Spaces:
Runtime error
Runtime error
| # Copyright 2025 Google LLC | |
| # | |
| # Licensed under the Apache License, Version 2.0 (the "License"); | |
| # you may not use this file except in compliance with the License. | |
| # You may obtain a copy of the License at | |
| # | |
| # http://www.apache.org/licenses/LICENSE-2.0 | |
| # | |
| # Unless required by applicable law or agreed to in writing, software | |
| # distributed under the License is distributed on an "AS IS" BASIS, | |
| # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | |
| # See the License for the specific language governing permissions and | |
| # limitations under the License. | |
| """Gemini simulation module to match the original cache key signatures.""" | |
| from cache_manager import intake_cache as cache | |
| from llm_client import gemma_roleplay | |
| def gemini_get_text_response( | |
| prompt: str, | |
| stop_sequences: list = None, | |
| temperature: float = 0.1, | |
| max_output_tokens: int = 4000, | |
| top_p: float = 0.8, | |
| top_k: int = 10, | |
| ): | |
| """Checks cache first via memoization. On cache miss, calls Gemma roleplay.""" | |
| messages = [{"role": "user", "content": prompt}] | |
| return gemma_roleplay.chat_completion( | |
| messages=messages, | |
| temperature=temperature, | |
| max_tokens=max_output_tokens, | |
| stream=False, | |
| ) | |