fix: Resolve issue with processing for gpt4 series models (#1485)

<!-- .github/pull_request_template.md -->

## Description
Use JSON_SCHEMA mode only for GPT-5 series models, it's a new mode from
OpenAI for structured output processing that they didn't properly handle
for older models

## Type of Change
<!-- Please check the relevant option -->
- [x] Bug fix (non-breaking change that fixes an issue)
- [ ] New feature (non-breaking change that adds functionality)
- [ ] Breaking change (fix or feature that would cause existing
functionality to change)
- [ ] Documentation update
- [ ] Code refactoring
- [ ] Performance improvement
- [ ] Other (please specify):

## Pre-submission Checklist
<!-- Please check all boxes that apply before submitting your PR -->
- [ ] **I have tested my changes thoroughly before submitting this PR**
- [ ] **This PR contains minimal changes necessary to address the
issue/feature**
- [ ] My code follows the project's coding standards and style
guidelines
- [ ] I have added tests that prove my fix is effective or that my
feature works
- [ ] I have added necessary documentation (if applicable)
- [ ] All new and existing tests pass
- [ ] I have searched existing PRs to ensure this change hasn't been
submitted already
- [ ] I have linked any relevant issues in the description
- [ ] My commits have clear and descriptive messages

## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.

cognee/infrastructure/llm/structured_output_framework/litellm_instructor/llm/openai/adapter.py

@@ -73,10 +73,19 @@ class OpenAIAdapter(LLMInterface):
         fallback_api_key: str = None,
         fallback_endpoint: str = None,
     ):
-        self.aclient = instructor.from_litellm(
-            litellm.acompletion, mode=instructor.Mode.JSON_SCHEMA
-        )
-        self.client = instructor.from_litellm(litellm.completion, mode=instructor.Mode.JSON_SCHEMA)
+        # TODO: With gpt5 series models OpenAI expects JSON_SCHEMA as a mode for structured outputs.
+        #       Make sure all new gpt models will work with this mode as well.
+        if "gpt-5" in model:
+            self.aclient = instructor.from_litellm(
+                litellm.acompletion, mode=instructor.Mode.JSON_SCHEMA
+            )
+            self.client = instructor.from_litellm(
+                litellm.completion, mode=instructor.Mode.JSON_SCHEMA
+            )
+        else:
+            self.aclient = instructor.from_litellm(litellm.acompletion)
+            self.client = instructor.from_litellm(litellm.completion)
+
         self.transcription_model = transcription_model
         self.model = model
         self.api_key = api_key