mirror of
https://github.com/infiniflow/ragflow.git
synced 2025-09-25 16:16:01 +00:00
340354b79c
### What problem does this PR solve? [https://github.com/infiniflow/ragflow/issues/8324](url) docker image version: v0.19.1 The `_clean_conf` function was not implemented in the `_chat` and `chat_streamly` methods of the `GeminiChat` class, causing the error "Unknown field for GenerationConfig: max_tokens" when the default LLM config includes the "max_tokens" parameter. **Buggy Code(ragflow/rag/llm/chat_model.py)** ```python class GeminiChat(Base): def __init__(self, key, model_name, base_url=None, **kwargs): super().__init__(key, model_name, base_url=base_url, **kwargs) from google.generativeai import GenerativeModel, client client.configure(api_key=key) _client = client.get_default_generative_client() self.model_name = "models/" + model_name self.model = GenerativeModel(model_name=self.model_name) self.model._client = _client def _clean_conf(self, gen_conf): for k in list(gen_conf.keys()): if k not in ["temperature", "top_p"]: del gen_conf[k] return gen_conf def _chat(self, history, gen_conf): from google.generativeai.types import content_types system = history[0]["content"] if history and history[0]["role"] == "system" else "" hist = [] for item in history: if item["role"] == "system": continue hist.append(deepcopy(item)) item = hist[-1] if "role" in item and item["role"] == "assistant": item["role"] = "model" if "role" in item and item["role"] == "system": item["role"] = "user" if "content" in item: item["parts"] = item.pop("content") if system: self.model._system_instruction = content_types.to_content(system) response = self.model.generate_content(hist, generation_config=gen_conf) ans = response.text return ans, response.usage_metadata.total_token_count def chat_streamly(self, system, history, gen_conf): from google.generativeai.types import content_types if system: self.model._system_instruction = content_types.to_content(system) #❌_clean_conf was not implemented for k in list(gen_conf.keys()): if k not in ["temperature", "top_p", "max_tokens"]: del gen_conf[k] for item in history: if "role" in item and item["role"] == "assistant": item["role"] = "model" if "content" in item: item["parts"] = item.pop("content") ans = "" try: response = self.model.generate_content(history, generation_config=gen_conf, stream=True) for resp in response: ans = resp.text yield ans yield response._chunks[-1].usage_metadata.total_token_count except Exception as e: yield ans + "\n**ERROR**: " + str(e) yield 0 ``` **Implement the _clean_conf function** ```python class GeminiChat(Base): def __init__(self, key, model_name, base_url=None, **kwargs): super().__init__(key, model_name, base_url=base_url, **kwargs) from google.generativeai import GenerativeModel, client client.configure(api_key=key) _client = client.get_default_generative_client() self.model_name = "models/" + model_name self.model = GenerativeModel(model_name=self.model_name) self.model._client = _client def _clean_conf(self, gen_conf): for k in list(gen_conf.keys()): if k not in ["temperature", "top_p"]: del gen_conf[k] return gen_conf def _chat(self, history, gen_conf): from google.generativeai.types import content_types #✅ implement _clean_conf to remove the wrong parameters gen_conf = self._clean_conf(gen_conf) system = history[0]["content"] if history and history[0]["role"] == "system" else "" hist = [] for item in history: if item["role"] == "system": continue hist.append(deepcopy(item)) item = hist[-1] if "role" in item and item["role"] == "assistant": item["role"] = "model" if "role" in item and item["role"] == "system": item["role"] = "user" if "content" in item: item["parts"] = item.pop("content") if system: self.model._system_instruction = content_types.to_content(system) response = self.model.generate_content(hist, generation_config=gen_conf) ans = response.text return ans, response.usage_metadata.total_token_count def chat_streamly(self, system, history, gen_conf): from google.generativeai.types import content_types #✅ implement _clean_conf to remove the wrong parameters gen_conf = self._clean_conf(gen_conf) if system: self.model._system_instruction = content_types.to_content(system) #✅Removed duplicate parameter filtering logic "for k in list(gen_conf.keys()):" for item in history: if "role" in item and item["role"] == "assistant": item["role"] = "model" if "content" in item: item["parts"] = item.pop("content") ans = "" try: response = self.model.generate_content(history, generation_config=gen_conf, stream=True) for resp in response: ans = resp.text yield ans yield response._chunks[-1].usage_metadata.total_token_count except Exception as e: yield ans + "\n**ERROR**: " + str(e) yield 0 ``` ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue) --------- Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>