Grab your coffee. Here are this week’s highlights.
📅 Today’s Picks
Convert Chart Images to CSV with IBM Granite Vision
Problem
Chart data often contains valuable insights, but extracting numbers from these charts manually is time-consuming and tedious.
Solution
IBM’s Granite Vision 3.3 2B converts chart images directly into structured CSV data using Hugging Face Transformers.
Here’s how to extract structured data from any chart image in three steps.
1. Load the Model
Load the chart-to-CSV model from HuggingFace using the transformers library.
<span class="kn">from</span><span class="w"> </span><span class="nn">transformers</span><span class="w"> </span><span class="kn">import</span> <span class="n">AutoProcessor</span><span class="p">,</span> <span class="n">AutoModelForVision2Seq</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">huggingface_hub</span><span class="w"> </span><span class="kn">import</span> <span class="n">hf_hub_download</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">PIL</span><span class="w"> </span><span class="kn">import</span> <span class="n">Image</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">torch</span>
<span class="n">model_path</span> <span class="o">=</span> <span class="s2">"ibm-granite/granite-vision-3.3-2b-chart2csv-preview"</span>
<span class="n">device</span> <span class="o">=</span> <span class="s2">"cuda"</span> <span class="k">if</span> <span class="n">torch</span><span class="o">.</span><span class="n">cuda</span><span class="o">.</span><span class="n">is_available</span><span class="p">()</span> <span class="k">else</span> <span class="s2">"cpu"</span>
<span class="n">processor</span> <span class="o">=</span> <span class="n">AutoProcessor</span><span class="o">.</span><span class="n">from_pretrained</span><span class="p">(</span><span class="n">model_path</span><span class="p">)</span>
<span class="n">model</span> <span class="o">=</span> <span class="n">AutoModelForVision2Seq</span><span class="o">.</span><span class="n">from_pretrained</span><span class="p">(</span><span class="n">model_path</span><span class="p">)</span><span class="o">.</span><span class="n">to</span><span class="p">(</span><span class="n">device</span><span class="p">)</span>
2. Prepare Your Chart
Define the chart image and task instruction in a conversation format.
<span class="c1"># Load a chart image</span>
<span class="n">img_path</span> <span class="o">=</span> <span class="n">hf_hub_download</span><span class="p">(</span>
<span class="n">repo_id</span><span class="o">=</span><span class="n">model_path</span><span class="p">,</span> <span class="n">filename</span><span class="o">=</span><span class="s2">"example.jpg"</span>
<span class="p">)</span>
<span class="n">img</span> <span class="o">=</span> <span class="n">Image</span><span class="o">.</span><span class="n">open</span><span class="p">(</span><span class="n">img_path</span><span class="p">)</span>
<span class="c1"># Use the chart-to-CSV prompt</span>
<span class="n">conversation</span> <span class="o">=</span> <span class="p">[</span>
<span class="p">{</span><span class="s2">"role"</span><span class="p">:</span> <span class="s2">"user"</span><span class="p">,</span> <span class="s2">"content"</span><span class="p">:</span> <span class="p">[</span>
<span class="p">{</span><span class="s2">"type"</span><span class="p">:</span> <span class="s2">"image"</span><span class="p">,</span> <span class="s2">"url"</span><span class="p">:</span> <span class="n">img_path</span><span class="p">},</span>
<span class="p">{</span><span class="s2">"type"</span><span class="p">:</span> <span class="s2">"text"</span><span class="p">,</span> <span class="s2">"text"</span><span class="p">:</span> <span class="s2">"Parse the chart in the image to CSV format."</span><span class="p">}</span>
<span class="p">]}</span>
<span class="p">]</span>
3. Generate CSV Output
Apply the chat template, generate tokens, and decode back to CSV text.
<span class="n">inputs</span> <span class="o">=</span> <span class="n">processor</span><span class="o">.</span><span class="n">apply_chat_template</span><span class="p">(</span>
<span class="n">conversation</span><span class="p">,</span>
<span class="n">add_generation_prompt</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
<span class="n">tokenize</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
<span class="n">return_dict</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
<span class="n">return_tensors</span><span class="o">=</span><span class="s2">"pt"</span>
<span class="p">)</span><span class="o">.</span><span class="n">to</span><span class="p">(</span><span class="n">device</span><span class="p">)</span>
<span class="n">output</span> <span class="o">=</span> <span class="n">model</span><span class="o">.</span><span class="n">generate</span><span class="p">(</span><span class="o">**</span><span class="n">inputs</span><span class="p">,</span> <span class="n">max_new_tokens</span><span class="o">=</span><span class="mi">500</span><span class="p">)</span>
<span class="n">csv_output</span> <span class="o">=</span> <span class="n">processor</span><span class="o">.</span><span class="n">decode</span><span class="p">(</span><span class="n">output</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">skip_special_tokens</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
<span class="nb">print</span><span class="p">(</span><span class="n">csv_output</span><span class="p">)</span>
Output:
State,2017,2018
NJ,4.6,4.1
CT,4.7,4.1
DE,4.5,3.8
NY,4.7,4.1
PA,4.9,4.3
PydanticAI: Control OpenAI Data Retention with openai_store
Problem
By default, OpenAI may retain your API request data for internal review and model improvement. For healthcare, finance, and legal applications, this default creates compliance risks you can’t afford.
Solution
PydanticAI v1.52.0 introduces the openai_store setting to explicitly disable data retention in one line.
☕️ Weekly Finds
msgvault [Data Management] – Archive a lifetime of email and chat locally with full Gmail backup, search, DuckDB-powered analytics, an interactive TUI, and an MCP server for querying messages with AI
monty [Developer Tools] – Minimal, secure Python interpreter written in Rust designed for use by AI agents, providing sandboxed code execution with safety guarantees
baserow [No-Code Platform] – Open-source no-code platform for building databases, applications, automations, and AI agents with enterprise-grade security and self-hosted deployment options
Looking for a specific tool? Explore 70+ Python tools →
Stay Current with CodeCut
Actionable Python tips, curated for busy data pros. Skim in under 2 minutes, three times a week.
