adeel akhani

40 posts

adeel akhani banner
adeel akhani

adeel akhani

@adeel_712

software engineering @uwaterloo, prev. engineer @boardyai, @scriptrunner_ai

Pickering/Toronto Katılım Kasım 2024
70 Takip Edilen47 Takipçiler
Sabitlenmiş Tweet
adeel akhani
adeel akhani@adeel_712·
i built a free way to index and search any docs locally (cli or mcp) with a memory layer runs entirely on your machine via @ollama
English
12
4
18
1.3K
tanmay
tanmay@tanmaymshah·
3D reconstruction stands as one of the most prevalent problems in the CV space. Made a NeRF from scratch to learn more. Optimized across 2× NVIDIA T4 GPUs with F16 mixed-precision with @runpod. Peeked @ PSNR of 22, video pinned below!
tanmay tweet mediatanmay tweet media
English
2
2
5
402
adeel akhani
adeel akhani@adeel_712·
@ollama note: benchmarks sent the full page tree every time. scoping your index to a specific section url shrinks that tree a lot and helps. there's a how_to_use mcp tool that tells agents exactly how.
English
0
0
1
50
adeel akhani
adeel akhani@adeel_712·
@ollama wanted to know which local model handles tree navigation best
adeel akhani tweet media
English
4
0
2
157
adeel akhani
adeel akhani@adeel_712·
i built a free way to index and search any docs locally (cli or mcp) with a memory layer runs entirely on your machine via @ollama
English
12
4
18
1.3K
adeel akhani
adeel akhani@adeel_712·
@ollama phi4-mini default, best speed/accuracy tradeoff. gemma4:26b noticeably better if you have the ram.
English
0
0
1
67
adeel akhani
adeel akhani@adeel_712·
@ollama the root issue is the task combines 3 things at once: scan 400 semi-repetitive lines, semantically match a query to a page name, and return constrained json. small models can do each individually, they just fall apart when you need all 3 together.
English
0
0
1
50
adeel akhani
adeel akhani@adeel_712·
@ollama all 7-14b models scored the same. the task: read 400 node paths, pick the right ones, return valid hex ids as json. most would ignore the json instruction and just answer the question from training data. some hallucinated ids and tuning temperature, num_predict didn't help.
English
0
0
2
115
adeel akhani
adeel akhani@adeel_712·
@ollama indexing builds a section tree from the url structure and headings. on search a local llm reads that tree and picks the relevant sections. hybrid vector + bm25 runs inside just those sections. another llm pass reranks and filters. tree reasoning also gets semantically cached.
English
0
0
2
117
adeel akhani
adeel akhani@adeel_712·
@ollama 6 cli/mcp abilities: index any doc site. search your docs in natural language. inspect the section tree localdocs built. manage multiple indexed sources. swap the reasoning model. control the memory layer. agents also get a how_to_use tool to use efficiently.
English
0
0
2
122
adeel akhani
adeel akhani@adeel_712·
@ollama free, local, no api keys. cli and mcp. install: npm install -g @adeel712/localdocs github: github.com/adeelakhani/lo… npm package: @adeel712/localdocs" target="_blank" rel="nofollow noopener">npmjs.com/package/@adeel… pull phi4-mini and nomic-embed-text in ollama and you're setup. mcp instructions and various other details are in the readme
English
0
0
2
187
adeel akhani retweetledi
harshilpujara_
harshilpujara_@harshilpujara17·
Built a PM tool over the weekend as an AI-first product designer. PMs drown in data assembly, not actual thinking. Me and Claude Code built Northstar. Risk flags, insight cards woven into your board before you even ask. PMs aren't paid to prep. They're paid to think ahead.
English
0
1
1
125
adeel akhani
adeel akhani@adeel_712·
why buy a super expensive computer and not make full use of these modern day local llms
English
2
1
9
195
adeel akhani retweetledi
tridhatri vallamkondu
tridhatri vallamkondu@TridhatriV·
@owengretzinger keeps asking me to put out a project updates daily but I'm too lazy to navigate through linear's complex UI So I made my own app where I can push updates , tickets and agents. all powered by fff from @neogoose_btw
English
5
4
28
7.2K
lekan
lekan@sportynest·
Where is the tech community in Toronto and how do I join it
English
36
3
133
24.5K
adeel akhani retweetledi
Cursor
Cursor@cursor_ai·
We're introducing Cursor Automations to build always-on agents.
English
368
547
7.1K
2.4M