Building an AI-powered search engine from scratch
β’
8
Astra Clelia Bertelli PRO
as-cle-bert
AI & ML interests
Biology + Artificial Intelligence = β€οΈ | AI for sustainable development, sustainable development for AI | Researching on Machine Learning Enhancement | I love automation for everyday things | Blogger | Open Source
Recent Activity
posted
an
update
3 days ago
I got my GitHub Wrapped for 2024 today!π₯
Get yours here on HuggingFace π https://huggingface.co/spaces/as-cle-bert/what-a-git-year
GitHub repo with the code to reproduce it π https://github.com/AstraBert/what-a-git-year
Hope that everybody had a Git year!π
updated
a Space
4 days ago
as-cle-bert/pokemon-bot
updated
a Space
4 days ago
as-cle-bert/what-a-git-year
Articles
Organizations
Posts
27
Post
2046
I got my GitHub Wrapped for 2024 today!π₯
Get yours here on HuggingFace π as-cle-bert/what-a-git-year
GitHub repo with the code to reproduce it π https://github.com/AstraBert/what-a-git-year
Hope that everybody had a Git year!π
Get yours here on HuggingFace π as-cle-bert/what-a-git-year
GitHub repo with the code to reproduce it π https://github.com/AstraBert/what-a-git-year
Hope that everybody had a Git year!π
Post
1641
Hi HuggingFacers!π€ΆπΌ
As my last 2024 project, I've dropped a Discord Bot that knows a lot about Pokemonsπ¦
GitHub π https://github.com/AstraBert/Pokemon-Bot
Demo Space π as-cle-bert/pokemon-bot
The bot integrates:
- Chat features (Cohere's Command-R) with RAG functionalities (hybrid search and reranking with Qdrant) and chat memory (managed through PostgreSQL) to produce information about Pokemons
- Image-based search to identify Pokemons from their images (via Qdrant)
- Card package random extraction and description
HuggingFaceπ€, as usual, plays the most important role in the application stack, with the following models:
- sentence-transformers/LaBSE
- prithivida/Splade_PP_en_v1
- facebook/dinov2-large
And datasets:
- Karbo31881/Pokemon_images
- wanghaofan/pokemon-wiki-captions
- TheFusion21/PokemonCards
Have fun!π
As my last 2024 project, I've dropped a Discord Bot that knows a lot about Pokemonsπ¦
GitHub π https://github.com/AstraBert/Pokemon-Bot
Demo Space π as-cle-bert/pokemon-bot
The bot integrates:
- Chat features (Cohere's Command-R) with RAG functionalities (hybrid search and reranking with Qdrant) and chat memory (managed through PostgreSQL) to produce information about Pokemons
- Image-based search to identify Pokemons from their images (via Qdrant)
- Card package random extraction and description
HuggingFaceπ€, as usual, plays the most important role in the application stack, with the following models:
- sentence-transformers/LaBSE
- prithivida/Splade_PP_en_v1
- facebook/dinov2-large
And datasets:
- Karbo31881/Pokemon_images
- wanghaofan/pokemon-wiki-captions
- TheFusion21/PokemonCards
Have fun!π
Collections
2
Testing retrieval performance of embedding models with SenTrEv
-
sentence-transformers/all-MiniLM-L6-v2
Sentence Similarity β’ Updated β’ 73.1M β’ β’ 2.73k -
sentence-transformers/all-mpnet-base-v2
Sentence Similarity β’ Updated β’ 20M β’ β’ 942 -
sentence-transformers/sentence-t5-base
Sentence Similarity β’ Updated β’ 169k β’ 45 -
Supabase/gte-small
Feature Extraction β’ Updated β’ 1.3M β’ 71
Spaces related to everything-ai tasks
spaces
22
pinned
Running
4
π¨
Pokemon Bot
A bot that knows a lot about Pokemons
pinned
Running
7
π’
What A Git Year
Showcase your GitHub achievements in the past year!
pinned
Running
4
π
Bsky Feedllama Demo
Demo for BlueSky FeedLlama with Streamlit and Cohere
pinned
Running
6
π¬
BioMedicalPapersBot
Bot that scrapes Pubmed
pinned
Paused
4
β‘
Books Mixer Ai
Mix and twist your favorite books with AI!
pinned
Running
1
β‘
Streamlit Supabase Auth Ui
Seamless Supabase authentication for seamless Streamlit apps
models
11
as-cle-bert/bcus-class-segformer
Image Classification
β’
Updated
β’
9
as-cle-bert/tinyllama-essay-scorer
Text Generation
β’
Updated
β’
22
β’
1
as-cle-bert/tiny-fungal-llama
Text Generation
β’
Updated
β’
34
β’
1
as-cle-bert/carbon-footprint-prediction
Tabular Regression
β’
Updated
β’
1
as-cle-bert/saccharomyces-pythia-v1
Text Generation
β’
Updated
β’
16
as-cle-bert/resistBERT
Text Classification
β’
Updated
β’
13
β’
1
as-cle-bert/segformer-v1-breastcancer
Image Segmentation
β’
Updated
β’
14
as-cle-bert/segformer-breastcancer
Image Segmentation
β’
Updated
β’
16
as-cle-bert/beit-banana-diseases
Image Classification
β’
Updated
β’
10
β’
1
as-cle-bert/bus-deit
Image Classification
β’
Updated
β’
17
β’
1
datasets
14
as-cle-bert/architecture_vs_normal_image_prompts
Viewer
β’
Updated
β’
6k
β’
10
β’
1
as-cle-bert/speckledata
Viewer
β’
Updated
β’
2.43k
β’
45
as-cle-bert/saccaromyces-cerevisiae-base
Viewer
β’
Updated
β’
368
β’
48
β’
1
as-cle-bert/AMR-Gene-Families
Viewer
β’
Updated
β’
1.5k
β’
43
β’
1
as-cle-bert/scerevisiae-proteins-reduced
Viewer
β’
Updated
β’
600
β’
55
as-cle-bert/plastic-enzymes
Viewer
β’
Updated
β’
1.64k
β’
37
β’
1
as-cle-bert/scerevisiae-transcripts-biotypes
Viewer
β’
Updated
β’
6.72k
β’
43
β’
1
as-cle-bert/breastcancer-semantic-segmentation
Viewer
β’
Updated
β’
40
β’
44
as-cle-bert/banana-disease-classification
Viewer
β’
Updated
β’
777
β’
43
β’
1
as-cle-bert/breastcancer-auto-objdetect
Viewer
β’
Updated
β’
547
β’
68
β’
1