16
Captionate
πΈ
Generate Instagram captions from images
Bilge YΓΌcel
bilgeyucel
AI & ML interests
NLP, Semantic Search, LLMs
Recent Activity
updated
a Space
about 1 month ago
bilgeyucel/captionate
upvoted
an
article
about 2 months ago
Introducing Trackio: A Lightweight Experiment Tracking Library from Hugging Face
liked
a model
2 months ago
google/embeddinggemma-300m
Organizations
updated
a
Space
about 1 month ago
upvoted
an
article
about 2 months ago
Article
Introducing Trackio: A Lightweight Experiment Tracking Library from Hugging Face
β’
191
liked
a
model
2 months ago
upvoted
an
article
2 months ago
Article
Welcome EmbeddingGemma, Google's new efficient embedding model
β’
253
reacted to
anakin87's
post with β€οΈ
3 months ago
Post
1087
Haystack can now see π
The latest release of the Haystack OSS LLM framework adds a long-requested feature: image support!
π Notebooks below
This isn't just about passing images to an LLM. We built several features to enable practical multimodal use cases.
What's new?
π§ Support for multiple LLM providers: OpenAI, Amazon Bedrock, Google Gemini, Mistral, NVIDIA, OpenRouter, Ollama and more (support for Hugging Face API coming π)
ποΈ Prompt template language to handle structured inputs, including images
π PDF and image converters
π Image embedders using CLIP-like models
π§Ύ LLM-based extractor to pull text from images
𧩠Components to build multimodal RAG pipelines and Agents
I had the chance of leading this effort with @sjrhuschlee (great collab).
π Below you can find two notebooks to explore the new features:
σ ―β’σ σ Introduction to Multimodal Text Generation https://haystack.deepset.ai/cookbook/multimodal_intro
σ ―β’σ σ Creating Vision+Text RAG Pipelines https://haystack.deepset.ai/tutorials/46_multimodal_rag
(πΌοΈ image by @bilgeyucel )
The latest release of the Haystack OSS LLM framework adds a long-requested feature: image support!
π Notebooks below
This isn't just about passing images to an LLM. We built several features to enable practical multimodal use cases.
What's new?
π§ Support for multiple LLM providers: OpenAI, Amazon Bedrock, Google Gemini, Mistral, NVIDIA, OpenRouter, Ollama and more (support for Hugging Face API coming π)
ποΈ Prompt template language to handle structured inputs, including images
π PDF and image converters
π Image embedders using CLIP-like models
π§Ύ LLM-based extractor to pull text from images
𧩠Components to build multimodal RAG pipelines and Agents
I had the chance of leading this effort with @sjrhuschlee (great collab).
π Below you can find two notebooks to explore the new features:
σ ―β’σ σ Introduction to Multimodal Text Generation https://haystack.deepset.ai/cookbook/multimodal_intro
σ ―β’σ σ Creating Vision+Text RAG Pipelines https://haystack.deepset.ai/tutorials/46_multimodal_rag
(πΌοΈ image by @bilgeyucel )
reacted to
anakin87's
post with π₯
3 months ago
Post
388
π΅οΈπ Building Browser Agents - notebook
No API? No problem.
Browser Agents can use websites like you do: click, type, wait, read.
π Step-by-step notebook: https://colab.research.google.com/github/deepset-ai/haystack-cookbook/blob/main/notebooks/browser_agents.ipynb
π₯ In the video, the Agent:
- Goes to Hugging Face Spaces
- Finds black-forest-labs/FLUX.1-schnell
- Expands a short prompt ("my holiday on Lake Como") into a detailed image generation prompt
- Waits for the image
- Returns the image URL
## What else can it do?
Great for information gathering and summarization
ποΈποΈ Compare news websites and create a table of shared stories with links
βΆοΈ Find content creator social profiles from YouTube videos
ποΈ Find a product's price range on Amazon
π π Gather public transportation travel options
## How is it built?
ποΈ Haystack β Agent execution logic
π§ Google Gemini 2.5 Flash β Good and fast LLM with a generous free tier
π οΈ Playwright MCP server β Browser automation tools: navigate, click, type, wait...
Even without vision capabilities, this setup can get quite far.
## Next steps
- Try a local open model
- Move from notebook to real deployment
- Incorporate vision
And you? Have you built something similar? What's in your stack?
No API? No problem.
Browser Agents can use websites like you do: click, type, wait, read.
π Step-by-step notebook: https://colab.research.google.com/github/deepset-ai/haystack-cookbook/blob/main/notebooks/browser_agents.ipynb
π₯ In the video, the Agent:
- Goes to Hugging Face Spaces
- Finds black-forest-labs/FLUX.1-schnell
- Expands a short prompt ("my holiday on Lake Como") into a detailed image generation prompt
- Waits for the image
- Returns the image URL
## What else can it do?
Great for information gathering and summarization
ποΈποΈ Compare news websites and create a table of shared stories with links
βΆοΈ Find content creator social profiles from YouTube videos
ποΈ Find a product's price range on Amazon
π π Gather public transportation travel options
## How is it built?
ποΈ Haystack β Agent execution logic
π§ Google Gemini 2.5 Flash β Good and fast LLM with a generous free tier
π οΈ Playwright MCP server β Browser automation tools: navigate, click, type, wait...
Even without vision capabilities, this setup can get quite far.
## Next steps
- Try a local open model
- Move from notebook to real deployment
- Incorporate vision
And you? Have you built something similar? What's in your stack?
liked
a
model
4 months ago
liked
a
dataset
4 months ago
liked
a
model
10 months ago
liked
a
model
12 months ago
reacted to
alielfilali01's
post with π
about 1 year ago
Post
1773
I feel like this incredible resource hasn't gotten the attention it deserves in the community!
@clefourrier and generally the HuggingFace evaluation team put together a fantastic guidebook covering a lot about ππ©πππ¨ππ§ππ’π‘ from basics to advanced tips.
link : https://github.com/huggingface/evaluation-guidebook
I havenβt finished it yet, but i'am enjoying every piece of it so far. Huge thanks @clefourrier and the team for this invaluable resource !
@clefourrier and generally the HuggingFace evaluation team put together a fantastic guidebook covering a lot about ππ©πππ¨ππ§ππ’π‘ from basics to advanced tips.
link : https://github.com/huggingface/evaluation-guidebook
I havenβt finished it yet, but i'am enjoying every piece of it so far. Huge thanks @clefourrier and the team for this invaluable resource !
- 3 replies
liked
2
datasets
about 1 year ago
liked
a
Space
about 1 year ago
liked
a
model
over 1 year ago
upvoted
an
article
over 1 year ago
Article
Mixedbread π€ deepset: Announcing our New German/English Embedding Model
By
β’
β’
15
liked
a
Space
over 1 year ago
upvoted
an
article
over 1 year ago
Article
CPU Optimized Embeddings with π€ Optimum Intel and fastRAG
β’
11
liked
a
Space
over 1 year ago
upvoted
an
article
over 1 year ago
Article
βοΈ π§πΌβπΎ Let's grow some Domain Specific Datasets together
By
β’
β’
29