Building on HF

3 3

Prabhat PRO

prabhatkr

AI & ML interests

None yet

Recent Activity

posted an update about 2 hours ago

Why did FastMemory achieve 100% accuracy at 10 million tokens while the SOTA is stalling at 64%? It’s not because we have a better "retriever." It’s because we changed the Topology of Truth. Standard RAG treats your data like a pile of leaves. You search for a leaf, and you hope you find the right one. As the pile grows to 10 million leaves, you inevitably fail. FastMemory treats your data like a Building. Topological Isolation: We use Rust-driven Louvain clustering to atomize text into "Logic Rooms." Crystalline Grounding: Facts don't "decay" in our context; they are locked into a deterministic graph. Sub-Second O(1) Routing: We don't "search" the haystack; we navigate the floor plan. If your AI is mission-critical, "mostly right" is a liability. It’s time to move beyond the RAG pile and into the topological foundation. Verify Yourself: https://huggingface.co/datasets/fastbuilderai/fastmemory-supremacy-benchmarks/blob/main/README.md #MachineLearning #GraphAI #LouvainClustering #FastBuilder #EngineeringExcellence

updated a dataset about 7 hours ago

fastbuilderai/fastmemory-supremacy-benchmarks

posted an update 4 days ago

AI fails to scale because it wasn't trained on the data it is expected to work. Enterprise data is messier than the internet and web data that has been used to train the general models. That's why the bootup response of AI seems delightful. But that glory fades when rubber meets the road. The other approaches like RAG, KG and Ontologies proved unworthy too. In a recent hot out-of-the-press research, Topology beats RAG/KG/Ontology by a huge margin. Download PDF: https://arxiv.org/html/2603.12458v1 Blog: https://fastbuilder.ai/blog/why-ai-fails-to-scale-why-topology-is-the-top-choice-for-the-enterprise FastMemory is a topology builder for direct AI integration. Just 3 lines of code to build topology and wrap it in your LLM queries. ❌ You don't have to build embedding pipelines. Also no $$$ spent of embedding token usage. ❌ You also don't have to invest in heavy vector storage which is bigger in size than the underlying data. Vectors are 20%-50% bigger in size than text data storage. ✅ You only need the python app running the 'fastmemory' library and store the topology as graph in Neo4J or graphDB or any such storage. ✅ The stored topology is 10X-30X smaller than the data. Get the magic of AI right away similar to native AI performance without heavy infra. #topology #AI #RAG #Ontology #knowledgegraph #fastmemory

View all activity

Organizations

posted an update about 2 hours ago

Post

Why did FastMemory achieve 100% accuracy at 10 million tokens while the SOTA is stalling at 64%?

It’s not because we have a better "retriever." It’s because we changed the Topology of Truth.

Standard RAG treats your data like a pile of leaves. You search for a leaf, and you hope you find the right one. As the pile grows to 10 million leaves, you inevitably fail.

FastMemory treats your data like a Building.

Topological Isolation: We use Rust-driven Louvain clustering to atomize text into "Logic Rooms."
Crystalline Grounding: Facts don't "decay" in our context; they are locked into a deterministic graph.
Sub-Second O(1) Routing: We don't "search" the haystack; we navigate the floor plan.
If your AI is mission-critical, "mostly right" is a liability. It’s time to move beyond the RAG pile and into the topological foundation.

Verify Yourself: fastbuilderai/fastmemory-supremacy-benchmarks

#MachineLearning #GraphAI #LouvainClustering #FastBuilder #EngineeringExcellence

posted an update 4 days ago

Post

113

AI fails to scale because it wasn't trained on the data it is expected to work.

Enterprise data is messier than the internet and web data that has been used to train the general models. That's why the bootup response of AI seems delightful. But that glory fades when rubber meets the road.

The other approaches like RAG, KG and Ontologies proved unworthy too.

In a recent hot out-of-the-press research, Topology beats RAG/KG/Ontology by a huge margin.

Download PDF: https://arxiv.org/html/2603.12458v1

Blog: https://fastbuilder.ai/blog/why-ai-fails-to-scale-why-topology-is-the-top-choice-for-the-enterprise

FastMemory is a topology builder for direct AI integration. Just 3 lines of code to build topology and wrap it in your LLM queries.

❌ You don't have to build embedding pipelines. Also no $$$ spent of embedding token usage.

❌ You also don't have to invest in heavy vector storage which is bigger in size than the underlying data. Vectors are 20%-50% bigger in size than text data storage.

✅ You only need the python app running the 'fastmemory' library and store the topology as graph in Neo4J or graphDB or any such storage.

✅ The stored topology is 10X-30X smaller than the data.

Get the magic of AI right away similar to native AI performance without heavy infra.

#topology #AI #RAG #Ontology #knowledgegraph #fastmemory

posted an update 6 days ago

Post

172

A new SOTA achieved by FaastMemory - Cybersecurity can be truly agentic.

fastbuilderai/FastMemory

13. Adversarial Red-Team (Intel) 0.0% (Prompt Injection Hack) 14.8% (Database Leak) 🏆 100% (Zero-Hallucination Firewall)

posted an update 9 days ago

Post

1274

🚀 Is Vector RAG Dead? Why We Built FastMemory to Beat PageIndex
If you've built a RAG pipeline for complex financial documents, you already know the painful truth: Standard vector search fails when things get complicated.

While tools like PageIndex and Mafin 2.5 provide great out-of-the-box PDF chat experiences, they hit structural bottlenecks the second you push them past basic queries.

We just published a comprehensive benchmark study comparing FastMemory against PageIndex across 5 advanced datasets. The results fundamentally change how we should think about document ingestion.

Read more: https://x.com/FastBuilderAI/status/2037404008978018493

2 replies

posted an update about 2 months ago

Post

243

Robotics benchmark published for new SOTA in CleanRL benchmark ParamTatva/sanskrit-ppo-hopper-v5

repliedto their post 4 months ago

posted an update 4 months ago

Post

1905

Language Dexterity Benchmark

I am working on a new benchmark to establish human language dexterity. My hypothesis is that certain language allow for more accurate dexterous behaviour - Pointed, unambigous, and confusion-free references of parts of speech in small and large contexts. There are certain languages with high degree of accurate grammar like Sanskrit, Esperanto, and Turkish. I am native Sanskrit speaker.
I have plans to establish this benchmark and test this hypothesis across 100 langauges. I have created 25 task prompts for text, image, video and robotics manipulation. We can test langauges across multiple popular models. Here is the github link: https://github.com/ParamTatva-org/Linguistic-Dexterity-Benchmark

1 reply

reactedto singhsidhukuldeep's post with ❤️ almost 2 years ago

Post

1784

How many times have you said Pandas is slow and still kept on using it? 🐼💨

Get ready to say Pandas can be fast but it's expensive 😂

🙌 Original Limitations:

💻 CPU-Bound Processing: Traditional pandas operations are CPU-bound (mostly single-threaded😰), leading to slower processing of large datasets.

🧠 Memory Constraints: Handling large datasets in memory-intensive operations can lead to inefficiencies and limitations.

𝌣 Achievements with @nvidia RAPIDS cuDF:

🚀 GPU Acceleration: RAPIDS cuDF leverages GPU computing. Users switch to GPU-accelerated operations without modifying existing pandas code.

🔄 Unified Workflows: Seamlessly integrates GPU and CPU operations, falling back to CPU when necessary.

📈 Optimized Performance: With extreme parallel operation opportunity of GPUs, this achieves up to 150x speedup in data processing, demonstrated through benchmarks like DuckDB.

😅New Limitations:

🎮 GPU Availability: Requires a GPU (not everything should need a GPU)

🔄 Library Compatibility: Currently in the initial stages, all the functionality cannot be ported

🐢 Data Transfer Overhead: Moving data between CPU and GPU can introduce latency if not managed efficiently. As some operations still run on the CPU.

🤔 User Adoption: We already had vectorization support in Pandas, people just didn't use it as it was difficult to implement. We already had DASK for parallelization. It's not that solutions didn't exist

Blog: https://developer.nvidia.com/blog/rapids-cudf-accelerates-pandas-nearly-150x-with-zero-code-changes/

For Jupyter Notebooks:

%load_ext cudf.pandas
import pandas as pd

For python scripts:

python -m cudf.pandas script.py

repliedto their post almost 2 years ago

Cute scholarly noise. Here is the link https://www.thehitavada.com/Encyc/2021/8/22/The-status-and-place-of-Sanskrit-language-in-modern-India.amp.html. What a dictionary has is not all for Sanskrit especially because the effort has been always siloed. Anyways, the logic of compunding and infliction can render most of the dictionaries to a few pages.

reactedto radames's post with 🔥 almost 2 years ago

Post

2174

AI-town now runs on Hugging Face Spaces with our API for LLMs and embeddings, including the open-source Convex backend, all in one container. Easy to duplicate and config on your own

Demo: radames/ai-town
Instructions: https://github.com/radames/ai-town-huggingface

9 replies

reactedto awacke1's post with 🔥 almost 2 years ago

Post

2493

I just completed getting all four aspects of the new OpenAI GPT-4-o Omni model to process Text, Image, Audio, and Video.

Check it out and let me know what you think!

Space: awacke1/GPT-4o-omni-text-audio-image-video

Discussion: awacke1/GPT-4o-omni-text-audio-image-video

Test Runs for All Four Modalities: awacke1/GPT-4o-omni-text-audio-image-video#1

--Aaron - @awacke1

4 replies

posted an update almost 2 years ago

Post

1213

Is there a correlation between number of words and knowledge?
Sanskrit has 1000X more words than any other language.

4 replies

Prabhat PRO

AI & ML interests

Recent Activity

Organizations

prabhatkr's activity