Spaces:
Runtime error
Runtime error
Update app.py
Browse files
app.py
CHANGED
@@ -218,8 +218,11 @@ def get_analysis_prompt(step_number):
|
|
218 |
|
219 |
step_name = step_info["Name"]
|
220 |
standard_time = step_info["Standard Time"]
|
221 |
-
|
222 |
|
|
|
|
|
|
|
223 |
return f"""
|
224 |
You are an AI expert system specialized in analyzing manufacturing processes and identifying production delays in tire manufacturing. Your role is to accurately classify delay reasons based on visual evidence from production line footage.
|
225 |
Task Context:
|
@@ -229,27 +232,12 @@ Carefully observe the video for visual cues indicating production interruption.
|
|
229 |
- If no person is visible in any of the frames, the reason probably might be due to their absence.
|
230 |
- If a person is visible in the video and is observed touching and modifying the layers of the tire, it indicates an issue with tire patching, and the person might be repairing it.
|
231 |
- Compare observed evidence against the following possible delay reasons:
|
232 |
-
|
233 |
-
Following are the subactivities
|
234 |
-
|
235 |
-
{get_step_info(step_number)}
|
236 |
-
|
237 |
Please provide your output in the following format:
|
238 |
Output:
|
239 |
-
|
240 |
-
Lack of raw material
|
241 |
-
Inner Liner Adjustment by Technician
|
242 |
-
Person rebuilding defective Tire Sections
|
243 |
-
Manual Adjustment in Ply1 Apply
|
244 |
-
Technician repairing defective Tire Sections
|
245 |
-
Delay in Bead Set
|
246 |
-
Delay in Turnup
|
247 |
-
Person Repairing sidewall
|
248 |
-
Person rebuilding defective Tire Sections
|
249 |
-
Delay in Sidewall Stitching
|
250 |
-
No person available to load Carcass
|
251 |
-
No person available to collect tire
|
252 |
-
|
253 |
1. **Selected Reason:** [State the most likely reason from the given options]
|
254 |
2. **Visual Evidence:** [Describe specific visual cues that support your selection]
|
255 |
3. **Reasoning:** [Explain why this reason best matches the observed evidence]
|
|
|
218 |
|
219 |
step_name = step_info["Name"]
|
220 |
standard_time = step_info["Standard Time"]
|
221 |
+
potential_delay_reasons = step_info.get("Potential_Delay_Reasons", [])
|
222 |
|
223 |
+
# Constructing the prompt dynamically with potential delay reasons
|
224 |
+
potential_reasons_text = "\n ".join(potential_delay_reasons)
|
225 |
+
|
226 |
return f"""
|
227 |
You are an AI expert system specialized in analyzing manufacturing processes and identifying production delays in tire manufacturing. Your role is to accurately classify delay reasons based on visual evidence from production line footage.
|
228 |
Task Context:
|
|
|
232 |
- If no person is visible in any of the frames, the reason probably might be due to their absence.
|
233 |
- If a person is visible in the video and is observed touching and modifying the layers of the tire, it indicates an issue with tire patching, and the person might be repairing it.
|
234 |
- Compare observed evidence against the following possible delay reasons:
|
235 |
+
{potential_reasons_text}
|
236 |
+
Following are the subactivities that need to happen in this step:
|
237 |
+
{get_step_info(step_number)["Video_substeps_expected"]}
|
|
|
|
|
238 |
Please provide your output in the following format:
|
239 |
Output:
|
240 |
+
{potential_reasons_text}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
241 |
1. **Selected Reason:** [State the most likely reason from the given options]
|
242 |
2. **Visual Evidence:** [Describe specific visual cues that support your selection]
|
243 |
3. **Reasoning:** [Explain why this reason best matches the observed evidence]
|