Our @mrscoopers.bsky.social will speak on “Mixing Sparse & Dense Representations” in Week 2 of Modern Retrieval for Humans and Agents by Trey Grainger and Doug Turnbull.
🔗 Details: aipoweredsearch.com/articles/ai-...
Our @mrscoopers.bsky.social will speak on “Mixing Sparse & Dense Representations” in Week 2 of Modern Retrieval for Humans and Agents by Trey Grainger and Doug Turnbull.
🔗 Details: aipoweredsearch.com/articles/ai-...
@qdrant.bsky.social Discord, I finally got a hint🫡
Threw together a guide on decay functions for #relevance score boosting, aka fresher by time/closer by geo
🪄https://medium.com/qdrant/untangling-relevance-score-boosting-in-vector-search-ccffb4a574d0
@qdrant.bsky.social Discord, I finally got a hint🫡
Threw together a guide on decay functions for #relevance score boosting, aka fresher by time/closer by geo
🪄https://medium.com/qdrant/untangling-relevance-score-boosting-in-vector-search-ccffb4a574d0
🌩️ #Cloud #inference dropped RN (local with FastEmbed was sneakily there for some time).
So here comes the convenient plugging in of text/images in Qdrant, while saving on latency.
👇A lb of details
🌩️ #Cloud #inference dropped RN (local with FastEmbed was sneakily there for some time).
So here comes the convenient plugging in of text/images in Qdrant, while saving on latency.
👇A lb of details
Qdrant will host a full day of workshops & talks on #vector #search & #AI at Colosseum Berlin on the 26th.
Btw, it’s a Filmtheater, so we’ll all be kinda movie stars (pun heavily intended).
👀 Details: qdrant.tech/blog/vector-...
Qdrant will host a full day of workshops & talks on #vector #search & #AI at Colosseum Berlin on the 26th.
Btw, it’s a Filmtheater, so we’ll all be kinda movie stars (pun heavily intended).
👀 Details: qdrant.tech/blog/vector-...
P.S. Mostly got a stroke spelling "hitchhiker"
For anyone implementing textual RAG, check the blog by @cle-does-things.bsky.social!
✅ useful tips, from chunking to evals-related;
✅ projects applying each tip in the wild.
👉 qdrant.tech/blog/hitchhi...
P.S. Mostly got a stroke spelling "hitchhiker"
Next Wed, #Munich, lu.ma/xh0natks
Next Wed, #Munich, lu.ma/xh0natks
Kudos to @hf.co for making this 5th version of SentenceTransformers real, I really-really want to see what the HF community will craft with this 👀👀👀
🔥 huggingface.co/blog/train-s...
Kudos to @hf.co for making this 5th version of SentenceTransformers real, I really-really want to see what the HF community will craft with this 👀👀👀
🔥 huggingface.co/blog/train-s...
I do be unironically loving people asking questions❤️
P.S. A link to @LukawskiKacper & my "Vector Search" module JFYI 👇
I do be unironically loving people asking questions❤️
P.S. A link to @LukawskiKacper & my "Vector Search" module JFYI 👇
Was possible due to new n8n's amazing feature - verified community nodes.
No more HTTP nodes for calling Qdrant's API ever again!
@qdrant.bsky.social + @n8n.io = 🤘
👇links
Was possible due to new n8n's amazing feature - verified community nodes.
No more HTTP nodes for calling Qdrant's API ever again!
@qdrant.bsky.social + @n8n.io = 🤘
👇links
I'll really try to make my talk (on the 17th at 11:10 am in Kesselhaus) fit this "𝘏𝘮𝘮𝘮𝘮, 𝘐 𝘴𝘩𝘰𝘶𝘭𝘥 𝘵𝘳𝘺 𝘵𝘩𝘪𝘴 𝘳𝘯" vibe of @berlinbuzzwords.de!
To TLDR, it's about making 𝐬𝐩𝐚𝐫𝐬𝐞 𝐩𝐚𝐫𝐭 𝐢𝐧 𝐡𝐲𝐛𝐫𝐢𝐝 𝐬𝐞𝐚𝐫𝐜𝐡𝐞𝐬 as 𝐫𝐞𝐥𝐢𝐚𝐛𝐥𝐞 as BM25, but 𝐬𝐞𝐦𝐚𝐧𝐭𝐢𝐜𝐚𝐥𝐥𝐲 𝐚𝐰𝐚𝐫𝐞 (so 𝐛𝐞𝐭𝐭𝐞𝐫 than BM25)
I'll really try to make my talk (on the 17th at 11:10 am in Kesselhaus) fit this "𝘏𝘮𝘮𝘮𝘮, 𝘐 𝘴𝘩𝘰𝘶𝘭𝘥 𝘵𝘳𝘺 𝘵𝘩𝘪𝘴 𝘳𝘯" vibe of @berlinbuzzwords.de!
To TLDR, it's about making 𝐬𝐩𝐚𝐫𝐬𝐞 𝐩𝐚𝐫𝐭 𝐢𝐧 𝐡𝐲𝐛𝐫𝐢𝐝 𝐬𝐞𝐚𝐫𝐜𝐡𝐞𝐬 as 𝐫𝐞𝐥𝐢𝐚𝐛𝐥𝐞 as BM25, but 𝐬𝐞𝐦𝐚𝐧𝐭𝐢𝐜𝐚𝐥𝐥𝐲 𝐚𝐰𝐚𝐫𝐞 (so 𝐛𝐞𝐭𝐭𝐞𝐫 than BM25)
CapCut:
- Lemme quickly transcribe your "FastEmbed" as "fast & bad", ha?
- How about we call "upsert operation" an "absurd operation"?
Is CapCut secretly paid by our competitors?🤔
CapCut:
- Lemme quickly transcribe your "FastEmbed" as "fast & bad", ha?
- How about we call "upsert operation" an "absurd operation"?
Is CapCut secretly paid by our competitors?🤔
Here's a riddle for you: if an LLM finishes generation when it sees EOS, when do prog rock artists understand that the song should end?
Here's a riddle for you: if an LLM finishes generation when it sees EOS, when do prog rock artists understand that the song should end?
- "In the case of LLMs fine-tuned for function-calling, the thought process is optional"
> the thought process is optional.
... me every other day.
Seriously, are we teaching agents to think before they act, when 90% of us here don't do that?
- "In the case of LLMs fine-tuned for function-calling, the thought process is optional"
> the thought process is optional.
... me every other day.
Seriously, are we teaching agents to think before they act, when 90% of us here don't do that?
1. Is there a good read on jailbreaking agents? (spooky-scary)
2. Are instruct models slowly transforming to instruct-to-call-tools ones?
#hf_agents_course #agents
1. Is there a good read on jailbreaking agents? (spooky-scary)
2. Are instruct models slowly transforming to instruct-to-call-tools ones?
#hf_agents_course #agents
🫣I think I've never finished any online course ever & am interested to see:
a) as a devrel, how ppl out there do courses;
b) as a vector search advocate, how ppl out there approach agents.
🫣I think I've never finished any online course ever & am interested to see:
a) as a devrel, how ppl out there do courses;
b) as a vector search advocate, how ppl out there approach agents.
🥨Another onsite event of my baby, BASED #search meetup, is confirmed & happening on 12th of June in Tacto's office
I love this community & us discussing search without gatekeeping & boring advertisements:)
👉 lu.ma/cyelt1n6
#ai #rag #agents
🥨Another onsite event of my baby, BASED #search meetup, is confirmed & happening on 12th of June in Tacto's office
I love this community & us discussing search without gatekeeping & boring advertisements:)
👉 lu.ma/cyelt1n6
#ai #rag #agents