Raj
@raj
Followers
3K
Following
11K
Media
325
Statuses
6K
Building https://t.co/TddibHHFII, a wire-compatible replacement for the OpenAI Assistant API.
Boston, MA
Joined July 2006
OpenAI released the Responses API yesterday. 24 hours later I have reimplemented the API and it's running on Ragwalla, my service.
1
2
5
Called it.
aws.amazon.com
Amazon S3 Vectors is a new cloud object store that provides native support for storing and querying vectors at massive scale, offering up to 90% cost reduction compared to conventional approaches...
When does S3 become a vector store? Seems inefficient that I need to send text to OpenAI to generate embeddings, store the embeddings in a vector store, then store the text as an object in S3. I should be able to store the text in a special vector store bucket in S3 with.
0
0
1
RT @thecyrusjanssen: An Iranian man left this comment on my YouTube channel. It's the single best explanation I've ever heard on the future….
0
6K
0
Correction: I removed it from the AppStore —- it’s only available from our website to download.
0
0
0
AI Files supports the OpenAI API and Ragwalla, my implementation of the OpenAI Files and Vector Stores APIs in addition to Assistants and Responses. Here's the Ragwalla blog post on AI Files too:
ragwalla.com
AI Files, is a free app designed to simplify file management for OpenAI’s Files and Vector Store APIs. Quickly bulk upload, delete, manage vector stores, and se
0
0
1
So I wrote a simple Mac app in Swift that allows me to configure multiple API keys, stores them securely in KeyChain Access, allows bulk operations and supports keyboard commands.
0
0
0
But that really can't be the right answer. Now I have to manage API keys, copy vector store IDs, include the dependencies, etc. It's a huge pain.
1
0
0
Ragwalla supports 5,000,000 vectors per vector store and you can use many vector stores together!.
0
0
1
If you're interested in using the Responses API with true choice with respect to completion model and vector embeddings at very large scale -- you should try Ragwalla. It's at
ragwalla.com
Build intelligent AI agents with Ragwalla's enterprise RAG platform. OpenAI Assistants API compatible with enhanced security, multi-model support, and custom fu
0
0
1
With Ragwalla you won't be limited by a maximum of 10,000 documents that OpenAI supports in a given vector store.
2
0
1
I had been reimplementing the Assistants API on Ragwalla, so the plumbing was already in place for streaming, function calling, vector search, tons of embedding models and support for more than 200+ completion models through @OpenRouterAI.
1
0
1
PDF parsing costs comparison between Google Gemini, Anthropic Claude Sonnet, and Mistral OCR: . Google's Gemini 2.0 Flash: 1,000 pages * $0.00025 = $0.25. Mistral OCR: 1,000 pages * $0.001 = $1.00. Anthropic's Claude 3.7 Sonnet: 1,000 pages * $0.009 = $9.00.
0
0
0
Good luck getting anything other than an HTTP 500 response from using PDF and OCR functionality with the @mistralai API.
Announcing @MistralAI OCR - the world’s best document understanding API. 🔍 State-of-the-art understanding of complex documents.🌍 Natively multilingual and multimodal.⚡ Fastest in its category.📄 Doc-as-prompt, structured output.🔒 Available for on-prem deployment
0
0
0
RT @sunbains: DeepSeek doesn’t seem like a side project by some quants. Writing a correct distributed file system alone is a multi year p….
github.com
A high-performance distributed file system designed to address the challenges of AI training and inference workloads. - GitHub - deepseek-ai/3FS: A high-performance distributed file system design...
0
217
0
RT @PaulieBlade: @AlexandruC4 Everyone knows BRICS stands for Belgium, Rhode Island, Canada and Spain.
0
390
0
