Deepankar Mahapatro

[Deepankar Mahapatro @_deepankarm_]

🧠Introducing 𝐛𝐚𝐛𝐲𝐚𝐠𝐢-𝐚𝐬-𝐚-𝐬𝐞𝐫𝐯𝐢𝐜𝐞.

🤝Integrate @yoheinakajima 's babyagi with your own applications - thanks to @langchain and @JinaAI_'s langchain-serve with one simple command - 𝐥𝐜-𝐬𝐞𝐫𝐯𝐞 𝐝𝐞𝐩𝐥𝐨𝐲 𝐛𝐚𝐛𝐲𝐚𝐠𝐢

https://t.co/znsNhe8Klo

[Deepankar Mahapatro @_deepankarm_]

@evalstate @mitsuhiko @simonw Wrote about a few of the idiosyncrasies here - https://t.co/8cQoVPT1Vi

[OpenAI Developers @OpenAIDevs]

Today we’re announcing Open Responses: an open-source spec for building multi-provider, interoperable LLM interfaces built on top of the original OpenAI Responses API.

✅ Multi-provider by default
✅ Useful for real-world workflows
✅ Extensible without fragmentation

Build agentic systems without rewriting your stack for every model: https://t.co/ZJPNDemq40

[Deepankar Mahapatro @_deepankarm_]

@OpenAIDevs Thank you so much! This was such a pain while building multi-provider agent backends.

https://t.co/8cQoVPT1Vi

[Deepankar Mahapatro @_deepankarm_]

@juldanjou @sileht Please check out pyleak. It helps detecting blocked event loops and the exact code location responsible.

https://t.co/XKVA5J0DS8

[Deepankar Mahapatro @_deepankarm_]

@trq212 Open source tool to run chaos engineering experiments for AI Agents

https://t.co/JlXxfFbYd3

[Deepankar Mahapatro @_deepankarm_]

@willmcgugan I've built pyleak to detect such blocking operations in CI - https://t.co/XKVA5J0DS8

[Deepankar Mahapatro @_deepankarm_]

I wrote about the issues we faced trusting "OpenAI-compatible" claims across models and providers. @simonw highlighted the same problem in his AAIF post. Hope @linuxfoundation considers this - a real spec would open doors for languages beyond Python/TS.

https://t.co/8cQoVPT1Vi

[Deepankar Mahapatro @_deepankarm_]

@ibuildthecloud @thdxr @ibuildthecloud this is such a pain while building for production! The compatibility claim is a lie. We need a standard.

I wrote about it in detail here - https://t.co/8cQoVPT1Vi

[Deepankar Mahapatro @_deepankarm_]

@TodePond If anyone's looking for a solution using Go - https://t.co/Hi427HZGpO

[Deepankar Mahapatro @_deepankarm_]

@swyx @ankrgyl @mojombo Streaming + structured output latency has been a real pain. godantic (Go) solves this among other things - repairs incomplete JSON mid-stream, returns typed results immediately.

https://t.co/Hi427HZGpO

[Deepankar Mahapatro @_deepankarm_]

@bo_wangbo Congratulations Bo 💙

[Deepankar Mahapatro @_deepankarm_]

@bo_wangbo Congratulations Bo!!

[Han Xiao ✈️ ICML 2026 @hxiao]

okay this is a happy surprise. During the ICLR2024 keynote, in one slide of @jietang keynote speech about @ChatGLM to AGI, @JinaAI_ is there on the top 20 Github organizations 😃

[Jina AI @JinaAI_]

🤨 This fine-tuning is too good to be true? Just tell us what you want your embeddings to excel at, e.g., car insurance claims, financial news, Spanish dialogs. Specify your wish in a prompt; and remember this is your only input to our API. In about 30 mins, we then deliver a ready-to-use, fine-tuned embedding model that can be loaded via SentenceTransformers. Behind the scenes, we take care of everything else: from generating useful synthetic data to managing the train-eval-test ML workflow, and finally, uploading the fine-tuned model to the @huggingface Hub. Yep, under this very minimal UI abstraction, so much happens!

[Jeff Geerling @geerlingguy]

If IBM decides to merge Terraform and Ansible, would that be Terrible?

[Jina AI @JinaAI_]

We are releasing two new open-source reranker models: jina-reranker-v1-turbo-en and jina-reranker-v1-tiny-en, the latter has only 30M parameters and four layers! 🤯 These two new rerankers enjoy 5X faster inference speed than our last jina-reranker-v1-base model at only a very small cost on the quality. You can find these two models on @huggingface
Turbo (6-layer, 37.8M parameters): https://t.co/U1g32ZjuLX
Tiny (4-layer, 33M parameters):
https://t.co/QlyXdkDTPw

[Jina AI @JinaAI_]

Feeding webpages to LLMs is crucial for grounding, but it's hard to do right. Scraping webpages is complex and unreliable, especially with dynamic pages. 🥁Introduce Jina Reader: simply prefix any URL with 𝗵𝘁𝘁𝗽𝘀://𝗿.𝗷𝗶𝗻𝗮.𝗮𝗶 and get an LLM-friendly input! Our Reader API acts as a proxy that processes any URL by performing browser rendering, content extraction, and cleaning, ultimately converting it into well-formatted text that is ready to use. It does all the nasty job so you don't have to.

[LlamaIndex 🦙 @llama_index]

Jina's new reranker can dramatically improve the quality of your RAG application!

Vector search by itself can help you search your data by meaning, but paper after paper shows using a post-retrieval reranker like @JinaAI_'s just-released jina-reranker-v1-base-en can give the quality of your results and the resulting query to the LLM a big boost.

Step through using their reranker step-by-step with LlamaIndex and @MistralAI:
https://t.co/6U3hd3PZkR

[Jina AI @JinaAI_]

🚀 Introducing Reranker API! Leveraging our latest research for top-notch performance, enjoy a boost of +20% in accuracy on vector search & RAG systems. Kickstart with 1 million tokens on us! https://t.co/mQru3mgWdp

[Jina AI @JinaAI_]

Our open-source bilingual Spanish-English embedding model is now ready for download through @huggingface. Start using it right away to power your state-of-the-art AI applications.

https://t.co/EnbHAmcXIc