From 1bff478fcc827af8ddd8d4ffe1ee4e982ea0e1ba Mon Sep 17 00:00:00 2001 From: "github-actions[bot]" Date: Fri, 11 Jul 2025 05:19:35 +0000 Subject: [PATCH] =?UTF-8?q?=F0=9F=A4=96=20=E8=87=AA=E5=8A=A8=E6=A0=BC?= =?UTF-8?q?=E5=BC=8F=E5=8C=96=E4=BB=A3=E7=A0=81=20[skip=20ci]?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- scripts/import_openie.py | 4 +++- scripts/info_extraction.py | 2 +- scripts/log_viewer_optimized.py | 2 +- src/chat/express/exprssion_learner.py | 2 +- src/chat/knowledge/embedding_store.py | 4 ++-- src/chat/memory_system/Hippocampus.py | 2 +- src/chat/planner_actions/action_modifier.py | 2 +- src/chat/replyer/default_generator.py | 2 +- src/chat/utils/typo_generator.py | 2 +- src/config/config_base.py | 2 +- src/mais4u/mais4u_chat/s4u_prompt.py | 2 +- src/tools/not_using/get_knowledge.py | 2 +- 12 files changed, 15 insertions(+), 13 deletions(-) diff --git a/scripts/import_openie.py b/scripts/import_openie.py index fc677877f..1a36fd240 100644 --- a/scripts/import_openie.py +++ b/scripts/import_openie.py @@ -58,7 +58,9 @@ def hash_deduplicate( # 保存去重后的三元组 new_triple_list_data = {} - for _, (raw_paragraph, triple_list) in enumerate(zip(raw_paragraphs.values(), triple_list_data.values())): + for _, (raw_paragraph, triple_list) in enumerate( + zip(raw_paragraphs.values(), triple_list_data.values(), strict=False) + ): # 段落hash paragraph_hash = get_sha256(raw_paragraph) if f"{PG_NAMESPACE}-{paragraph_hash}" in stored_pg_hashes and paragraph_hash in stored_paragraph_hashes: diff --git a/scripts/info_extraction.py b/scripts/info_extraction.py index b9f278325..b7e2b5592 100644 --- a/scripts/info_extraction.py +++ b/scripts/info_extraction.py @@ -174,7 +174,7 @@ def main(): # sourcery skip: comprehension-to-generator, extract-method with ThreadPoolExecutor(max_workers=workers) as executor: future_to_hash = { executor.submit(process_single_text, pg_hash, raw_data, llm_client_list): pg_hash - for pg_hash, raw_data in zip(all_sha256_list, all_raw_datas) + for pg_hash, raw_data in zip(all_sha256_list, all_raw_datas, strict=False) } with Progress( diff --git a/scripts/log_viewer_optimized.py b/scripts/log_viewer_optimized.py index fbf698e87..3a96e4aac 100644 --- a/scripts/log_viewer_optimized.py +++ b/scripts/log_viewer_optimized.py @@ -354,7 +354,7 @@ class VirtualLogDisplay: # 为每个部分应用正确的标签 current_len = 0 - for part, tag_name in zip(parts, tags): + for part, tag_name in zip(parts, tags, strict=False): start_index = f"{start_pos}+{current_len}c" end_index = f"{start_pos}+{current_len + len(part)}c" self.text_widget.tag_add(tag_name, start_index, end_index) diff --git a/src/chat/express/exprssion_learner.py b/src/chat/express/exprssion_learner.py index 9b170d9a3..2d05e51a0 100644 --- a/src/chat/express/exprssion_learner.py +++ b/src/chat/express/exprssion_learner.py @@ -119,7 +119,7 @@ class ExpressionLearner: min_len = min(len(s1), len(s2)) if min_len < 5: return False - same = sum(1 for a, b in zip(s1, s2) if a == b) + same = sum(1 for a, b in zip(s1, s2, strict=False) if a == b) return same / min_len > 0.8 async def learn_and_store_expression(self) -> List[Tuple[str, str, str]]: diff --git a/src/chat/knowledge/embedding_store.py b/src/chat/knowledge/embedding_store.py index 1214611ec..1d887e1fe 100644 --- a/src/chat/knowledge/embedding_store.py +++ b/src/chat/knowledge/embedding_store.py @@ -59,7 +59,7 @@ EMBEDDING_SIM_THRESHOLD = 0.99 def cosine_similarity(a, b): # 计算余弦相似度 - dot = sum(x * y for x, y in zip(a, b)) + dot = sum(x * y for x, y in zip(a, b, strict=False)) norm_a = math.sqrt(sum(x * x for x in a)) norm_b = math.sqrt(sum(x * x for x in b)) if norm_a == 0 or norm_b == 0: @@ -285,7 +285,7 @@ class EmbeddingStore: distances = list(distances.flatten()) result = [ (self.idx2hash[str(int(idx))], float(sim)) - for (idx, sim) in zip(indices, distances) + for (idx, sim) in zip(indices, distances, strict=False) if idx in range(len(self.idx2hash)) ] diff --git a/src/chat/memory_system/Hippocampus.py b/src/chat/memory_system/Hippocampus.py index 29a26f64c..165a6ac45 100644 --- a/src/chat/memory_system/Hippocampus.py +++ b/src/chat/memory_system/Hippocampus.py @@ -819,7 +819,7 @@ class EntorhinalCortex: timestamps = sample_scheduler.get_timestamp_array() # 使用 translate_timestamp_to_human_readable 并指定 mode="normal" readable_timestamps = [translate_timestamp_to_human_readable(ts, mode="normal") for ts in timestamps] - for _, readable_timestamp in zip(timestamps, readable_timestamps): + for _, readable_timestamp in zip(timestamps, readable_timestamps, strict=False): logger.debug(f"回忆往事: {readable_timestamp}") chat_samples = [] for timestamp in timestamps: diff --git a/src/chat/planner_actions/action_modifier.py b/src/chat/planner_actions/action_modifier.py index a2e0066cf..e603fb5a8 100644 --- a/src/chat/planner_actions/action_modifier.py +++ b/src/chat/planner_actions/action_modifier.py @@ -299,7 +299,7 @@ class ActionModifier: task_results = await asyncio.gather(*tasks, return_exceptions=True) # 处理结果并更新缓存 - for _, (action_name, result) in enumerate(zip(task_names, task_results)): + for _, (action_name, result) in enumerate(zip(task_names, task_results, strict=False)): if isinstance(result, Exception): logger.error(f"{self.log_prefix}LLM判定action {action_name} 时出错: {result}") results[action_name] = False diff --git a/src/chat/replyer/default_generator.py b/src/chat/replyer/default_generator.py index 846112305..f62fd719b 100644 --- a/src/chat/replyer/default_generator.py +++ b/src/chat/replyer/default_generator.py @@ -974,7 +974,7 @@ def weighted_sample_no_replacement(items, weights, k) -> list: 2. 不会重复选中同一个元素 """ selected = [] - pool = list(zip(items, weights)) + pool = list(zip(items, weights, strict=False)) for _ in range(min(k, len(pool))): total = sum(w for _, w in pool) r = random.uniform(0, total) diff --git a/src/chat/utils/typo_generator.py b/src/chat/utils/typo_generator.py index 24d65057c..7c373f132 100644 --- a/src/chat/utils/typo_generator.py +++ b/src/chat/utils/typo_generator.py @@ -363,7 +363,7 @@ class ChineseTypoGenerator: else: # 处理多字词的单字替换 word_result = [] - for _, (char, py) in enumerate(zip(word, word_pinyin)): + for _, (char, py) in enumerate(zip(word, word_pinyin, strict=False)): # 词中的字替换概率降低 word_error_rate = self.error_rate * (0.7 ** (len(word) - 1)) diff --git a/src/config/config_base.py b/src/config/config_base.py index 6c414f0b2..129f5a1c0 100644 --- a/src/config/config_base.py +++ b/src/config/config_base.py @@ -94,7 +94,7 @@ class ConfigBase: raise TypeError( f"Expected {len(field_type_args)} items for {field_type.__name__}, got {len(value)}" ) - return tuple(cls._convert_field(item, arg) for item, arg in zip(value, field_type_args)) + return tuple(cls._convert_field(item, arg) for item, arg in zip(value, field_type_args, strict=False)) if field_origin_type is dict: # 检查提供的value是否为dict diff --git a/src/mais4u/mais4u_chat/s4u_prompt.py b/src/mais4u/mais4u_chat/s4u_prompt.py index 13c142e8d..b4d25a1be 100644 --- a/src/mais4u/mais4u_chat/s4u_prompt.py +++ b/src/mais4u/mais4u_chat/s4u_prompt.py @@ -247,7 +247,7 @@ def weighted_sample_no_replacement(items, weights, k) -> list: 2. 不会重复选中同一个元素 """ selected = [] - pool = list(zip(items, weights)) + pool = list(zip(items, weights, strict=False)) for _ in range(min(k, len(pool))): total = sum(w for _, w in pool) r = random.uniform(0, total) diff --git a/src/tools/not_using/get_knowledge.py b/src/tools/not_using/get_knowledge.py index cebb01684..c436d7742 100644 --- a/src/tools/not_using/get_knowledge.py +++ b/src/tools/not_using/get_knowledge.py @@ -54,7 +54,7 @@ class SearchKnowledgeTool(BaseTool): @staticmethod def _cosine_similarity(vec1: List[float], vec2: List[float]) -> float: """计算两个向量之间的余弦相似度""" - dot_product = sum(p * q for p, q in zip(vec1, vec2)) + dot_product = sum(p * q for p, q in zip(vec1, vec2, strict=False)) magnitude1 = math.sqrt(sum(p * p for p in vec1)) magnitude2 = math.sqrt(sum(q * q for q in vec2)) if magnitude1 == 0 or magnitude2 == 0: