WHG2023
commited on
Commit
·
4252b44
1
Parent(s):
87eec00
Enhanced Dual Output Features - Both descriptions AND LaTeX code + Multiple compilation options + Professional USPTO-ready vector graphics + Immediate understanding without compilation barriers
Browse files- .env +14 -0
- ENHANCED_DUAL_OUTPUT_FEATURES.md +356 -0
- __pycache__/gemini_image_generator.cpython-312.pyc +0 -0
- __pycache__/real_ai_agents_implementation.cpython-312.pyc +0 -0
- app.py +21 -7
- gemini_image_generator.py +353 -261
.env
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
GRADIO_API_KEY=your_gradio_api_key
|
2 |
+
MODAL_API_KEY=ak-MJz2rp4PN5L0wrja0ZU6C9
|
3 |
+
NEBIUS_API_KEY=eyJhbGciOiJIUzI1NiIsImtpZCI6IlV6SXJWd1h0dnprLVRvdzlLZWstc0M1akptWXBvX1VaVkxUZlpnMDRlOFUiLCJ0eXAiOiJKV1QifQ.eyJzdWIiOiJnb29nbGUtb2F1dGgyfDEwMTg3NzczODM4MjkyNTg5OTYyNSIsInNjb3BlIjoib3BlbmlkIG9mZmxpbmVfYWNjZXNzIiwiaXNzIjoiYXBpX2tleV9pc3N1ZXIiLCJhdWQiOlsiaHR0cHM6Ly9uZWJpdXMtaW5mZXJlbmNlLmV1LmF1dGgwLmNvbS9hcGkvdjIvIl0sImV4cCI6MTkwNzM1Nzk5MywidXVpZCI6ImVmNGMyYmI1LTU0ZWEtNDg3Yi04Mjc1LWNjZTU0NTlhMWJlMyIsIm5hbWUiOiJIYWNrMjAyNSIsImV4cGlyZXNfYXQiOiIyMDMwLTA2LTEwVDIxOjM5OjUzKzAwMDAifQ.jgNqVFRs3y88YVkTxTUkwtA0NXCBxtyTBz7mePnNbPM
|
4 |
+
ANTHROPIC_API_KEY=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
|
5 |
+
OPENAI_API_KEY=your_openai_api_key
|
6 |
+
HYPERBOLIC_API_KEY=your_hyperbolic_api_key
|
7 |
+
MISTRAL_API_KEY=your_mistral_api_key
|
8 |
+
SAMBANOVA_API_KEY=your_sambanova_api_key
|
9 |
+
OPENROUTER_API_KEY=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
|
10 |
+
PUBMED_API_KEY=c0c9587b298469a200bdd7f28bd0d4b02b08
|
11 |
+
MODAL_BACKEND_URL="https://gebhardt-wolfh--patent-architect-fastapi-app.modal.run"
|
12 |
+
GROQ_API_KEY="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"
|
13 |
+
TAVILY_API_KEY="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"
|
14 |
+
GEMINI_API_KEY="AIzaSyCQU-TsvYphz_gvJuOq2IagCsPOmE3_kTM"
|
ENHANCED_DUAL_OUTPUT_FEATURES.md
ADDED
@@ -0,0 +1,356 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# 🚀 Enhanced Dual Output Features for Patent Architect AI v2
|
2 |
+
|
3 |
+
## 🌟 Overview
|
4 |
+
|
5 |
+
Patent Architect AI v2 now features **Enhanced Dual Output** - a revolutionary approach that provides both detailed technical descriptions AND professional LaTeX/TikZ code for patent figures, with multiple compilation options including embedded web-based conversion.
|
6 |
+
|
7 |
+
## ✨ What's New
|
8 |
+
|
9 |
+
### **Before Enhancement:**
|
10 |
+
- ❌ Either text descriptions OR LaTeX code
|
11 |
+
- ❌ Limited viewing options
|
12 |
+
- ❌ Manual compilation required
|
13 |
+
- ❌ No immediate understanding
|
14 |
+
|
15 |
+
### **After Enhancement:**
|
16 |
+
- ✅ **Both detailed descriptions AND LaTeX code**
|
17 |
+
- ✅ **Multiple compilation options** (local, web-based, Overleaf)
|
18 |
+
- ✅ **Pre-compiled images** when possible
|
19 |
+
- ✅ **Immediate understanding** + professional quality
|
20 |
+
- ✅ **USPTO-ready output** with vector graphics
|
21 |
+
|
22 |
+
---
|
23 |
+
|
24 |
+
## 🎯 Key Features
|
25 |
+
|
26 |
+
### 1. **Dual Output Generation**
|
27 |
+
```python
|
28 |
+
result = generator.generate_dual_output_figure(
|
29 |
+
invention_description="Smart coffee mug...",
|
30 |
+
figure_type="technical_diagram"
|
31 |
+
)
|
32 |
+
|
33 |
+
# Returns:
|
34 |
+
# - Detailed technical description (readable immediately)
|
35 |
+
# - Professional LaTeX/TikZ code (compilation-ready)
|
36 |
+
# - Optional pre-compiled image
|
37 |
+
```
|
38 |
+
|
39 |
+
### 2. **Multiple Compilation Options**
|
40 |
+
|
41 |
+
#### **Option A: Pre-Compiled Images** 🖼️
|
42 |
+
- Automatic compilation when LaTeX tools available
|
43 |
+
- Both local and web-based compilation attempts
|
44 |
+
- Immediate viewing without additional steps
|
45 |
+
|
46 |
+
#### **Option B: Overleaf Integration** 🌐 (Recommended)
|
47 |
+
- Direct upload to Overleaf.com (free account)
|
48 |
+
- One-click compilation to professional PDF
|
49 |
+
- No software installation required
|
50 |
+
|
51 |
+
#### **Option C: Local Compilation** 💻
|
52 |
+
- Full LaTeX installation with TikZ package
|
53 |
+
- Command-line compilation for developers
|
54 |
+
- Maximum control and customization
|
55 |
+
|
56 |
+
#### **Option D: Web Preview** 📱
|
57 |
+
- LaTeX Live for quick previews
|
58 |
+
- Mobile-friendly viewing
|
59 |
+
- Instant code validation
|
60 |
+
|
61 |
+
### 3. **Enhanced User Experience**
|
62 |
+
|
63 |
+
#### **Immediate Understanding:**
|
64 |
+
```
|
65 |
+
📝 Technical Description Preview:
|
66 |
+
The smart coffee mug comprises a cylindrical vessel (1) with
|
67 |
+
an integrated phase-change material chamber (2) positioned
|
68 |
+
between the inner wall (3) and outer wall (4)...
|
69 |
+
```
|
70 |
+
|
71 |
+
#### **Professional LaTeX Code:**
|
72 |
+
```latex
|
73 |
+
\documentclass[12pt]{article}
|
74 |
+
\usepackage{tikz}
|
75 |
+
\begin{tikzpicture}[scale=1.2]
|
76 |
+
\draw[thick] (0,0) rectangle (4,6);
|
77 |
+
\node at (2,5.5) {1};
|
78 |
+
\draw[fill=blue!20] (0.5,1) rectangle (3.5,4);
|
79 |
+
\node at (2,2.5) {2};
|
80 |
+
...
|
81 |
+
\end{tikzpicture}
|
82 |
+
```
|
83 |
+
|
84 |
+
---
|
85 |
+
|
86 |
+
## 📊 Enhanced Integration with Patent Architect
|
87 |
+
|
88 |
+
### **New Output Format:**
|
89 |
+
|
90 |
+
```markdown
|
91 |
+
## 🎨 Enhanced Patent Figures with Dual Output
|
92 |
+
|
93 |
+
✨ Generated 3 complete figure sets with both detailed descriptions AND LaTeX/TikZ code
|
94 |
+
🖼️ 2/3 figures successfully compiled to images (1 local, 1 web compilation)
|
95 |
+
|
96 |
+
### Figure 1: Overall System Diagram
|
97 |
+
|
98 |
+
🖼️ Compiled Image: `patent_figure_technical_diagram_20241215_143022.png` (Local compilation)
|
99 |
+
|
100 |
+
📝 Technical Description:
|
101 |
+
The smart coffee mug system comprises a primary vessel with integrated temperature
|
102 |
+
control using phase-change materials...
|
103 |
+
|
104 |
+
🎨 LaTeX/TikZ Code: `patent_figure_technical_diagram_20241215_143022.tex`
|
105 |
+
|
106 |
+
🚀 Multiple Viewing Options:
|
107 |
+
|
108 |
+
1. ✅ Pre-Compiled Image Available: View in output folder
|
109 |
+
2. 🌐 Online Compilation (Easiest):
|
110 |
+
- Go to Overleaf.com (free account)
|
111 |
+
- Upload .tex file → Click 'Recompile'
|
112 |
+
3. 💻 Local Compilation: pdflatex filename.tex
|
113 |
+
4. 📱 Mobile/Quick View: LaTeX Live (latexlive.com)
|
114 |
+
```
|
115 |
+
|
116 |
+
### **Business Benefits:**
|
117 |
+
|
118 |
+
- **Immediate Understanding:** Users read descriptions right away
|
119 |
+
- **Professional Quality:** LaTeX creates publication-grade vector graphics
|
120 |
+
- **USPTO Preferred:** Vector graphics ideal for patent applications
|
121 |
+
- **Multiple Skill Levels:** Options for beginners and experts
|
122 |
+
- **Cost Effective:** No expensive software required
|
123 |
+
|
124 |
+
---
|
125 |
+
|
126 |
+
## 🔧 Technical Implementation
|
127 |
+
|
128 |
+
### **Web-Based LaTeX Compilation**
|
129 |
+
|
130 |
+
```python
|
131 |
+
def _compile_latex_via_web_api(self, latex_code: str, filename: str) -> Optional[str]:
|
132 |
+
"""Compile LaTeX using web-based APIs."""
|
133 |
+
api_url = "https://latex.vercel.app/api/v2"
|
134 |
+
|
135 |
+
payload = {
|
136 |
+
"code": latex_code,
|
137 |
+
"format": "png",
|
138 |
+
"quality": 300
|
139 |
+
}
|
140 |
+
|
141 |
+
response = requests.post(api_url, json=payload, timeout=30)
|
142 |
+
# Returns compiled PNG image
|
143 |
+
```
|
144 |
+
|
145 |
+
### **Enhanced Local Compilation**
|
146 |
+
|
147 |
+
```python
|
148 |
+
def _compile_latex_to_image(self, latex_filepath: str) -> Optional[str]:
|
149 |
+
"""Enhanced compilation with multiple fallback methods."""
|
150 |
+
|
151 |
+
# Try local compilation first
|
152 |
+
if self.latex_available:
|
153 |
+
# pdflatex compilation
|
154 |
+
# Multiple PDF→PNG conversion methods
|
155 |
+
|
156 |
+
# Fallback to web compilation
|
157 |
+
web_result = self._compile_latex_via_web_api(latex_code, filename)
|
158 |
+
return web_result
|
159 |
+
```
|
160 |
+
|
161 |
+
### **Dual Output Generation**
|
162 |
+
|
163 |
+
```python
|
164 |
+
def generate_dual_output_figure(self, invention_description: str) -> Dict:
|
165 |
+
"""Generate both description AND LaTeX code."""
|
166 |
+
|
167 |
+
# Step 1: Generate detailed text description
|
168 |
+
text_response = self.model.generate_content([text_prompt])
|
169 |
+
detailed_description = text_response.text
|
170 |
+
|
171 |
+
# Step 2: Generate LaTeX/TikZ code
|
172 |
+
latex_response = self.model.generate_content([latex_prompt])
|
173 |
+
latex_code = latex_response.text
|
174 |
+
|
175 |
+
# Step 3: Try compilation
|
176 |
+
compiled_image_path = self._compile_latex_to_image(latex_filepath)
|
177 |
+
|
178 |
+
return {
|
179 |
+
"text_description": detailed_description,
|
180 |
+
"latex_code": latex_code,
|
181 |
+
"compiled_image_path": compiled_image_path,
|
182 |
+
# ... enhanced metadata
|
183 |
+
}
|
184 |
+
```
|
185 |
+
|
186 |
+
---
|
187 |
+
|
188 |
+
## 🎯 Usage Examples
|
189 |
+
|
190 |
+
### **Example 1: Basic Dual Output**
|
191 |
+
|
192 |
+
```python
|
193 |
+
from gemini_image_generator import GeminiImageGenerator
|
194 |
+
|
195 |
+
generator = GeminiImageGenerator()
|
196 |
+
|
197 |
+
result = generator.generate_dual_output_figure(
|
198 |
+
"A smart coffee mug with temperature control",
|
199 |
+
"technical_diagram"
|
200 |
+
)
|
201 |
+
|
202 |
+
if result["success"]:
|
203 |
+
print("📝 Description:", result["text_description"])
|
204 |
+
print("🎨 LaTeX Code:", result["latex_code"][:200] + "...")
|
205 |
+
if result["compiled_image_path"]:
|
206 |
+
print("🖼️ Image:", result["compiled_image_path"])
|
207 |
+
```
|
208 |
+
|
209 |
+
### **Example 2: Patent Architect Integration**
|
210 |
+
|
211 |
+
```python
|
212 |
+
# This happens automatically in Patent Architect
|
213 |
+
integration_result = generator.integrate_with_patent_architect(
|
214 |
+
"Modular vertical farming system with adaptive LED lighting"
|
215 |
+
)
|
216 |
+
|
217 |
+
# Returns enhanced content with:
|
218 |
+
# - Multiple figure descriptions
|
219 |
+
# - Multiple LaTeX code sets
|
220 |
+
# - Compilation statistics
|
221 |
+
# - User guidance
|
222 |
+
```
|
223 |
+
|
224 |
+
### **Example 3: Custom Compilation**
|
225 |
+
|
226 |
+
```python
|
227 |
+
# Generate without compilation
|
228 |
+
result = generator.generate_dual_output_figure(invention, figure_type)
|
229 |
+
|
230 |
+
# Then compile manually with different options
|
231 |
+
if result["latex_code"]:
|
232 |
+
# Option 1: Try web compilation
|
233 |
+
web_image = generator._compile_latex_via_web_api(
|
234 |
+
result["latex_code"],
|
235 |
+
"custom_figure"
|
236 |
+
)
|
237 |
+
|
238 |
+
# Option 2: Save for Overleaf
|
239 |
+
with open("for_overleaf.tex", "w") as f:
|
240 |
+
f.write(result["latex_code"])
|
241 |
+
```
|
242 |
+
|
243 |
+
---
|
244 |
+
|
245 |
+
## 📋 File Structure
|
246 |
+
|
247 |
+
### **Enhanced Output Files:**
|
248 |
+
|
249 |
+
```
|
250 |
+
patent_architect_figures/
|
251 |
+
├── patent_figure_technical_diagram_20241215_143022_description.txt
|
252 |
+
├── patent_figure_technical_diagram_20241215_143022.tex
|
253 |
+
├── patent_figure_technical_diagram_20241215_143022.png (if compiled)
|
254 |
+
├── patent_figure_cross_section_20241215_143045_description.txt
|
255 |
+
├── patent_figure_cross_section_20241215_143045.tex
|
256 |
+
└── patent_figure_cross_section_20241215_143045.pdf (if compiled)
|
257 |
+
```
|
258 |
+
|
259 |
+
### **File Categories:**
|
260 |
+
- **📝 Description Files:** `*_description.txt` - Immediate reading
|
261 |
+
- **🎨 LaTeX Files:** `*.tex` - Professional compilation
|
262 |
+
- **🖼️ Image Files:** `*.png`, `*.pdf` - Ready-to-use visuals
|
263 |
+
|
264 |
+
---
|
265 |
+
|
266 |
+
## 🏆 Advantages Over Traditional Approaches
|
267 |
+
|
268 |
+
### **Compared to Image-Only Generation:**
|
269 |
+
- ✅ **Immediate understanding** without compilation
|
270 |
+
- ✅ **Editable vector graphics** instead of fixed pixels
|
271 |
+
- ✅ **Multiple viewing options** for different skill levels
|
272 |
+
- ✅ **Professional quality** suitable for USPTO submission
|
273 |
+
|
274 |
+
### **Compared to LaTeX-Only Generation:**
|
275 |
+
- ✅ **No technical barrier** - read descriptions immediately
|
276 |
+
- ✅ **User-friendly** for non-LaTeX users
|
277 |
+
- ✅ **Multiple compilation paths** including web-based
|
278 |
+
- ✅ **Gradual learning** from descriptions to code
|
279 |
+
|
280 |
+
### **Compared to Description-Only Generation:**
|
281 |
+
- ✅ **Professional output** ready for patent submission
|
282 |
+
- ✅ **Vector graphics** with infinite scaling
|
283 |
+
- ✅ **Industry standard** LaTeX format
|
284 |
+
- ✅ **Customizable** for specific requirements
|
285 |
+
|
286 |
+
---
|
287 |
+
|
288 |
+
## 🚀 Getting Started
|
289 |
+
|
290 |
+
### **1. Quick Test:**
|
291 |
+
```bash
|
292 |
+
python test_latex_visualization.py
|
293 |
+
```
|
294 |
+
|
295 |
+
### **2. Patent Architect Integration:**
|
296 |
+
```bash
|
297 |
+
python app.py
|
298 |
+
# Then input: "Smart coffee mug with temperature control"
|
299 |
+
```
|
300 |
+
|
301 |
+
### **3. Direct API Usage:**
|
302 |
+
```python
|
303 |
+
from gemini_image_generator import GeminiImageGenerator
|
304 |
+
|
305 |
+
generator = GeminiImageGenerator()
|
306 |
+
result = generator.integrate_with_patent_architect("Your invention here")
|
307 |
+
print(result["content"])
|
308 |
+
```
|
309 |
+
|
310 |
+
---
|
311 |
+
|
312 |
+
## 🎯 Best Practices
|
313 |
+
|
314 |
+
### **For Immediate Use:**
|
315 |
+
1. **Read the generated descriptions** for instant understanding
|
316 |
+
2. **Check for pre-compiled images** in the output folder
|
317 |
+
3. **Use descriptions for patent applications** when images aren't needed
|
318 |
+
|
319 |
+
### **For Professional Quality:**
|
320 |
+
1. **Upload LaTeX to Overleaf.com** for best results
|
321 |
+
2. **Compile to PDF** for USPTO submission
|
322 |
+
3. **Edit LaTeX code** for custom adjustments
|
323 |
+
|
324 |
+
### **For Developers:**
|
325 |
+
1. **Install local LaTeX** for fastest compilation
|
326 |
+
2. **Use command-line tools** for batch processing
|
327 |
+
3. **Modify generation prompts** for specific requirements
|
328 |
+
|
329 |
+
---
|
330 |
+
|
331 |
+
## 🔮 Future Enhancements
|
332 |
+
|
333 |
+
### **Planned Features:**
|
334 |
+
- 🔄 **Interactive editing** of LaTeX code in browser
|
335 |
+
- 🎨 **Style templates** for different patent offices
|
336 |
+
- 📱 **Mobile app** for viewing and compilation
|
337 |
+
- 🤝 **Team collaboration** features
|
338 |
+
- 📊 **Analytics** on compilation success rates
|
339 |
+
|
340 |
+
### **API Improvements:**
|
341 |
+
- 🌐 **More web compilation services** for redundancy
|
342 |
+
- ⚡ **Faster compilation** with optimized APIs
|
343 |
+
- 🎯 **Custom templates** for specific industries
|
344 |
+
- 🔧 **Debugging tools** for LaTeX issues
|
345 |
+
|
346 |
+
---
|
347 |
+
|
348 |
+
## 🎉 Conclusion
|
349 |
+
|
350 |
+
The Enhanced Dual Output feature transforms Patent Architect AI v2 into a comprehensive patent figure generation platform that serves both technical and non-technical users. By providing both immediate understanding through descriptions AND professional quality through LaTeX code, with multiple compilation options, we've created the most user-friendly yet powerful patent figure system available.
|
351 |
+
|
352 |
+
**The result:** Users get immediate value while maintaining access to professional-grade output suitable for USPTO submission.
|
353 |
+
|
354 |
+
---
|
355 |
+
|
356 |
+
*Patent Architect AI v2 - Where Innovation Meets Intelligence* 🏆
|
__pycache__/gemini_image_generator.cpython-312.pyc
ADDED
Binary file (30.2 kB). View file
|
|
__pycache__/real_ai_agents_implementation.cpython-312.pyc
ADDED
Binary file (25 kB). View file
|
|
app.py
CHANGED
@@ -352,23 +352,37 @@ def format_patent_section(agent_name: str, content: str, thought: str = None, so
|
|
352 |
# COMPLETELY REPLACE the backend content with Gemini-generated content
|
353 |
content = gemini_result["content"]
|
354 |
|
355 |
-
# Check if we have
|
356 |
-
if gemini_result.get("
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
357 |
if gemini_result.get("latex_generated", 0) > 0:
|
358 |
content += "\n\n*🎨 Generated LaTeX/TikZ code using Google Gemini 2.0 Flash - Compile with pdflatex to create professional patent figures*\n\n"
|
359 |
content += f"*💡 To view images: Compile the .tex files in `{os.path.expanduser('~')}/patent_architect_figures/`*\n\n"
|
|
|
360 |
else:
|
361 |
content += "\n\n*🎨 Generated visual patent figures using Google Gemini 2.0 Flash - Professional images ready for USPTO submission*\n\n"
|
|
|
362 |
else:
|
363 |
content += "\n\n*📝 Generated detailed patent figure descriptions using Google Gemini 2.0 Flash - Professional technical specifications*\n\n"
|
|
|
364 |
|
365 |
print("✅ Gemini image generation successful - Backend content replaced")
|
366 |
|
367 |
-
# Update thought to reflect Gemini generation
|
368 |
-
if gemini_result.get("latex_generated", 0) > 0:
|
369 |
-
thought = "Generated professional LaTeX/TikZ code for patent figures using Google Gemini 2.0 Flash. Code can be compiled to create high-quality technical drawings with numbered components and USPTO-ready formatting."
|
370 |
-
else:
|
371 |
-
thought = "Generated high-quality patent figures using Google Gemini 2.0 Flash with professional technical drawings, numbered components, and USPTO-ready formatting."
|
372 |
else:
|
373 |
print(f"❌ Gemini generation failed: {gemini_result.get('error', 'Unknown error')}")
|
374 |
|
|
|
352 |
# COMPLETELY REPLACE the backend content with Gemini-generated content
|
353 |
content = gemini_result["content"]
|
354 |
|
355 |
+
# Check if we have dual output (descriptions + LaTeX)
|
356 |
+
if gemini_result.get("dual_output"):
|
357 |
+
# Enhanced dual output available
|
358 |
+
descriptions_available = gemini_result.get("descriptions_available", 0)
|
359 |
+
latex_available = gemini_result.get("latex_code_available", 0)
|
360 |
+
compiled_images = gemini_result.get("compiled_images", 0)
|
361 |
+
|
362 |
+
content += f"\n\n*🚀 Enhanced Dual Output: {descriptions_available} technical descriptions + {latex_available} LaTeX/TikZ code sets generated*\n\n"
|
363 |
+
|
364 |
+
if compiled_images > 0:
|
365 |
+
content += f"*🖼️ {compiled_images} figures successfully compiled to images - View immediately in output folder*\n\n"
|
366 |
+
|
367 |
+
content += f"*💡 Best Experience: Read descriptions above, then use LaTeX code with Overleaf.com for professional figures*\n\n"
|
368 |
+
|
369 |
+
# Update thought to reflect dual output
|
370 |
+
thought = f"Generated comprehensive dual output with {descriptions_available} detailed technical descriptions AND {latex_available} professional LaTeX/TikZ code sets. Users can read descriptions immediately and compile LaTeX for USPTO-ready vector graphics."
|
371 |
+
|
372 |
+
elif gemini_result.get("images_generated", 0) > 0:
|
373 |
if gemini_result.get("latex_generated", 0) > 0:
|
374 |
content += "\n\n*🎨 Generated LaTeX/TikZ code using Google Gemini 2.0 Flash - Compile with pdflatex to create professional patent figures*\n\n"
|
375 |
content += f"*💡 To view images: Compile the .tex files in `{os.path.expanduser('~')}/patent_architect_figures/`*\n\n"
|
376 |
+
thought = "Generated professional LaTeX/TikZ code for patent figures using Google Gemini 2.0 Flash. Code can be compiled to create high-quality technical drawings with numbered components and USPTO-ready formatting."
|
377 |
else:
|
378 |
content += "\n\n*🎨 Generated visual patent figures using Google Gemini 2.0 Flash - Professional images ready for USPTO submission*\n\n"
|
379 |
+
thought = "Generated high-quality patent figures using Google Gemini 2.0 Flash with professional technical drawings, numbered components, and USPTO-ready formatting."
|
380 |
else:
|
381 |
content += "\n\n*📝 Generated detailed patent figure descriptions using Google Gemini 2.0 Flash - Professional technical specifications*\n\n"
|
382 |
+
thought = "Generated detailed technical specifications for patent figures using Google Gemini 2.0 Flash with professional patent formatting."
|
383 |
|
384 |
print("✅ Gemini image generation successful - Backend content replaced")
|
385 |
|
|
|
|
|
|
|
|
|
|
|
386 |
else:
|
387 |
print(f"❌ Gemini generation failed: {gemini_result.get('error', 'Unknown error')}")
|
388 |
|
gemini_image_generator.py
CHANGED
@@ -1,7 +1,9 @@
|
|
1 |
#!/usr/bin/env python3
|
2 |
"""
|
3 |
-
Gemini Image Generator Integration for Patent Architect AI v2
|
4 |
-
Provides high-quality technical figure generation
|
|
|
|
|
5 |
"""
|
6 |
|
7 |
import os
|
@@ -9,6 +11,8 @@ import json
|
|
9 |
import base64
|
10 |
import requests
|
11 |
import tempfile
|
|
|
|
|
12 |
from typing import Dict, List, Optional, Tuple
|
13 |
import google.generativeai as genai
|
14 |
from datetime import datetime
|
@@ -18,10 +22,10 @@ from dotenv import load_dotenv
|
|
18 |
load_dotenv()
|
19 |
|
20 |
class GeminiImageGenerator:
|
21 |
-
"""
|
22 |
|
23 |
def __init__(self, api_key: Optional[str] = None, output_dir: Optional[str] = None):
|
24 |
-
"""Initialize the Gemini image generator.
|
25 |
|
26 |
Args:
|
27 |
api_key: Google Gemini API key
|
@@ -39,6 +43,9 @@ class GeminiImageGenerator:
|
|
39 |
self.output_dir = output_dir or os.path.join(os.path.expanduser("~"), "patent_architect_figures")
|
40 |
os.makedirs(self.output_dir, exist_ok=True)
|
41 |
|
|
|
|
|
|
|
42 |
# Image generation parameters
|
43 |
self.generation_config = {
|
44 |
'temperature': 0.4,
|
@@ -47,202 +54,242 @@ class GeminiImageGenerator:
|
|
47 |
'max_output_tokens': 8192,
|
48 |
}
|
49 |
|
50 |
-
def
|
51 |
-
|
52 |
-
|
53 |
-
|
54 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
55 |
|
56 |
Args:
|
57 |
-
|
58 |
-
|
59 |
-
specific_requirements: Additional requirements for the figure
|
60 |
|
61 |
Returns:
|
62 |
-
|
63 |
"""
|
64 |
try:
|
65 |
-
#
|
66 |
-
|
67 |
-
invention_description,
|
68 |
-
figure_type,
|
69 |
-
specific_requirements
|
70 |
-
)
|
71 |
|
72 |
-
|
73 |
-
|
|
|
|
|
|
|
74 |
|
75 |
-
|
76 |
-
|
77 |
-
|
|
|
|
|
|
|
|
|
78 |
|
79 |
-
|
80 |
-
|
81 |
-
'temperature': 0.1, # Low temperature for consistent technical drawings
|
82 |
-
'top_k': 1,
|
83 |
-
'top_p': 0.8,
|
84 |
-
'max_output_tokens': 4096,
|
85 |
-
}
|
86 |
|
87 |
-
|
88 |
-
|
|
|
|
|
|
|
89 |
|
90 |
-
|
91 |
-
|
92 |
-
|
93 |
-
|
94 |
-
|
95 |
-
|
96 |
-
|
97 |
-
|
98 |
-
|
99 |
-
|
100 |
-
|
101 |
-
|
102 |
-
|
103 |
-
|
104 |
-
|
105 |
-
|
106 |
-
|
107 |
-
|
108 |
-
|
109 |
-
|
110 |
-
|
111 |
-
return {
|
112 |
-
"success": True,
|
113 |
-
"image_generated": True,
|
114 |
-
"image_path": image_filepath,
|
115 |
-
"figure_description": f"Generated technical patent figure for {figure_type}",
|
116 |
-
"file_path": image_filepath,
|
117 |
-
"figure_type": figure_type,
|
118 |
-
"timestamp": timestamp,
|
119 |
-
"mime_type": mime_type,
|
120 |
-
"metadata": {
|
121 |
-
"invention": invention_description,
|
122 |
-
"requirements": specific_requirements,
|
123 |
-
"generation_config": image_generation_config
|
124 |
-
}
|
125 |
-
}
|
126 |
-
|
127 |
-
# Handle LaTeX/TikZ code generation (common for technical drawings)
|
128 |
-
elif image_data:
|
129 |
-
try:
|
130 |
-
# Decode the data as text (might be LaTeX/TikZ code)
|
131 |
-
code_content = base64.b64decode(image_data).decode('utf-8')
|
132 |
-
|
133 |
-
# Check if it looks like LaTeX/TikZ code
|
134 |
-
if any(keyword in code_content.lower() for keyword in ['tikz', 'latex', 'documentclass', '\\draw']):
|
135 |
-
print(f"🎨 Generated LaTeX/TikZ code for technical drawing")
|
136 |
-
|
137 |
-
# Save LaTeX code
|
138 |
-
latex_filename = f"patent_figure_{figure_type}_{timestamp}.tex"
|
139 |
-
latex_filepath = os.path.join(self.output_dir, latex_filename)
|
140 |
-
|
141 |
-
with open(latex_filepath, 'w', encoding='utf-8') as f:
|
142 |
-
f.write(f"% Patent Figure - {figure_type}\n")
|
143 |
-
f.write(f"% Generated: {datetime.now().isoformat()}\n")
|
144 |
-
f.write(f"% Invention: {invention_description}\n\n")
|
145 |
-
f.write(code_content)
|
146 |
-
|
147 |
-
return {
|
148 |
-
"success": True,
|
149 |
-
"image_generated": True,
|
150 |
-
"latex_generated": True,
|
151 |
-
"image_path": latex_filepath,
|
152 |
-
"figure_description": f"Generated LaTeX/TikZ code for technical patent figure: {figure_type}",
|
153 |
-
"file_path": latex_filepath,
|
154 |
-
"figure_type": figure_type,
|
155 |
-
"timestamp": timestamp,
|
156 |
-
"mime_type": "application/x-latex",
|
157 |
-
"code_preview": code_content[:200] + "..." if len(code_content) > 200 else code_content,
|
158 |
-
"metadata": {
|
159 |
-
"invention": invention_description,
|
160 |
-
"requirements": specific_requirements,
|
161 |
-
"generation_config": image_generation_config,
|
162 |
-
"format": "LaTeX/TikZ"
|
163 |
-
}
|
164 |
-
}
|
165 |
-
except Exception as decode_error:
|
166 |
-
print(f"⚠️ Could not decode inline data as text: {decode_error}")
|
167 |
|
168 |
-
|
169 |
-
|
170 |
-
|
171 |
-
|
172 |
-
|
173 |
-
|
174 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
175 |
|
176 |
-
#
|
177 |
-
|
178 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
179 |
|
180 |
-
|
181 |
-
|
182 |
-
|
183 |
-
|
184 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
185 |
|
186 |
-
|
187 |
-
|
188 |
-
|
189 |
-
|
190 |
-
|
191 |
-
|
192 |
-
|
193 |
-
|
194 |
-
|
195 |
-
|
196 |
-
|
197 |
-
|
198 |
-
"invention": invention_description,
|
199 |
-
"requirements": specific_requirements,
|
200 |
-
"generation_config": image_generation_config,
|
201 |
-
"format": "LaTeX/TikZ"
|
202 |
-
}
|
203 |
-
}
|
204 |
-
|
205 |
-
# If no image data, fall back to text description generation
|
206 |
-
print(f"ℹ️ No image data in response, generating detailed text description...")
|
207 |
-
|
208 |
-
except Exception as image_error:
|
209 |
-
print(f"⚠️ Image generation failed ({str(image_error)}), falling back to text description...")
|
210 |
|
211 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
212 |
text_prompt = self._create_patent_figure_prompt(
|
213 |
invention_description,
|
214 |
figure_type,
|
215 |
specific_requirements
|
216 |
)
|
217 |
|
218 |
-
|
219 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
220 |
|
221 |
-
# Save
|
222 |
-
|
223 |
-
|
224 |
|
225 |
-
|
|
|
|
|
|
|
|
|
226 |
f.write(f"Patent Figure Description\n")
|
227 |
f.write(f"========================\n\n")
|
228 |
f.write(f"Invention: {invention_description}\n\n")
|
229 |
f.write(f"Figure Type: {figure_type}\n\n")
|
230 |
-
f.write(f"Description:\n{
|
231 |
f.write(f"Generated: {datetime.now().isoformat()}\n")
|
232 |
|
233 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
234 |
|
235 |
return {
|
236 |
"success": True,
|
237 |
-
"
|
238 |
-
"
|
239 |
-
"
|
|
|
|
|
|
|
|
|
240 |
"figure_type": figure_type,
|
241 |
"timestamp": timestamp,
|
|
|
|
|
242 |
"metadata": {
|
243 |
"invention": invention_description,
|
244 |
"requirements": specific_requirements,
|
245 |
-
"
|
|
|
246 |
}
|
247 |
}
|
248 |
|
@@ -253,6 +300,15 @@ class GeminiImageGenerator:
|
|
253 |
"figure_type": figure_type
|
254 |
}
|
255 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
256 |
def generate_multiple_figures(self,
|
257 |
invention_description: str,
|
258 |
figure_types: List[str] = None) -> List[Dict]:
|
@@ -346,7 +402,7 @@ a professional patent figure. Focus on technical accuracy and completeness."""
|
|
346 |
invention_description: str,
|
347 |
figure_type: str,
|
348 |
specific_requirements: Optional[str] = None) -> str:
|
349 |
-
"""Create a prompt specifically for
|
350 |
|
351 |
Args:
|
352 |
invention_description: Description of the invention
|
@@ -354,29 +410,28 @@ a professional patent figure. Focus on technical accuracy and completeness."""
|
|
354 |
specific_requirements: Additional requirements
|
355 |
|
356 |
Returns:
|
357 |
-
Optimized prompt for
|
358 |
"""
|
359 |
-
base_prompt = f"""
|
360 |
|
361 |
Figure Type: {figure_type}
|
362 |
|
363 |
-
|
364 |
-
-
|
365 |
-
-
|
|
|
|
|
366 |
- Numbered components (1, 2, 3, etc.) with clear labels
|
367 |
-
-
|
368 |
-
- No
|
369 |
-
- Isometric or cross-sectional view as appropriate
|
370 |
-
- Clear spatial relationships between components
|
371 |
-
- Technical precision suitable for USPTO submission
|
372 |
|
373 |
-
|
374 |
-
- Use
|
375 |
-
-
|
376 |
-
-
|
377 |
-
-
|
378 |
-
-
|
379 |
-
- Include
|
380 |
|
381 |
"""
|
382 |
|
@@ -407,14 +462,14 @@ The drawing should be clear, precise, and technically accurate."""
|
|
407 |
def integrate_with_patent_architect(self,
|
408 |
invention_description: str,
|
409 |
figure_descriptions: List[str] = None) -> Dict:
|
410 |
-
"""
|
411 |
|
412 |
Args:
|
413 |
invention_description: The invention being patented
|
414 |
figure_descriptions: Specific figure descriptions needed
|
415 |
|
416 |
Returns:
|
417 |
-
Dict with content
|
418 |
"""
|
419 |
try:
|
420 |
if figure_descriptions is None:
|
@@ -423,22 +478,26 @@ The drawing should be clear, precise, and technically accurate."""
|
|
423 |
results = []
|
424 |
|
425 |
for i, figure_type in enumerate(figure_types, 1):
|
426 |
-
result = self.
|
427 |
if result["success"]:
|
428 |
results.append({
|
429 |
"figure_number": i,
|
430 |
-
"description": result["
|
431 |
-
"
|
|
|
|
|
|
|
|
|
432 |
"type": figure_type,
|
433 |
-
"
|
434 |
-
"
|
435 |
-
"
|
436 |
})
|
437 |
else:
|
438 |
# Generate specific requested figures
|
439 |
results = []
|
440 |
for i, description in enumerate(figure_descriptions, 1):
|
441 |
-
result = self.
|
442 |
invention_description,
|
443 |
f"custom_figure_{i}",
|
444 |
description
|
@@ -446,102 +505,135 @@ The drawing should be clear, precise, and technically accurate."""
|
|
446 |
if result["success"]:
|
447 |
results.append({
|
448 |
"figure_number": i,
|
449 |
-
"description": result["
|
450 |
-
"
|
|
|
|
|
|
|
|
|
451 |
"type": "custom",
|
452 |
-
"
|
453 |
-
"
|
454 |
-
"
|
455 |
})
|
456 |
|
457 |
-
#
|
458 |
if results:
|
459 |
-
content = "## Patent Figures\n\n"
|
460 |
|
461 |
-
# Count
|
462 |
-
images_generated = sum(1 for r in results if r.get("image_generated", False))
|
463 |
-
latex_generated = sum(1 for r in results if r.get("latex_generated", False))
|
464 |
total_figures = len(results)
|
|
|
|
|
|
|
465 |
|
466 |
-
|
467 |
-
|
468 |
-
|
469 |
-
|
470 |
-
|
471 |
-
|
472 |
-
|
|
|
|
|
|
|
|
|
|
|
473 |
|
474 |
for figure in results:
|
475 |
figure_title = figure['type'].replace('_', ' ').title()
|
476 |
content += f"### Figure {figure['figure_number']}: {figure_title}\n\n"
|
477 |
|
478 |
-
#
|
479 |
-
if figure.get("
|
480 |
-
|
481 |
-
|
482 |
-
|
483 |
-
|
484 |
-
|
485 |
-
|
486 |
-
|
487 |
-
|
488 |
-
|
489 |
-
|
490 |
-
|
491 |
-
|
492 |
-
|
493 |
-
|
494 |
-
|
495 |
-
|
496 |
-
|
497 |
-
|
498 |
-
|
499 |
-
|
500 |
-
|
501 |
-
|
502 |
-
|
503 |
-
|
504 |
-
|
505 |
-
|
506 |
-
|
507 |
-
|
508 |
-
|
509 |
-
|
510 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
511 |
|
512 |
-
#
|
513 |
content += "---\n\n"
|
514 |
-
content += f"
|
515 |
-
content += f"- Total Figures
|
516 |
-
content += f"-
|
517 |
-
|
518 |
-
|
519 |
-
content += f"-
|
520 |
|
521 |
-
|
522 |
-
|
523 |
-
|
524 |
-
|
525 |
-
|
526 |
-
|
527 |
-
|
528 |
-
|
|
|
|
|
|
|
|
|
529 |
|
530 |
-
content += f"
|
531 |
|
532 |
return {
|
533 |
"success": True,
|
534 |
"content": content,
|
535 |
"figures": results,
|
536 |
"total_figures": len(results),
|
537 |
-
"
|
538 |
-
"
|
539 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
540 |
}
|
541 |
else:
|
542 |
return {
|
543 |
"success": False,
|
544 |
-
"content": "### Technical Figures\n\nError generating patent figures. Please review invention description and try again.\n\n",
|
545 |
"error": "No figures were successfully generated"
|
546 |
}
|
547 |
|
@@ -585,7 +677,7 @@ def test_gemini_integration():
|
|
585 |
print(f" 🎨 Format: {result.get('mime_type', 'Unknown')}")
|
586 |
else:
|
587 |
print(f"ℹ️ Generated detailed text description (image generation unavailable)")
|
588 |
-
print(f" 📄 Description file: {result['
|
589 |
else:
|
590 |
print(f"❌ Individual generation failed: {result.get('error', 'Unknown error')}")
|
591 |
|
@@ -670,7 +762,7 @@ Draw this as a black and white technical patent figure."""
|
|
670 |
print(f" 📎 Has inline data: ✅")
|
671 |
print(f" 🎨 MIME type: {part.inline_data.mime_type}")
|
672 |
else:
|
673 |
-
print(f"
|
674 |
|
675 |
if hasattr(response, 'text') and response.text:
|
676 |
preview = response.text[:200] + "..." if len(response.text) > 200 else response.text
|
|
|
1 |
#!/usr/bin/env python3
|
2 |
"""
|
3 |
+
Enhanced Gemini Image Generator Integration for Patent Architect AI v2
|
4 |
+
Provides high-quality technical figure generation with dual output:
|
5 |
+
- Detailed technical descriptions for immediate understanding
|
6 |
+
- Professional LaTeX/TikZ code with embedded compilation options
|
7 |
"""
|
8 |
|
9 |
import os
|
|
|
11 |
import base64
|
12 |
import requests
|
13 |
import tempfile
|
14 |
+
import subprocess
|
15 |
+
import shutil
|
16 |
from typing import Dict, List, Optional, Tuple
|
17 |
import google.generativeai as genai
|
18 |
from datetime import datetime
|
|
|
22 |
load_dotenv()
|
23 |
|
24 |
class GeminiImageGenerator:
|
25 |
+
"""Enhanced Gemini integration with dual output and embedded compilation."""
|
26 |
|
27 |
def __init__(self, api_key: Optional[str] = None, output_dir: Optional[str] = None):
|
28 |
+
"""Initialize the enhanced Gemini image generator.
|
29 |
|
30 |
Args:
|
31 |
api_key: Google Gemini API key
|
|
|
43 |
self.output_dir = output_dir or os.path.join(os.path.expanduser("~"), "patent_architect_figures")
|
44 |
os.makedirs(self.output_dir, exist_ok=True)
|
45 |
|
46 |
+
# Check if LaTeX is available for compilation
|
47 |
+
self.latex_available = self._check_latex_installation()
|
48 |
+
|
49 |
# Image generation parameters
|
50 |
self.generation_config = {
|
51 |
'temperature': 0.4,
|
|
|
54 |
'max_output_tokens': 8192,
|
55 |
}
|
56 |
|
57 |
+
def _check_latex_installation(self) -> bool:
|
58 |
+
"""Check if LaTeX is available for compilation."""
|
59 |
+
try:
|
60 |
+
result = subprocess.run(['pdflatex', '--version'],
|
61 |
+
capture_output=True,
|
62 |
+
text=True,
|
63 |
+
timeout=5)
|
64 |
+
return result.returncode == 0
|
65 |
+
except (subprocess.TimeoutExpired, FileNotFoundError, subprocess.SubprocessError):
|
66 |
+
return False
|
67 |
+
|
68 |
+
def _compile_latex_via_web_api(self, latex_code: str, filename: str) -> Optional[str]:
|
69 |
+
"""Try to compile LaTeX using web-based APIs.
|
70 |
|
71 |
Args:
|
72 |
+
latex_code: LaTeX source code
|
73 |
+
filename: Base filename for output
|
|
|
74 |
|
75 |
Returns:
|
76 |
+
Path to compiled image or None if failed
|
77 |
"""
|
78 |
try:
|
79 |
+
# Try using a public LaTeX compilation API (example with LaTeX.Online)
|
80 |
+
api_url = "https://latex.vercel.app/api/v2"
|
|
|
|
|
|
|
|
|
81 |
|
82 |
+
payload = {
|
83 |
+
"code": latex_code,
|
84 |
+
"format": "png",
|
85 |
+
"quality": 300
|
86 |
+
}
|
87 |
|
88 |
+
print(f"🌐 Attempting web-based LaTeX compilation...")
|
89 |
+
response = requests.post(api_url, json=payload, timeout=30)
|
90 |
+
|
91 |
+
if response.status_code == 200:
|
92 |
+
# Save compiled image
|
93 |
+
image_filename = f"{filename}.png"
|
94 |
+
image_path = os.path.join(self.output_dir, image_filename)
|
95 |
|
96 |
+
with open(image_path, 'wb') as f:
|
97 |
+
f.write(response.content)
|
|
|
|
|
|
|
|
|
|
|
98 |
|
99 |
+
print(f"✅ Web compilation successful: {image_filename}")
|
100 |
+
return image_path
|
101 |
+
else:
|
102 |
+
print(f"⚠️ Web compilation failed: HTTP {response.status_code}")
|
103 |
+
return None
|
104 |
|
105 |
+
except Exception as e:
|
106 |
+
print(f"⚠️ Web compilation error: {e}")
|
107 |
+
return None
|
108 |
+
|
109 |
+
def _compile_latex_to_image(self, latex_filepath: str) -> Optional[str]:
|
110 |
+
"""Enhanced LaTeX compilation with multiple methods.
|
111 |
+
|
112 |
+
Args:
|
113 |
+
latex_filepath: Path to the .tex file
|
114 |
+
|
115 |
+
Returns:
|
116 |
+
Path to generated image file or None if compilation failed
|
117 |
+
"""
|
118 |
+
# Try local compilation first if available
|
119 |
+
if self.latex_available:
|
120 |
+
try:
|
121 |
+
# Get directory and filename
|
122 |
+
tex_dir = os.path.dirname(latex_filepath)
|
123 |
+
tex_filename = os.path.basename(latex_filepath)
|
124 |
+
base_name = os.path.splitext(tex_filename)[0]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
125 |
|
126 |
+
print(f"🔧 Attempting local LaTeX compilation...")
|
127 |
+
|
128 |
+
# Compile LaTeX to PDF
|
129 |
+
result = subprocess.run([
|
130 |
+
'pdflatex',
|
131 |
+
'-output-directory', tex_dir,
|
132 |
+
'-interaction=nonstopmode',
|
133 |
+
latex_filepath
|
134 |
+
], capture_output=True, text=True, timeout=30)
|
135 |
+
|
136 |
+
if result.returncode == 0:
|
137 |
+
# Check if PDF was created
|
138 |
+
pdf_path = os.path.join(tex_dir, f"{base_name}.pdf")
|
139 |
+
if os.path.exists(pdf_path):
|
140 |
+
# Try to convert PDF to PNG using available tools
|
141 |
+
png_path = os.path.join(tex_dir, f"{base_name}.png")
|
142 |
|
143 |
+
# Try different conversion methods
|
144 |
+
conversion_methods = [
|
145 |
+
# Method 1: pdftoppm (part of poppler-utils)
|
146 |
+
['pdftoppm', '-png', '-singlefile', '-r', '300', pdf_path, base_name],
|
147 |
+
# Method 2: ImageMagick convert
|
148 |
+
['convert', '-density', '300', pdf_path, png_path],
|
149 |
+
# Method 3: ghostscript
|
150 |
+
['gs', '-dNOPAUSE', '-dBATCH', '-sDEVICE=png16m', '-r300', f'-sOutputFile={png_path}', pdf_path]
|
151 |
+
]
|
152 |
|
153 |
+
for method in conversion_methods:
|
154 |
+
try:
|
155 |
+
if method[0] == 'pdftoppm':
|
156 |
+
result = subprocess.run(method,
|
157 |
+
cwd=tex_dir,
|
158 |
+
capture_output=True,
|
159 |
+
text=True,
|
160 |
+
timeout=30)
|
161 |
+
if result.returncode == 0:
|
162 |
+
expected_png = os.path.join(tex_dir, f"{base_name}.png")
|
163 |
+
if os.path.exists(expected_png):
|
164 |
+
print(f"✅ Local compilation successful: {expected_png}")
|
165 |
+
return expected_png
|
166 |
+
else:
|
167 |
+
result = subprocess.run(method,
|
168 |
+
capture_output=True,
|
169 |
+
text=True,
|
170 |
+
timeout=30)
|
171 |
+
if result.returncode == 0 and os.path.exists(png_path):
|
172 |
+
print(f"✅ Local compilation successful: {png_path}")
|
173 |
+
return png_path
|
174 |
+
|
175 |
+
except (subprocess.TimeoutExpired, FileNotFoundError):
|
176 |
+
continue
|
177 |
|
178 |
+
print(f"✅ PDF created but PNG conversion failed: {pdf_path}")
|
179 |
+
return pdf_path # Return PDF if PNG conversion failed
|
180 |
+
else:
|
181 |
+
print(f"⚠️ Local LaTeX compilation failed: {result.stderr}")
|
182 |
+
|
183 |
+
except Exception as e:
|
184 |
+
print(f"⚠️ Local LaTeX compilation error: {e}")
|
185 |
+
|
186 |
+
# Try web-based compilation as fallback
|
187 |
+
try:
|
188 |
+
with open(latex_filepath, 'r', encoding='utf-8') as f:
|
189 |
+
latex_code = f.read()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
190 |
|
191 |
+
base_name = os.path.splitext(os.path.basename(latex_filepath))[0]
|
192 |
+
web_result = self._compile_latex_via_web_api(latex_code, base_name)
|
193 |
+
if web_result:
|
194 |
+
return web_result
|
195 |
+
except Exception as e:
|
196 |
+
print(f"⚠️ Web compilation fallback failed: {e}")
|
197 |
+
|
198 |
+
return None
|
199 |
+
|
200 |
+
def generate_dual_output_figure(self,
|
201 |
+
invention_description: str,
|
202 |
+
figure_type: str = "technical_diagram",
|
203 |
+
specific_requirements: Optional[str] = None) -> Dict:
|
204 |
+
"""Generate both detailed description AND LaTeX code for a patent figure.
|
205 |
+
|
206 |
+
Args:
|
207 |
+
invention_description: Description of the invention
|
208 |
+
figure_type: Type of figure to generate
|
209 |
+
specific_requirements: Additional requirements for the figure
|
210 |
+
|
211 |
+
Returns:
|
212 |
+
Dict containing both text description and LaTeX code with compilation options
|
213 |
+
"""
|
214 |
+
try:
|
215 |
+
timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
|
216 |
+
|
217 |
+
# Step 1: Generate detailed text description
|
218 |
+
print(f"📝 Generating detailed technical description...")
|
219 |
text_prompt = self._create_patent_figure_prompt(
|
220 |
invention_description,
|
221 |
figure_type,
|
222 |
specific_requirements
|
223 |
)
|
224 |
|
225 |
+
text_response = self.model.generate_content([text_prompt])
|
226 |
+
detailed_description = text_response.text
|
227 |
+
|
228 |
+
# Step 2: Generate LaTeX/TikZ code
|
229 |
+
print(f"🎨 Generating LaTeX/TikZ code...")
|
230 |
+
latex_prompt = self._create_image_generation_prompt(
|
231 |
+
invention_description,
|
232 |
+
figure_type,
|
233 |
+
specific_requirements
|
234 |
+
)
|
235 |
+
|
236 |
+
latex_response = self.model.generate_content([latex_prompt],
|
237 |
+
generation_config={'temperature': 0.1})
|
238 |
+
latex_code = latex_response.text
|
239 |
|
240 |
+
# Save both outputs
|
241 |
+
text_filename = f"patent_figure_{figure_type}_{timestamp}_description.txt"
|
242 |
+
latex_filename = f"patent_figure_{figure_type}_{timestamp}.tex"
|
243 |
|
244 |
+
text_filepath = os.path.join(self.output_dir, text_filename)
|
245 |
+
latex_filepath = os.path.join(self.output_dir, latex_filename)
|
246 |
+
|
247 |
+
# Save detailed description
|
248 |
+
with open(text_filepath, 'w', encoding='utf-8') as f:
|
249 |
f.write(f"Patent Figure Description\n")
|
250 |
f.write(f"========================\n\n")
|
251 |
f.write(f"Invention: {invention_description}\n\n")
|
252 |
f.write(f"Figure Type: {figure_type}\n\n")
|
253 |
+
f.write(f"Description:\n{detailed_description}\n\n")
|
254 |
f.write(f"Generated: {datetime.now().isoformat()}\n")
|
255 |
|
256 |
+
# Save LaTeX code
|
257 |
+
with open(latex_filepath, 'w', encoding='utf-8') as f:
|
258 |
+
f.write(f"% Patent Figure - {figure_type}\n")
|
259 |
+
f.write(f"% Generated: {datetime.now().isoformat()}\n")
|
260 |
+
f.write(f"% Invention: {invention_description}\n\n")
|
261 |
+
f.write(latex_code)
|
262 |
+
|
263 |
+
# Try to compile LaTeX to image
|
264 |
+
compiled_image_path = None
|
265 |
+
compilation_method = None
|
266 |
+
|
267 |
+
if any(keyword in latex_code.lower() for keyword in ['tikz', 'latex', 'documentclass', '\\draw']):
|
268 |
+
compiled_image_path = self._compile_latex_to_image(latex_filepath)
|
269 |
+
if compiled_image_path:
|
270 |
+
if self.latex_available:
|
271 |
+
compilation_method = "local"
|
272 |
+
else:
|
273 |
+
compilation_method = "web"
|
274 |
|
275 |
return {
|
276 |
"success": True,
|
277 |
+
"dual_output": True,
|
278 |
+
"text_description": detailed_description,
|
279 |
+
"latex_code": latex_code,
|
280 |
+
"text_file_path": text_filepath,
|
281 |
+
"latex_file_path": latex_filepath,
|
282 |
+
"compiled_image_path": compiled_image_path,
|
283 |
+
"compilation_method": compilation_method,
|
284 |
"figure_type": figure_type,
|
285 |
"timestamp": timestamp,
|
286 |
+
"code_preview": latex_code[:400] + "..." if len(latex_code) > 400 else latex_code,
|
287 |
+
"description_preview": detailed_description[:300] + "..." if len(detailed_description) > 300 else detailed_description,
|
288 |
"metadata": {
|
289 |
"invention": invention_description,
|
290 |
"requirements": specific_requirements,
|
291 |
+
"latex_available": self.latex_available,
|
292 |
+
"output_formats": ["description", "latex", "compiled_image"] if compiled_image_path else ["description", "latex"]
|
293 |
}
|
294 |
}
|
295 |
|
|
|
300 |
"figure_type": figure_type
|
301 |
}
|
302 |
|
303 |
+
def generate_patent_figure(self,
|
304 |
+
invention_description: str,
|
305 |
+
figure_type: str = "technical_diagram",
|
306 |
+
specific_requirements: Optional[str] = None) -> Dict:
|
307 |
+
"""Enhanced patent figure generation with dual output option."""
|
308 |
+
|
309 |
+
# Use the new dual output method for better results
|
310 |
+
return self.generate_dual_output_figure(invention_description, figure_type, specific_requirements)
|
311 |
+
|
312 |
def generate_multiple_figures(self,
|
313 |
invention_description: str,
|
314 |
figure_types: List[str] = None) -> List[Dict]:
|
|
|
402 |
invention_description: str,
|
403 |
figure_type: str,
|
404 |
specific_requirements: Optional[str] = None) -> str:
|
405 |
+
"""Create a prompt specifically for LaTeX/TikZ code generation.
|
406 |
|
407 |
Args:
|
408 |
invention_description: Description of the invention
|
|
|
410 |
specific_requirements: Additional requirements
|
411 |
|
412 |
Returns:
|
413 |
+
Optimized prompt for LaTeX/TikZ patent figure generation
|
414 |
"""
|
415 |
+
base_prompt = f"""Generate ONLY LaTeX/TikZ code for a professional patent figure showing: {invention_description}
|
416 |
|
417 |
Figure Type: {figure_type}
|
418 |
|
419 |
+
OUTPUT REQUIREMENTS:
|
420 |
+
- Complete LaTeX document ready to compile
|
421 |
+
- Start with \\documentclass{{article}} and end with \\end{{document}}
|
422 |
+
- Include necessary packages: \\usepackage{{tikz}}, \\usepackage{{geometry}}
|
423 |
+
- Professional patent-style technical drawing
|
424 |
- Numbered components (1, 2, 3, etc.) with clear labels
|
425 |
+
- Clean, precise TikZ drawing commands
|
426 |
+
- No explanatory text - ONLY LaTeX code
|
|
|
|
|
|
|
427 |
|
428 |
+
TECHNICAL DRAWING REQUIREMENTS:
|
429 |
+
- Use TikZ \\draw commands for all shapes
|
430 |
+
- Include numbered component labels with \\node commands
|
431 |
+
- Proper scaling and positioning
|
432 |
+
- Professional technical drawing style
|
433 |
+
- Clear spatial relationships between components
|
434 |
+
- Include connecting lines and annotations where relevant
|
435 |
|
436 |
"""
|
437 |
|
|
|
462 |
def integrate_with_patent_architect(self,
|
463 |
invention_description: str,
|
464 |
figure_descriptions: List[str] = None) -> Dict:
|
465 |
+
"""Enhanced integration point for Patent Architect AI v2 system with dual output.
|
466 |
|
467 |
Args:
|
468 |
invention_description: The invention being patented
|
469 |
figure_descriptions: Specific figure descriptions needed
|
470 |
|
471 |
Returns:
|
472 |
+
Dict with enhanced content including both descriptions and LaTeX code
|
473 |
"""
|
474 |
try:
|
475 |
if figure_descriptions is None:
|
|
|
478 |
results = []
|
479 |
|
480 |
for i, figure_type in enumerate(figure_types, 1):
|
481 |
+
result = self.generate_dual_output_figure(invention_description, figure_type)
|
482 |
if result["success"]:
|
483 |
results.append({
|
484 |
"figure_number": i,
|
485 |
+
"description": result["text_description"],
|
486 |
+
"latex_code": result["latex_code"],
|
487 |
+
"text_file_path": result["text_file_path"],
|
488 |
+
"latex_file_path": result["latex_file_path"],
|
489 |
+
"compiled_image_path": result.get("compiled_image_path"),
|
490 |
+
"compilation_method": result.get("compilation_method"),
|
491 |
"type": figure_type,
|
492 |
+
"dual_output": True,
|
493 |
+
"code_preview": result.get("code_preview", ""),
|
494 |
+
"description_preview": result.get("description_preview", "")
|
495 |
})
|
496 |
else:
|
497 |
# Generate specific requested figures
|
498 |
results = []
|
499 |
for i, description in enumerate(figure_descriptions, 1):
|
500 |
+
result = self.generate_dual_output_figure(
|
501 |
invention_description,
|
502 |
f"custom_figure_{i}",
|
503 |
description
|
|
|
505 |
if result["success"]:
|
506 |
results.append({
|
507 |
"figure_number": i,
|
508 |
+
"description": result["text_description"],
|
509 |
+
"latex_code": result["latex_code"],
|
510 |
+
"text_file_path": result["text_file_path"],
|
511 |
+
"latex_file_path": result["latex_file_path"],
|
512 |
+
"compiled_image_path": result.get("compiled_image_path"),
|
513 |
+
"compilation_method": result.get("compilation_method"),
|
514 |
"type": "custom",
|
515 |
+
"dual_output": True,
|
516 |
+
"code_preview": result.get("code_preview", ""),
|
517 |
+
"description_preview": result.get("description_preview", "")
|
518 |
})
|
519 |
|
520 |
+
# Enhanced formatting for Patent Architect with dual output
|
521 |
if results:
|
522 |
+
content = "## 🎨 Enhanced Patent Figures with Dual Output\n\n"
|
523 |
|
524 |
+
# Count outputs
|
|
|
|
|
525 |
total_figures = len(results)
|
526 |
+
compiled_images = sum(1 for r in results if r.get("compiled_image_path"))
|
527 |
+
local_compiled = sum(1 for r in results if r.get("compilation_method") == "local")
|
528 |
+
web_compiled = sum(1 for r in results if r.get("compilation_method") == "web")
|
529 |
|
530 |
+
content += f"*✨ Generated {total_figures} complete figure sets with both detailed descriptions AND LaTeX/TikZ code*\n\n"
|
531 |
+
|
532 |
+
if compiled_images > 0:
|
533 |
+
content += f"*🖼️ {compiled_images}/{total_figures} figures successfully compiled to images"
|
534 |
+
if local_compiled > 0:
|
535 |
+
content += f" ({local_compiled} local"
|
536 |
+
if web_compiled > 0:
|
537 |
+
if local_compiled > 0:
|
538 |
+
content += f", {web_compiled} web"
|
539 |
+
else:
|
540 |
+
content += f" ({web_compiled} web"
|
541 |
+
content += " compilation)*\n\n"
|
542 |
|
543 |
for figure in results:
|
544 |
figure_title = figure['type'].replace('_', ' ').title()
|
545 |
content += f"### Figure {figure['figure_number']}: {figure_title}\n\n"
|
546 |
|
547 |
+
# Show compiled image if available
|
548 |
+
if figure.get("compiled_image_path"):
|
549 |
+
image_filename = os.path.basename(figure['compiled_image_path'])
|
550 |
+
content += f"**🖼️ Compiled Image:** `{image_filename}` ({'Local' if figure.get('compilation_method') == 'local' else 'Web'} compilation)\n\n"
|
551 |
+
|
552 |
+
# Always show detailed description
|
553 |
+
content += f"**📝 Technical Description:**\n"
|
554 |
+
content += f"{figure['description'][:500]}{'...' if len(figure['description']) > 500 else ''}\n\n"
|
555 |
+
|
556 |
+
# Always show LaTeX code with enhanced instructions
|
557 |
+
latex_filename = os.path.basename(figure['latex_file_path'])
|
558 |
+
content += f"**🎨 LaTeX/TikZ Code:** `{latex_filename}`\n\n"
|
559 |
+
|
560 |
+
# Show code preview
|
561 |
+
if figure.get('code_preview'):
|
562 |
+
content += f"**Code Preview:**\n```latex\n{figure['code_preview']}\n```\n\n"
|
563 |
+
|
564 |
+
# Enhanced compilation options
|
565 |
+
content += f"**🚀 Multiple Viewing Options:**\n\n"
|
566 |
+
|
567 |
+
if figure.get("compiled_image_path"):
|
568 |
+
content += f"1. **✅ Pre-Compiled Image Available**: View `{os.path.basename(figure['compiled_image_path'])}` in output folder\n"
|
569 |
+
|
570 |
+
content += f"2. **🌐 Online Compilation (Easiest)**:\n"
|
571 |
+
content += f" - Go to [Overleaf.com](https://overleaf.com) (free account)\n"
|
572 |
+
content += f" - Create new project → Upload → Select `{latex_filename}`\n"
|
573 |
+
content += f" - Click 'Recompile' for instant professional PDF\n"
|
574 |
+
content += f" - Download PDF for USPTO submission\n\n"
|
575 |
+
|
576 |
+
content += f"3. **💻 Local Compilation**:\n"
|
577 |
+
content += f" - Install LaTeX: [MiKTeX](https://miktex.org/) (Windows) or [TeX Live](https://www.tug.org/texlive/)\n"
|
578 |
+
content += f" - Run: `pdflatex {latex_filename}`\n"
|
579 |
+
content += f" - Convert to PNG: `pdftoppm -png -singlefile output.pdf figure`\n\n"
|
580 |
+
|
581 |
+
content += f"4. **📱 Mobile/Quick View**: Use [LaTeX Live](https://latexlive.com) - paste code for instant preview\n\n"
|
582 |
+
|
583 |
+
# File information
|
584 |
+
content += f"**📁 Generated Files:**\n"
|
585 |
+
content += f"- 📝 Description: `{os.path.basename(figure['text_file_path'])}`\n"
|
586 |
+
content += f"- 🎨 LaTeX Code: `{latex_filename}`\n"
|
587 |
+
if figure.get("compiled_image_path"):
|
588 |
+
content += f"- 🖼️ Compiled Image: `{os.path.basename(figure['compiled_image_path'])}`\n"
|
589 |
+
content += f"- 📂 Location: `{os.path.dirname(figure['text_file_path'])}`\n\n"
|
590 |
|
591 |
+
# Enhanced summary and guidance
|
592 |
content += "---\n\n"
|
593 |
+
content += f"**📊 Generation Summary:**\n"
|
594 |
+
content += f"- **Total Figures:** {total_figures} complete sets\n"
|
595 |
+
content += f"- **Dual Output:** ✅ Both descriptions AND LaTeX code\n"
|
596 |
+
content += f"- **Compiled Images:** {compiled_images} ready to view\n"
|
597 |
+
content += f"- **USPTO Ready:** ✅ Professional patent figure quality\n"
|
598 |
+
content += f"- **Vector Graphics:** ✅ Infinite scaling, publication quality\n\n"
|
599 |
|
600 |
+
content += f"**🏆 Why This is Better:**\n"
|
601 |
+
content += f"- **Immediate Understanding:** Read detailed technical descriptions right now\n"
|
602 |
+
content += f"- **Professional Quality:** LaTeX creates publication-grade vector graphics\n"
|
603 |
+
content += f"- **Multiple Options:** View online (Overleaf), locally, or pre-compiled images\n"
|
604 |
+
content += f"- **USPTO Preferred:** Vector graphics are ideal for patent applications\n"
|
605 |
+
content += f"- **Editable:** Modify LaTeX code for custom adjustments\n\n"
|
606 |
+
|
607 |
+
content += f"**🎯 Quick Start Guide:**\n"
|
608 |
+
content += f"1. **Read the descriptions above** for immediate technical understanding\n"
|
609 |
+
content += f"2. **View compiled images** if available in the output folder\n"
|
610 |
+
content += f"3. **For publication quality**: Use Overleaf.com with the .tex files\n"
|
611 |
+
content += f"4. **For USPTO submission**: Compile LaTeX to PDF for vector graphics\n\n"
|
612 |
|
613 |
+
content += f"*Generated: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')} | Output: `{self.output_dir}`*\n\n"
|
614 |
|
615 |
return {
|
616 |
"success": True,
|
617 |
"content": content,
|
618 |
"figures": results,
|
619 |
"total_figures": len(results),
|
620 |
+
"dual_output": True,
|
621 |
+
"compiled_images": compiled_images,
|
622 |
+
"descriptions_available": total_figures,
|
623 |
+
"latex_code_available": total_figures,
|
624 |
+
"enhanced_features": [
|
625 |
+
"detailed_descriptions",
|
626 |
+
"latex_tikz_code",
|
627 |
+
"multiple_compilation_options",
|
628 |
+
"pre_compiled_images",
|
629 |
+
"overleaf_integration",
|
630 |
+
"uspto_ready_output"
|
631 |
+
]
|
632 |
}
|
633 |
else:
|
634 |
return {
|
635 |
"success": False,
|
636 |
+
"content": "### Technical Figures\n\nError generating enhanced patent figures. Please review invention description and try again.\n\n",
|
637 |
"error": "No figures were successfully generated"
|
638 |
}
|
639 |
|
|
|
677 |
print(f" 🎨 Format: {result.get('mime_type', 'Unknown')}")
|
678 |
else:
|
679 |
print(f"ℹ️ Generated detailed text description (image generation unavailable)")
|
680 |
+
print(f" 📄 Description file: {result['text_file_path']}")
|
681 |
else:
|
682 |
print(f"❌ Individual generation failed: {result.get('error', 'Unknown error')}")
|
683 |
|
|
|
762 |
print(f" 📎 Has inline data: ✅")
|
763 |
print(f" 🎨 MIME type: {part.inline_data.mime_type}")
|
764 |
else:
|
765 |
+
print(f" �� Has inline data: ❌")
|
766 |
|
767 |
if hasattr(response, 'text') and response.text:
|
768 |
preview = response.text[:200] + "..." if len(response.text) > 200 else response.text
|