# 🤗 Course Projects **URL:** https://discuss.huggingface.co/c/course/course-event/25.md [Latest](https://discuss.huggingface.co/latest.md) · [Categories](https://discuss.huggingface.co/categories.md) --- ## [About the 🤗 Course Projects category](https://discuss.huggingface.co/t/about-the-course-projects-category/11510)
**Author:** [@sgugger](https://discuss.huggingface.co/u/sgugger)\ **Replies:** 3\ **Last updated:** [January 20, 2022, 11:44am UTC](https://discuss.huggingface.co/t/about-the-course-projects-category/11510 "2022-01-20T11:44:36Z")
This category will regroup all course projects for the Course Community Event. It is just open as a teaser right now, you will be able to post in it starting Friday November 12th. For this event, you will work in teams … --- ## [Attachements not available on https://agents-course-unit4-scoring.hf.space/docs#](https://discuss.huggingface.co/t/attachements-not-available-on-https-agents-course-unit4-scoring-hf-space-docs/171219)
**Author:** [@vsaez](https://discuss.huggingface.co/u/vsaez)\ **Replies:** 3\ **Last updated:** [July 12, 2026, 3:46am UTC](https://discuss.huggingface.co/t/attachements-not-available-on-https-agents-course-unit4-scoring-hf-space-docs/171219 "2026-07-12T03:46:08Z")
Hi! :waving\_hand: I’m currently working on the GAIA evaluation agent, and I’ve run into an issue with the task attachments (images, audio files, Python code, Excel sheets, etc.). According to the documentation, these f… --- ## [Create your own writing assistant](https://discuss.huggingface.co/t/create-your-own-writing-assistant/11568)
**Author:** [@lewtun](https://discuss.huggingface.co/u/lewtun)\ **Replies:** 18\ **Last updated:** [November 22, 2025, 12:47am UTC](https://discuss.huggingface.co/t/create-your-own-writing-assistant/11568 "2025-11-22T00:47:28Z")
:wave: Please read the topic category description to understand what this is all about Description Many email and word processing applications can now automatically detect and correct common grammatical errors as you … --- ## [Seeking Advice on Fine-Tuning a Legal Language Model for Nepalese Law (LLM + RAG)](https://discuss.huggingface.co/t/seeking-advice-on-fine-tuning-a-legal-language-model-for-nepalese-law-llm-rag/142935)
**Author:** [@sachindhital123](https://discuss.huggingface.co/u/sachindhital123)\ **Replies:** 3\ **Last updated:** [November 11, 2025, 10:27pm UTC](https://discuss.huggingface.co/t/seeking-advice-on-fine-tuning-a-legal-language-model-for-nepalese-law-llm-rag/142935 "2025-11-11T22:27:52Z")
Hi everyone, :waving\_hand: I’m working on building an AI-powered legal assistant focused on Nepalese law. My goal is to create a model that can provide legal advice by understanding and interpreting laws, acts, and judi… --- ## [Is there any agent that can search google](https://discuss.huggingface.co/t/is-there-any-agent-that-can-search-google/141016)
**Author:** [@Abdelkareem](https://discuss.huggingface.co/u/Abdelkareem)\ **Replies:** 2\ **Last updated:** [February 28, 2025, 10:40am UTC](https://discuss.huggingface.co/t/is-there-any-agent-that-can-search-google/141016 "2025-02-28T10:40:19Z")
I want to build a smolagent that can search the results of google search ? there is the google API search but i don’t want to use it’s limit is very bad to me. --- ## [Extracting and segmenting handwritten and printed text in the images](https://discuss.huggingface.co/t/extracting-and-segmenting-handwritten-and-printed-text-in-the-images/99536)
**Author:** [@itxsalman](https://discuss.huggingface.co/u/itxsalman)\ **Replies:** 1\ **Last updated:** [January 4, 2025, 1:31pm UTC](https://discuss.huggingface.co/t/extracting-and-segmenting-handwritten-and-printed-text-in-the-images/99536 "2025-01-04T13:31:35Z")
The project aim is to first segment (or draw Bounding box ) and classify the handwritten and printed text in the images and then extract handwritten and printed text from the images. The printed text can be extracted eas… --- ## [Create your own search engine](https://discuss.huggingface.co/t/create-your-own-search-engine/11575)
**Author:** [@lewtun](https://discuss.huggingface.co/u/lewtun)\ **Replies:** 11\ **Last updated:** [December 29, 2024, 3:53pm UTC](https://discuss.huggingface.co/t/create-your-own-search-engine/11575 "2024-12-29T15:53:58Z")
:wave: Please read the topic category description to understand what this is all about Create your own search engine In Chapter 5 of the :hugs: Course, you learned how to use FAISS to find documents that are most sema… --- ## [365 Data Science - Free Access](https://discuss.huggingface.co/t/365-data-science-free-access/115013)
**Author:** [@PeterTKD](https://discuss.huggingface.co/u/PeterTKD)\ **Replies:** 0\ **Last updated:** [November 1, 2024, 2:18pm UTC](https://discuss.huggingface.co/t/365-data-science-free-access/115013 "2024-11-01T14:18:45Z")
Just wanted to share a cool resource I found—365 Data Science is currently offering free 21-day access to all their courses. If you’re into machine learning, NLP, or working with large language models, this might be usef… --- ## [Create a multilingual classifier](https://discuss.huggingface.co/t/create-a-multilingual-classifier/11519)
**Author:** [@lewtun](https://discuss.huggingface.co/u/lewtun)\ **Replies:** 3\ **Last updated:** [October 22, 2024, 2:48pm UTC](https://discuss.huggingface.co/t/create-a-multilingual-classifier/11519 "2024-10-22T14:48:31Z")
:wave: Please read the topic category description to understand what this is all about Description Many countries have populations that speak and write in more than one language. Building NLP applications in these con… --- ## [Use OpenAI's CLIP for image search](https://discuss.huggingface.co/t/use-openais-clip-for-image-search/11577)
**Author:** [@lewtun](https://discuss.huggingface.co/u/lewtun)\ **Replies:** 21\ **Last updated:** [June 4, 2024, 4:45pm UTC](https://discuss.huggingface.co/t/use-openais-clip-for-image-search/11577 "2024-06-04T16:45:19Z")
:wave: Please read the topic category description to understand what this is all about Description One of the most exciting developments in 2021 was the release of OpenAI’s CLIP model, which was trained on a variety o… --- ## [Cloud Kitchen Set-up for Business](https://discuss.huggingface.co/t/cloud-kitchen-set-up-for-business/92578)
**Author:** [@creatureindustry](https://discuss.huggingface.co/u/creatureindustry)\ **Replies:** 0\ **Last updated:** [June 17, 2024, 12:53pm UTC](https://discuss.huggingface.co/t/cloud-kitchen-set-up-for-business/92578 "2024-06-17T12:53:46Z")
Transform your culinary dreams into reality with our comprehensive guide to launching a successful cloud kitchen. From legalities and equipment to menu planning and delivery logistics, we’ve got you covered. Start your j… --- ## [GPTSAN-japanese Summarisation](https://discuss.huggingface.co/t/gptsan-japanese-summarisation/85758)
**Author:** [@minkhantycc](https://discuss.huggingface.co/u/minkhantycc)\ **Replies:** 0\ **Last updated:** [May 8, 2024, 5:58am UTC](https://discuss.huggingface.co/t/gptsan-japanese-summarisation/85758 "2024-05-08T05:58:31Z")
Hi guys, I am trying to fine-tune GPTSAN model for summarisation task as explained in a blog post of huggingface. Please look here. The modifications I made are changing model re-define preprocessing step. def prepro… --- ## [Elasticsearch With Haystack -Initial connection to Elasticsearch failed](https://discuss.huggingface.co/t/elasticsearch-with-haystack-initial-connection-to-elasticsearch-failed/17510)
**Author:** [@sh-rashtchi](https://discuss.huggingface.co/u/sh-rashtchi)\ **Replies:** 3\ **Last updated:** [April 15, 2024, 11:40am UTC](https://discuss.huggingface.co/t/elasticsearch-with-haystack-initial-connection-to-elasticsearch-failed/17510 "2024-04-15T11:40:14Z")
Hi I am trying to run Chapter 7 to learn about Haystack for QA: I am using Jupyter Notebook which is connected to my GCP VM : Debian GNU/Linux 9, Tesla V100 I did install debian version but facing the following error… --- ## [LLM, CNN and SDRs](https://discuss.huggingface.co/t/llm-cnn-and-sdrs/75577)
**Author:** [@aquahood](https://discuss.huggingface.co/u/aquahood)\ **Replies:** 0\ **Last updated:** [March 2, 2024, 9:19am UTC](https://discuss.huggingface.co/t/llm-cnn-and-sdrs/75577 "2024-03-02T09:19:07Z")
I would like to combine a e.e. dataset (I have 400 advanced electrical engineering and radio engineering, and space vehicle engineering textbooks I would like to integrate into a knowledge based), then add all the liter… --- ## [Use EncoderDecoder models for text summarization](https://discuss.huggingface.co/t/use-encoderdecoder-models-for-text-summarization/11525)
**Author:** [@lewtun](https://discuss.huggingface.co/u/lewtun)\ **Replies:** 3\ **Last updated:** [December 28, 2023, 12:00pm UTC](https://discuss.huggingface.co/t/use-encoderdecoder-models-for-text-summarization/11525 "2023-12-28T12:00:31Z")
:wave: Please read the topic category description to understand what this is all about Description Most of the available Transformer models for text summarization are only available for English documents. At the same … --- ## [Build a question answering system in your own language](https://discuss.huggingface.co/t/build-a-question-answering-system-in-your-own-language/11570)
**Author:** [@lewtun](https://discuss.huggingface.co/u/lewtun)\ **Replies:** 14\ **Last updated:** [December 28, 2023, 8:14am UTC](https://discuss.huggingface.co/t/build-a-question-answering-system-in-your-own-language/11570 "2023-12-28T08:14:15Z")
:wave: Please read the topic category description to understand what this is all about Description One of the major challenges with NLP today is the lack of systems for the thousands of non-English languages in the wo… --- ## [AI Content Detection Tool](https://discuss.huggingface.co/t/ai-content-detection-tool/54112)
**Author:** [@Samarjeet-singh-chha](https://discuss.huggingface.co/u/Samarjeet-singh-chha)\ **Replies:** 1\ **Last updated:** [December 25, 2023, 2:16pm UTC](https://discuss.huggingface.co/t/ai-content-detection-tool/54112 "2023-12-25T14:16:32Z")
I am working on a AI content detection tool, where the tool takes an input and tells how much percentage of input is human written. Like orignality.ai similar tool, help me how to train such a model for best accuracy, b… --- ## [Generate Vector Graphics (Icons, ...) as SVG](https://discuss.huggingface.co/t/generate-vector-graphics-icons-as-svg/37690)
**Author:** [@kgoedecke](https://discuss.huggingface.co/u/kgoedecke)\ **Replies:** 0\ **Last updated:** [April 25, 2023, 1:54pm UTC](https://discuss.huggingface.co/t/generate-vector-graphics-icons-as-svg/37690 "2023-04-25T13:54:55Z")
I’d be really interested in working on this. Has this been looked into yet, what are the unique challenges? --- ## [Generate your own TV shows](https://discuss.huggingface.co/t/generate-your-own-tv-shows/11511)
**Author:** [@lewtun](https://discuss.huggingface.co/u/lewtun)\ **Replies:** 2\ **Last updated:** [April 18, 2023, 10:43am UTC](https://discuss.huggingface.co/t/generate-your-own-tv-shows/11511 "2023-04-18T10:43:48Z")
:wave: Please read the topic category description to understand what this is all about Description Fine-tune an autoregressive Transformer model on the transcripts of your favourite TV show to generate new episodes! M… --- ## [Project: Create a new zero-shot model with NLI data](https://discuss.huggingface.co/t/project-create-a-new-zero-shot-model-with-nli-data/11858)
**Author:** [@MoritzLaurer](https://discuss.huggingface.co/u/MoritzLaurer)\ **Replies:** 9\ **Last updated:** [April 11, 2023, 7:47am UTC](https://discuss.huggingface.co/t/project-create-a-new-zero-shot-model-with-nli-data/11858 "2023-04-11T07:47:22Z")
Description The zero-shot classification pipeline has becomes very popular on Hugging Face. It allows you to classify a text in any category without having to fine-tune a model for the specific classification task you ar… --- ## [Where did eval\_preds in compute\_metrics function come from?](https://discuss.huggingface.co/t/where-did-eval-preds-in-compute-metrics-function-come-from/35292)
**Author:** [@soujanna](https://discuss.huggingface.co/u/soujanna)\ **Replies:** 0\ **Last updated:** [April 2, 2023, 3:38am UTC](https://discuss.huggingface.co/t/where-did-eval-preds-in-compute-metrics-function-come-from/35292 "2023-04-02T03:38:04Z")
In Chapter 3 of the Huggingface NLP course, Section Fine Tuning a Model with the Trainer API, I see this concise function, which calls eval\_preds: def compute\_metrics(eval\_preds): metric = evaluate.load(“glue”, “mrpc”) … --- ## [Build a Twitter topic extractor](https://discuss.huggingface.co/t/build-a-twitter-topic-extractor/11571)
**Author:** [@lewtun](https://discuss.huggingface.co/u/lewtun)\ **Replies:** 7\ **Last updated:** [March 7, 2023, 1:43pm UTC](https://discuss.huggingface.co/t/build-a-twitter-topic-extractor/11571 "2023-03-07T13:43:00Z")
:wave: Please read the topic category description to understand what this is all about Description Twitter classifies trending tweets according to predefined set of topics like “Data science”, “Hip hop”, “Sport” etc. … --- ## [Create an AI assistant for lawyers](https://discuss.huggingface.co/t/create-an-ai-assistant-for-lawyers/11512)
**Author:** [@lewtun](https://discuss.huggingface.co/u/lewtun)\ **Replies:** 12\ **Last updated:** [February 21, 2023, 4:12am UTC](https://discuss.huggingface.co/t/create-an-ai-assistant-for-lawyers/11512 "2023-02-21T04:12:59Z")
:wave: Please read the topic category description to understand what this is all about Description The Contract Understanding Atticus Dataset (CUAD) is a new dataset for legal contract review. Legal contracts often co… --- ## [Image captioning for low resource Indian Languages](https://discuss.huggingface.co/t/image-captioning-for-low-resource-indian-languages/11764)
**Author:** [@seanbenhur](https://discuss.huggingface.co/u/seanbenhur)\ **Replies:** 3\ **Last updated:** [December 20, 2022, 2:16pm UTC](https://discuss.huggingface.co/t/image-captioning-for-low-resource-indian-languages/11764 "2022-12-20T14:16:42Z")
There are many image captioning systems exist for english language, here in this project we will develop an Image captioning system for an Indian language If we have time and resource, we can extend this to other langua… --- ## [Build a cover letter generator](https://discuss.huggingface.co/t/build-a-cover-letter-generator/11721)
**Author:** [@nouamanetazi](https://discuss.huggingface.co/u/nouamanetazi)\ **Replies:** 6\ **Last updated:** [October 28, 2022, 9:02pm UTC](https://discuss.huggingface.co/t/build-a-cover-letter-generator/11721 "2022-10-28T21:02:40Z")
Description Sometimes students spend more time working on their cover letters, customizing them for each company, than working on their portfolio. And the preliminary screening steps that are based only on cover letters … --- ## [Great Home Improvement Tools For Your iPhone Or iTouc](https://discuss.huggingface.co/t/great-home-improvement-tools-for-your-iphone-or-itouc/23630)
**Author:** [@ToniPhilpps](https://discuss.huggingface.co/u/ToniPhilpps)\ **Replies:** 0\ **Last updated:** [September 26, 2022, 11:10am UTC](https://discuss.huggingface.co/t/great-home-improvement-tools-for-your-iphone-or-itouc/23630 "2022-09-26T11:10:01Z")
It also has tools and features that you can use in creating bullet lists, aligning paragraphs, adjusting indentation and doing other extensive formatting tasks. There is also an auto save and auto-correct feature. https… --- ## [Build a language detector](https://discuss.huggingface.co/t/build-a-language-detector/11520)
**Author:** [@lewtun](https://discuss.huggingface.co/u/lewtun)\ **Replies:** 12\ **Last updated:** [January 26, 2022, 10:44am UTC](https://discuss.huggingface.co/t/build-a-language-detector/11520 "2022-01-26T10:44:27Z")
:wave: Please read the topic category description to understand what this is all about Description For many online applications it is not known in advance what language an end-user will communicate in. The goal of thi… --- ## [Build a news summarizer](https://discuss.huggingface.co/t/build-a-news-summarizer/11572)
**Author:** [@lewtun](https://discuss.huggingface.co/u/lewtun)\ **Replies:** 7\ **Last updated:** [November 19, 2021, 5:23am UTC](https://discuss.huggingface.co/t/build-a-news-summarizer/11572 "2021-11-19T05:23:13Z")
Description A common data science task for many business is to be able to condense the news about their products or services into short summaries. The goal of this task is to fine-tune a model to automatically summarise … --- ## [Poster2Plot: Generate Movie/T.V show plot from poster](https://discuss.huggingface.co/t/poster2plot-generate-movie-t-v-show-plot-from-poster/12132)
**Author:** [@dsr](https://discuss.huggingface.co/u/dsr)\ **Replies:** 5\ **Last updated:** [November 24, 2021, 3:38am UTC](https://discuss.huggingface.co/t/poster2plot-generate-movie-t-v-show-plot-from-poster/12132 "2021-11-24T03:38:50Z")
Description Our team is working on building an image captioning model which can generate a movie/t.v show plot from it’s poster. The goal of this project is to create an image captioning model using a transformer encode… --- ## [Build a title recommender for scientific articles](https://discuss.huggingface.co/t/build-a-title-recommender-for-scientific-articles/11522)
**Author:** [@lewtun](https://discuss.huggingface.co/u/lewtun)\ **Replies:** 20\ **Last updated:** [November 22, 2021, 10:26pm UTC](https://discuss.huggingface.co/t/build-a-title-recommender-for-scientific-articles/11522 "2021-11-22T22:26:00Z")
:wave: Please read the topic category description to understand what this is all about Description If you’ve ever worked in research, then you know that picking a catchy title for your articles is not easy! In this pr… [Next page](https://discuss.huggingface.co/c/course/course-event/25.md?page=1)