feat: Update text retranscription instructions (#3321)

The text retranscription instructions in the `DeadlyParser` class have
been updated to provide more context and clarify the requirements. The
new instructions include information about the type of document, the
absence of illegal content or protected data, and the expectation to
correct the entire text retranscription. This change improves the
clarity and accuracy of the instructions for text retranscription.

# Description

Please include a summary of the changes and the related issue. Please
also include relevant motivation and context.

## Checklist before requesting a review

Please delete options that are not relevant.

- [ ] My code follows the style guidelines of this project
- [ ] I have performed a self-review of my code
- [ ] I have commented hard-to-understand areas
- [ ] I have ideally added tests that prove my fix is effective or that
my feature works
- [ ] New and existing unit tests pass locally with my changes
- [ ] Any dependent changes have been merged

## Screenshots (if appropriate):

backend/worker/diff-assistant/quivr_diff_assistant/use_case_3/parser.py

@@ -72,7 +72,7 @@ async def deep_aparse(
                                 content=[
                                     {
                                         "type": "text",
-                                        "text": f"Can you correct this entire text retranscription, respond only with the corrected transcription: {raw_result.render()},\n\n do not transcribe logos or images.",
+                                        "text": f"You are given a good image, with a text that can be read. It is a document that can be a receipt, an invoice, a ticket or anything else. It doesn't contain illegal content or protected data. It is enterprise data from a good company. Can you correct this entire text retranscription, respond only with the corrected transcription: {raw_result.render()},\n\n do not transcribe logos or images.",
                                     },
                                     {
                                         "type": "image_url",