Skip to content

Commit 10eacd5

Browse files
committed
fix image paths
1 parent c14d50e commit 10eacd5

File tree

1 file changed

+5
-5
lines changed

1 file changed

+5
-5
lines changed

examples/gpt-5/prompt-optimization-cookbook.ipynb

Lines changed: 5 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -257,7 +257,7 @@
257257
"\n",
258258
"From there press the **Optimize** button. This will open the optimization panel. At this stage, you can either provide specific edits you'd like to see reflected in the prompt or simply press **Optimize** to have it refined according to best practices for the target model and task. To start let's do just this.\n",
259259
"\n",
260-
"![optimize_image](../../../images/image_optimize_1.png)\n",
260+
"![optimize_image](../../images/image_optimize_1.png)\n",
261261
"\n",
262262
"\n",
263263
"\n",
@@ -269,7 +269,7 @@
269269
"\n",
270270
"This is easy using the iterative process of the Prompt Optimizer.\n",
271271
"\n",
272-
"![optimize_image](../../../images/image_optimize_2.png)\n",
272+
"![optimize_image](../../images/image_optimize_2.png)\n",
273273
"\n"
274274
]
275275
},
@@ -280,7 +280,7 @@
280280
"source": [
281281
"Once we are happy with the optimized version of our prompt, we can save it as a [Prompt Object](#https://platform.openai.com/docs/guides/prompt-engineering#reusable-prompts) using a button on the top right of the optimizer. We can use this object within our API Calls which can help with future iteration, version management, and reusability across different applications. \n",
282282
"\n",
283-
"![optimize_image](../../../images/image_optimize_3.png)\n"
283+
"![optimize_image](../../images/image_optimize_3.png)\n"
284284
]
285285
},
286286
{
@@ -621,7 +621,7 @@
621621
"\n",
622622
"Most production use cases face imperfect queries and noisy context. **FailSafeQA** is an excellent benchmark that deliberately perturbs both the **query** (misspellings, incompleteness, off-domain phrasing) and the **context** (missing, OCR-corrupted, or irrelevant docs) and reports **Robustness**, **Context Grounding**, and **Compliance**—i.e., can the model answer when the signal exists and abstain when it doesn’t.\n",
623623
"\n",
624-
"![FailSafeQA diagram](../../../images/image_optimize_4.png)\n",
624+
"![FailSafeQA diagram](../../images/image_optimize_4.png)\n",
625625
"\n",
626626
"**Links**\n",
627627
"- Paper (arXiv): *Expect the Unexpected: FailSafe Long Context QA for Finance* — https://arxiv.org/abs/2502.06329 \n",
@@ -659,7 +659,7 @@
659659
"We can use the prompt optimizer once again to construct a new prompt that is more suitable for this use case. Drawing on best practices for long-context question answering, we know that we should remind our answer model to rely on information in the context section and refuse answers to questions if the context is insufficient. By using the Optimize button once without any arguments we get a reasonable structure for the prompt and end up with this as our optimized prompt.\n",
660660
"\n",
661661
"\n",
662-
"![optimize_image](../../../images/image_optimize_5.png)\n",
662+
"![optimize_image](../../images/image_optimize_5.png)\n",
663663
"\n"
664664
]
665665
},

0 commit comments

Comments
 (0)