex.bsky.social
github.com/vectara/open...
github.com/vectara/open...
Reposted by Ofer Mendelevitch
We finally have an animal selected for our upcoming O'Reilly book "Hands-on RAG for production" - the Brown Hyena. Two first chapters (as early release) expected in May.
April 14, 2025 at 6:03 PM
We finally have an animal selected for our upcoming O'Reilly book "Hands-on RAG for production" - the Brown Hyena. Two first chapters (as early release) expected in May.
Excited about the Data Council 2025 event next week.
April 14, 2025 at 6:11 PM
Excited about the Data Council 2025 event next week.
We finally have an animal selected for our upcoming O'Reilly book "Hands-on RAG for production" - the Brown Hyena. Two first chapters (as early release) expected in May.
April 14, 2025 at 6:03 PM
We finally have an animal selected for our upcoming O'Reilly book "Hands-on RAG for production" - the Brown Hyena. Two first chapters (as early release) expected in May.
Reposted by Ofer Mendelevitch
Reposted by Ofer Mendelevitch
Happy to share the new open-rag-eval: a new approach in RAG evaluation.
Repo: github.com/vectara/open...
blog: www.vectara.com/blog/towards...
Repo: github.com/vectara/open...
blog: www.vectara.com/blog/towards...
GitHub - vectara/open-rag-eval: Open source RAG evaluation package
Open source RAG evaluation package. Contribute to vectara/open-rag-eval development by creating an account on GitHub.
github.com
April 8, 2025 at 2:52 PM
Happy to share the new open-rag-eval: a new approach in RAG evaluation.
Repo: github.com/vectara/open...
blog: www.vectara.com/blog/towards...
Repo: github.com/vectara/open...
blog: www.vectara.com/blog/towards...
Happy to share the new open-rag-eval: a new approach in RAG evaluation.
Repo: github.com/vectara/open...
blog: www.vectara.com/blog/towards...
Repo: github.com/vectara/open...
blog: www.vectara.com/blog/towards...
GitHub - vectara/open-rag-eval: Open source RAG evaluation package
Open source RAG evaluation package. Contribute to vectara/open-rag-eval development by creating an account on GitHub.
github.com
April 8, 2025 at 2:52 PM
Happy to share the new open-rag-eval: a new approach in RAG evaluation.
Repo: github.com/vectara/open...
blog: www.vectara.com/blog/towards...
Repo: github.com/vectara/open...
blog: www.vectara.com/blog/towards...
Reposted by Ofer Mendelevitch
Announcing Vectara’s Python-SDK
A Python-native interface for Vectara, built for developers.
www.vectara.com
January 2, 2025 at 7:18 PM