HackerReposA FIELD GUIDE TO OPEN SOURCE
ProSponsor the shelf♧ 0
← Back to top all-time
towhee-io
examples
Jupyter Notebook2022–2023
towhee-io / examples

examples

Analyze the unstructured data with Towhee, such as reverse image search, reverse video search, audio classification, question and answer systems, molecular search, etc.

Creative & MediaAI & Machine LearningLearning & Reference
Explore on GitHubRead Hacker News discussions
2Distinct people
2Mentions
0Explicit recommenders
517GitHub stars
REPOSITORY AT A GLANCE

What to know before exploring

What it is

Analyze the unstructured data with Towhee, such as reverse image search, reverse video search, audio classification, question and answer systems, molecular search, etc.

GitHub

Where it is used

No documented product use has been verified yet.

What people are saying

No recommendation phrase was found in the indexed comments.

No classified warning is attached to this page. Read the discussions before treating silence as approval.

Also in these discussions

No other repository is repeatedly linked in the same discussions.

This week on Hacker News

Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 1:49:46 PM UTC.

No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.

Mentions over time

HN mentions by week2 dated mentions

Observed mentions: 2022-09-22 19:16:44 UTC to 2023-03-26 14:20:32 UTC. Weeks start Monday, UTC.

012022-09-19 00:00:00 UTC to 2022-09-26 00:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 commentsSep 192022-09-26 00:00:00 UTC to 2022-10-03 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2022-10-03 00:00:00 UTC to 2022-10-10 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2022-10-10 00:00:00 UTC to 2022-10-17 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2022-10-17 00:00:00 UTC to 2022-10-24 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2022-10-24 00:00:00 UTC to 2022-10-31 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2022-10-31 00:00:00 UTC to 2022-11-07 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2022-11-07 00:00:00 UTC to 2022-11-14 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2022-11-14 00:00:00 UTC to 2022-11-21 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2022-11-21 00:00:00 UTC to 2022-11-28 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2022-11-28 00:00:00 UTC to 2022-12-05 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2022-12-05 00:00:00 UTC to 2022-12-12 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2022-12-12 00:00:00 UTC to 2022-12-19 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2022-12-19 00:00:00 UTC to 2022-12-26 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 commentsDec 192022-12-26 00:00:00 UTC to 2023-01-02 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-01-02 00:00:00 UTC to 2023-01-09 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-01-09 00:00:00 UTC to 2023-01-16 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-01-16 00:00:00 UTC to 2023-01-23 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-01-23 00:00:00 UTC to 2023-01-30 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-01-30 00:00:00 UTC to 2023-02-06 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-02-06 00:00:00 UTC to 2023-02-13 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-02-13 00:00:00 UTC to 2023-02-20 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-02-20 00:00:00 UTC to 2023-02-27 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-02-27 00:00:00 UTC to 2023-03-06 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-03-06 00:00:00 UTC to 2023-03-13 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-03-13 00:00:00 UTC to 2023-03-20 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-03-20 00:00:00 UTC to 2023-03-27 00:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 commentsMar 20

Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.

View mention counts and date ranges
UTC ranges include their start and exclude their end. Select a period to filter the source evidence.
PeriodStart (UTC)End (exclusive, UTC)MentionsSubmissionsComments
Sep 192022-09-19 00:00:00 UTC2022-09-26 00:00:00 UTC101
Sep 262022-09-26 00:00:00 UTC2022-10-03 00:00:00 UTC000
Oct 32022-10-03 00:00:00 UTC2022-10-10 00:00:00 UTC000
Oct 102022-10-10 00:00:00 UTC2022-10-17 00:00:00 UTC000
Oct 172022-10-17 00:00:00 UTC2022-10-24 00:00:00 UTC000
Oct 242022-10-24 00:00:00 UTC2022-10-31 00:00:00 UTC000
Oct 312022-10-31 00:00:00 UTC2022-11-07 00:00:00 UTC000
Nov 72022-11-07 00:00:00 UTC2022-11-14 00:00:00 UTC000
Nov 142022-11-14 00:00:00 UTC2022-11-21 00:00:00 UTC000
Nov 212022-11-21 00:00:00 UTC2022-11-28 00:00:00 UTC000
Nov 282022-11-28 00:00:00 UTC2022-12-05 00:00:00 UTC000
Dec 52022-12-05 00:00:00 UTC2022-12-12 00:00:00 UTC000
Dec 122022-12-12 00:00:00 UTC2022-12-19 00:00:00 UTC000
Dec 192022-12-19 00:00:00 UTC2022-12-26 00:00:00 UTC000
Dec 262022-12-26 00:00:00 UTC2023-01-02 00:00:00 UTC000
Jan 22023-01-02 00:00:00 UTC2023-01-09 00:00:00 UTC000
Jan 92023-01-09 00:00:00 UTC2023-01-16 00:00:00 UTC000
Jan 162023-01-16 00:00:00 UTC2023-01-23 00:00:00 UTC000
Jan 232023-01-23 00:00:00 UTC2023-01-30 00:00:00 UTC000
Jan 302023-01-30 00:00:00 UTC2023-02-06 00:00:00 UTC000
Feb 62023-02-06 00:00:00 UTC2023-02-13 00:00:00 UTC000
Feb 132023-02-13 00:00:00 UTC2023-02-20 00:00:00 UTC000
Feb 202023-02-20 00:00:00 UTC2023-02-27 00:00:00 UTC000
Feb 272023-02-27 00:00:00 UTC2023-03-06 00:00:00 UTC000
Mar 62023-03-06 00:00:00 UTC2023-03-13 00:00:00 UTC000
Mar 132023-03-13 00:00:00 UTC2023-03-20 00:00:00 UTC000
Mar 202023-03-20 00:00:00 UTC2023-03-27 00:00:00 UTC101

What Hacker News says

2 sources
kkielhofner·Mar 26, 2023
As another commenter noted, Milvus is overkill and a "bit much" if you're learning/playing. A good intro to the field with progression towards a full Milvus implementation could be starting with towhee[0] (which is also supported by Milvus). towhee has an example to do exactly what you want with CLIP[1]. For icing on the cake the example notebook includes deployment of the model with Nvidia Triton Server[2], which IMO is hands down the best way to actually deploy an ML model[3]. [0] - https://towhee.io/ [1] - https://github.com/towhee-io/examples/tree/main/image/text_i... [2] - https://github.com/triton-inference-server/server [3] - https://news.ycombinator.com/item?id=35199418#35200266
In Vector database built for scalable similarity search
fhaltmayer·Sep 22, 2022
Usually this is done in three steps. The first step is using a neural network to create a bounding box around the object, then generating vector embeddings of the object, and then using similarity search on vector embeddings. The first step is accomplished by training a detection model to generate the bounding box around your object, this can usually be done by finetuning an already trained detection model. For this step the data you would need is all the images of the object you have with a bounding box created around it, the version of the object doesnt matter here. The second step involves using a generalized image classification model thats been pretrained on generalized data (VGG, etc.) and a vector search engine/vector database. You would start by using the image classification model to generate vector embeddings (https://frankzliu.
Read the rest
com/blog/understanding-neural-network-embe...) of all the different versions of the object. The more ground truth images you have, the better, but it doesn't require the same amount as training a classifier model. Once you have your versions of the object as embeddings, you would store them in a vector database (for example Milvus: https://github.com/milvus-io/milvus). Now whenever you want to detect the object in an image you can run the image through the detection model to find the object in the image, then run the sliced out image of the object through the vector embedding model. With this vector embedding you can then perform a search in the vector database, and the closest results will most likely be the version of the object. Hopefully this helps with the general rundown of how it would look like. Here is an example using Milvus and Towhee https://github.com/towhee-io/examples/tree/3a2207d67b10a246f.... Disclaimer: I am a part of those two open source projects.
In Ask HN: Any good self-hosted image recognition software?

MAKE YOURSELF AT HOME

A few shortcuts

/
Search the collection
?
Open this guide
Esc
Close dialogs and navigation

Your saved repositories and interests stay in this browser.