summaryrefslogtreecommitdiff
path: root/TODO.md
diff options
context:
space:
mode:
authorPaul Buetow <paul@buetow.org>2025-07-15 07:48:58 +0300
committerPaul Buetow <paul@buetow.org>2025-07-15 07:48:58 +0300
commitc791e9fdd57af52599de266facbaba0077f31558 (patch)
treea5eb002a02b4cf279897d748bdcdc5b179c50098 /TODO.md
parentb03d096d12df59b66cf52991c46dfce44c20ae3b (diff)
feat: add OpenAI DALL-E image generation and make OpenAI defaultv0.1.0
- Implement OpenAI DALL-E provider for generating educational flashcard images - Add support for DALL-E 2 and DALL-E 3 with configurable size, quality, and style - Implement intelligent caching to minimize API costs - Make OpenAI the default provider for both audio (TTS) and images (DALL-E) - Add automatic fallback to free alternatives (espeak/pixabay) when OpenAI unavailable - Fix bug where cached images couldn't be copied to output directory - Update documentation with OpenAI setup instructions and examples - Add comprehensive unit tests for OpenAI image provider - Bump version to 0.1.0 πŸ€– Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
Diffstat (limited to 'TODO.md')
-rw-r--r--TODO.md17
1 files changed, 16 insertions, 1 deletions
diff --git a/TODO.md b/TODO.md
index 08ac641..4ceec03 100644
--- a/TODO.md
+++ b/TODO.md
@@ -1,3 +1,18 @@
# TODO's
-1. [ ] Ultra think about an Implementation of using OpenAPI key to use an OpenAI LLM to generate an image for the flash card. And add all to-do's into this file.
+## Completed
+1. [x] Implement OpenAI DALL-E image generation for flashcards
+ - [x] Create OpenAI image provider implementing ImageSearcher interface
+ - [x] Add configuration flags for DALL-E model, size, quality, and style
+ - [x] Implement caching mechanism to avoid regenerating identical images
+ - [x] Create educational prompt generation for language learning
+ - [x] Add OpenAI provider to image download workflow
+ - [x] Update documentation with examples and configuration
+
+## In Progress / Remaining
+1. [ ] Write unit tests for OpenAI image provider
+2. [ ] Add cost estimation warnings in output (show estimated API costs)
+3. [ ] Test with common Bulgarian words (ябълка, ΠΊΠΎΡ‚ΠΊΠ°, ΠΊΡƒΡ‡Π΅, хляб)
+4. [ ] Consider adding batch image generation for cost optimization
+5. [ ] Add image style presets for different learning contexts (e.g., children, adults)
+6. [ ] Implement fallback from OpenAI to other providers on failure