auto-coder 0.1.208__py3-none-any.whl → 0.1.209__py3-none-any.whl

{auto_coder-0.1.208.dist-info → auto_coder-0.1.209.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: auto-coder
-Version: 0.1.208
+Version: 0.1.209
 Summary: AutoCoder: AutoCoder
 Author: allwefantasy
 Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
@@ -69,13 +69,14 @@ Auto-Coder (powered by Byzer-LLM)
 </h3>
 
 <p align="center">
-| <a href="./docs/en"><b>English</b></a> | <a href="https://uelng8wukz.feishu.cn/wiki/QIpkwpQo2iSdkwk9nP6cNSPlnPc"><b>中文</b></a> |
+<a href="https://uelng8wukz.feishu.cn/wiki/QIpkwpQo2iSdkwk9nP6cNSPlnPc"><b>中文</b></a> |
 
 </p>
 
 ---
 
 *Latest News* 🔥
+- [2025/01] Release Auto-Coder 0.1.208
 - [2024/09] Release Auto-Coder 0.1.163
 - [2024/08] Release Auto-Coder 0.1.143
 - [2024/07] Release Auto-Coder 0.1.115

{auto_coder-0.1.208.dist-info → auto_coder-0.1.209.dist-info}/RECORD

@@ -8,7 +8,7 @@ autocoder/chat_auto_coder.py,sha256=zWmkG6b3-18unROg2u7cEkziJlyKIoDYIclW0fWDbCQ,
 autocoder/chat_auto_coder_lang.py,sha256=zU9VRY-l80fZnLJ0Op8A3wq27UhQHh9WcpSYU4SmnqU,8708
 autocoder/command_args.py,sha256=BpMbPceBzjCftPB0yOVsSmTmt61xS3gtc1WGKtcDHQs,30449
 autocoder/lang.py,sha256=U6AjVV8Rs1uLyjFCZ8sT6WWuNUxMBqkXXIOs4S120uk,14511
-autocoder/version.py,sha256=yqXFcZxOknaPmV5zVkh1GSc1MbMk5M2DKocsUSSTP7M,24
+autocoder/version.py,sha256=MoW2qh2N2F6fwWURhZTEXjwmdvPGpyt7_C-0W39jD7A,24
 autocoder/agent/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 autocoder/agent/auto_demand_organizer.py,sha256=NWSAEsEk94vT3lGjfo25kKLMwYdPcpy9e-i21txPasQ,6942
 autocoder/agent/auto_filegroup.py,sha256=CW7bqp0FW1GIEMnl-blyAc2UGT7O9Mom0q66ITz1ckM,6635
@@ -71,7 +71,7 @@ autocoder/rag/api_server.py,sha256=dRbhAZVRAOlZ64Cnxf4_rKb4iJwHnrWS9Zr67IVORw0,7
 autocoder/rag/doc_filter.py,sha256=H0g4s-Q8gJDUbYk9b1qkEyl7RgNzLbRF4UWELVKPDwk,9865
 autocoder/rag/document_retriever.py,sha256=5oThtxukGuRFF96o3pHKsk306a8diXbhgSrbqyU2BvM,8894
 autocoder/rag/llm_wrapper.py,sha256=sbDxCANiZyWb_ocqNgqu2oy3c2t8orPNRGleEs-Uwl8,2649
-autocoder/rag/long_context_rag.py,sha256=5XWXqjIr2z1FNQdQ6BeVAp7VllIHN9V19QuuuNjyFpM,24764
+autocoder/rag/long_context_rag.py,sha256=x8ZPg9cwTdFmz6CIzjA1ZPX7_5k3G-ZleL6v3B9CO6Y,24921
 autocoder/rag/rag_config.py,sha256=8LwFcTd8OJWWwi1_WY4IzjqgtT6RyE2j4PjxS5cCTDE,802
 autocoder/rag/rag_entry.py,sha256=6TKtErZ0Us9XSV6HgRKXA6yR3SiZGPHpynOKSaR1wgE,2463
 autocoder/rag/raw_rag.py,sha256=yS2Ur6kG0IRjhCj2_VonwxjY_xls_E62jO5Gz5j2nqE,2952
@@ -82,17 +82,17 @@ autocoder/rag/token_checker.py,sha256=jc76x6KWmvVxds6W8juZfQGaoErudc2HenG3sNQfSL
 autocoder/rag/token_counter.py,sha256=C-Lwc4oIjJpZDEqp9WLHGOe6hb4yhrdJpMtkrtp_1qc,2125
 autocoder/rag/token_limiter.py,sha256=dtIxCtHswZ2ut-XKbx8_SiWyv-xqnR1WAIcmh6f8Ktw,11137
 autocoder/rag/types.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-autocoder/rag/utils.py,sha256=MOMy0l2_YQ8foWnQQSvYmYAwghAWJ8_wVrdZh5DSaTg,4822
+autocoder/rag/utils.py,sha256=x5L8gskxUUGkVEP5K-0C-iYntE84asuDXOCqdzdNUoA,4956
 autocoder/rag/variable_holder.py,sha256=PFvBjFcR7-fNDD4Vcsc8CpH2Te057vcpwJMxtrfUgKI,75
 autocoder/rag/cache/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 autocoder/rag/cache/base_cache.py,sha256=KxrPKP-PunL7reXh5txT97DYLzGKm9M5O4CnOLDyX-c,403
 autocoder/rag/cache/byzer_storage_cache.py,sha256=LS-Z8x5HBL5u8Zrn0kniFX-tdR1ZsMp8fKoKFluSwuU,15375
 autocoder/rag/cache/file_monitor_cache.py,sha256=ZfWFEzhanwM78sj87dnDWS_mj1SjvK4U_-XdqMZOnhM,4947
-autocoder/rag/cache/simple_cache.py,sha256=Wb6udIAm3R0QO6ouSFDGdUowqvkuqOCHi2ncQNbMZ2U,8857
+autocoder/rag/cache/simple_cache.py,sha256=4ZnDHuQyNDxaJ70_OlRMiuwPbjYId8ZaukTRfKAtzCw,9279
 autocoder/rag/loaders/__init__.py,sha256=EQHEZ5Cmz-mGP2SllUTvcIbYCnF7W149dNpNItfs0yE,304
-autocoder/rag/loaders/docx_loader.py,sha256=FMRwmbACevcjTdhr5slVfXgq6SRoWPlEILMAfmQbQSI,547
+autocoder/rag/loaders/docx_loader.py,sha256=ejonb3OFxeMBEV_qRRh556SrjlBbDIsU7lTuxuXCQXg,610
 autocoder/rag/loaders/excel_loader.py,sha256=Ue8YB1z_kBs8SjIPuBskyM08Q1JiONs_BJZPrzi59oo,896
-autocoder/rag/loaders/pdf_loader.py,sha256=0-42afOpanFZZOFmuTmuu7AqZyzaOsLPnXRlPlHOnoM,650
+autocoder/rag/loaders/pdf_loader.py,sha256=9cLPdhfSiedvEUFFM7I-PkZ-9klJmj8AtuihETfzO_o,706
 autocoder/rag/loaders/ppt_loader.py,sha256=7VEYc-bqgK8VHCoGC3DIUcqbpda-E5jQF9lYLqP256I,1681
 autocoder/rag/stream_event/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 autocoder/rag/stream_event/event_writer.py,sha256=l7kq_LnDDE8E5dZ-73C7J2MgzSL7WrozdXk0eV-k55Q,409
@@ -115,9 +115,9 @@ autocoder/utils/request_event_queue.py,sha256=r3lo5qGsB1dIjzVQ05dnr0z_9Z3zOkBdP1
 autocoder/utils/request_queue.py,sha256=nwp6PMtgTCiuwJI24p8OLNZjUiprC-TsefQrhMI-yPE,3889
 autocoder/utils/rest.py,sha256=HawagAap3wMIDROGhY1730zSZrJR_EycODAA5qOj83c,8807
 autocoder/utils/tests.py,sha256=BqphrwyycGAvs-5mhH8pKtMZdObwhFtJ5MC_ZAOiLq8,1340
-auto_coder-0.1.208.dist-info/LICENSE,sha256=HrhfyXIkWY2tGFK11kg7vPCqhgh5DcxleloqdhrpyMY,11558
-auto_coder-0.1.208.dist-info/METADATA,sha256=zyzXEAoJ0t4iwED4AAmoikyYPg-4RwCg6JFm6Y34YhA,2575
-auto_coder-0.1.208.dist-info/WHEEL,sha256=GV9aMThwP_4oNCtvEC2ec3qUYutgWeAzklro_0m4WJQ,91
-auto_coder-0.1.208.dist-info/entry_points.txt,sha256=0nzHtHH4pNcM7xq4EBA2toS28Qelrvcbrr59GqD_0Ak,350
-auto_coder-0.1.208.dist-info/top_level.txt,sha256=Jqc0_uJSw2GwoFQAa9iJxYns-2mWla-9ok_Y3Gcznjk,10
-auto_coder-0.1.208.dist-info/RECORD,,
+auto_coder-0.1.209.dist-info/LICENSE,sha256=HrhfyXIkWY2tGFK11kg7vPCqhgh5DcxleloqdhrpyMY,11558
+auto_coder-0.1.209.dist-info/METADATA,sha256=W5eS6nakqpiW7JSoDFCgCbqFw8iN4vzzqoYXLOFmgzI,2571
+auto_coder-0.1.209.dist-info/WHEEL,sha256=GV9aMThwP_4oNCtvEC2ec3qUYutgWeAzklro_0m4WJQ,91
+auto_coder-0.1.209.dist-info/entry_points.txt,sha256=0nzHtHH4pNcM7xq4EBA2toS28Qelrvcbrr59GqD_0Ak,350
+auto_coder-0.1.209.dist-info/top_level.txt,sha256=Jqc0_uJSw2GwoFQAa9iJxYns-2mWla-9ok_Y3Gcznjk,10
+auto_coder-0.1.209.dist-info/RECORD,,

autocoder/rag/cache/simple_cache.py

@@ -98,7 +98,10 @@ class AutoCoderRAGAsyncUpdateQueue(BaseCacheManager):
                     process_file_in_multi_process, files_to_process)
 
             for file_info, result in zip(files_to_process, results):
-                self.update_cache(file_info, result)
+                if result:  # 只有当result不为空时才更新缓存
+                    self.update_cache(file_info, result)
+                else:
+                    logger.warning(f"Empty result for file: {file_info[0]}, skipping cache update")
 
             self.write_cache()
 
@@ -138,7 +141,10 @@ class AutoCoderRAGAsyncUpdateQueue(BaseCacheManager):
                     logger.info(f"{file_info[0]} is detected to be updated")
                     try:
                         result = process_file_local(file_info[0])
-                        self.update_cache(file_info, result)
+                        if result:  # 只有当result不为空时才更新缓存
+                            self.update_cache(file_info, result)
+                        else:
+                            logger.warning(f"Empty result for file: {file_info[0]}, skipping cache update")
                     except Exception as e:
                         logger.error(
                             f"SimpleCache Error in process_queue: {e}")

autocoder/rag/loaders/docx_loader.py

@@ -1,7 +1,7 @@
 from io import BytesIO
 import docx2txt
 from autocoder.utils._markitdown import MarkItDown
-
+import traceback
 
 def extract_text_from_docx_old(docx_path):
     with open(docx_path, "rb") as f:
@@ -16,5 +16,6 @@ def extract_text_from_docx(docx_path):
         md_converter = MarkItDown()
         result = md_converter.convert(docx_path)
         return result.text_content
-    except Exception as e:
+    except (BaseException, Exception) as e:
+        traceback.print_exc()
         return extract_text_from_docx_old(docx_path)

autocoder/rag/loaders/pdf_loader.py

@@ -1,6 +1,7 @@
 from io import BytesIO
 from pypdf import PdfReader
 from autocoder.utils._markitdown import MarkItDown
+import traceback
 
 
 def extract_text_from_pdf_old(file_path):
@@ -18,5 +19,6 @@ def extract_text_from_pdf(file_path):
         md_converter = MarkItDown()
         result = md_converter.convert(file_path)
         return result.text_content
-    except Exception as e:        
+    except (BaseException, Exception) as e:
+        traceback.print_exc()
         return extract_text_from_pdf_old(file_path)

autocoder/rag/long_context_rag.py

@@ -182,19 +182,25 @@ class LongContextRAG:
         使用以下文档和对话历史来提取相关信息。
 
         文档：
+        <documents>
         {% for doc in documents %}
         {{ doc }}
         {% endfor %}
+        </documents>
 
         对话历史：
+        <conversations>
         {% for msg in conversations %}
-        <{{ msg.role }}>: {{ msg.content }}
+        [{{ msg.role }}]: 
+        {{ msg.content }}
+        
         {% endfor %}
+        </conversations>
 
         请根据提供的文档内容、用户对话历史以及最后一个问题，提取并总结文档中与问题相关的重要信息。
         如果文档中没有相关信息，请回复"该文档中没有与问题相关的信息"。
         提取的信息尽量保持和原文中的一样，并且只输出这些信息。
-        """
+        """        
 
     @byzerllm.prompt()
     def _answer_question(
@@ -202,9 +208,11 @@ class LongContextRAG:
     ) -> Generator[str, None, None]:
         """        
         文档：
+        <documents>
         {% for doc in relevant_docs %}
         {{ doc }}
         {% endfor %}
+        </documents>
 
         使用以上文档来回答用户的问题。回答要求：
 

autocoder/rag/utils.py

@@ -9,13 +9,14 @@ import time
 from loguru import logger
 import traceback
 
+
 def process_file_in_multi_process(
     file_info: Tuple[str, str, float]
 ) -> List[SourceCode]:
     start_time = time.time()
     file_path, relative_path, _, _ = file_info
     try:
-        if file_path.endswith(".pdf"):            
+        if file_path.endswith(".pdf"):
             content = extract_text_from_pdf(file_path)
             v = [
                 SourceCode(
@@ -24,7 +25,7 @@ def process_file_in_multi_process(
                     tokens=count_tokens_worker(content),
                 )
             ]
-        elif file_path.endswith(".docx"):            
+        elif file_path.endswith(".docx"):
             content = extract_text_from_docx(file_path)
             v = [
                 SourceCode(
@@ -45,7 +46,8 @@ def process_file_in_multi_process(
             ]
         elif file_path.endswith(".pptx"):
             slides = extract_text_from_ppt(file_path)
-            content = "".join(f"#{slide[0]}\n{slide[1]}\n\n" for slide in slides)
+            content = "".join(
+                f"#{slide[0]}\n{slide[1]}\n\n" for slide in slides)
             v = [
                 SourceCode(
                     module_name=f"##File: {file_path}",
@@ -65,15 +67,16 @@ def process_file_in_multi_process(
             ]
         logger.info(f"Load file {file_path} in {time.time() - start_time}")
         return v
-    except Exception as e:
+    except (BaseException, Exception) as e:
         logger.error(f"Error processing file {file_path}: {str(e)}")
+        logger.error(f"Error type: {type(e).__name__}")
         return []
 
 
 def process_file_local(file_path: str) -> List[SourceCode]:
     start_time = time.time()
     try:
-        if file_path.endswith(".pdf"):            
+        if file_path.endswith(".pdf"):
             content = extract_text_from_pdf(file_path)
             v = [
                 SourceCode(
@@ -82,7 +85,7 @@ def process_file_local(file_path: str) -> List[SourceCode]:
                     tokens=count_tokens(content),
                 )
             ]
-        elif file_path.endswith(".docx"):            
+        elif file_path.endswith(".docx"):
             content = extract_text_from_docx(file_path)
             v = [
                 SourceCode(
@@ -103,7 +106,8 @@ def process_file_local(file_path: str) -> List[SourceCode]:
             ]
         elif file_path.endswith(".pptx"):
             slides = extract_text_from_ppt(file_path)
-            content = "".join(f"#{slide[0]}\n{slide[1]}\n\n" for slide in slides)
+            content = "".join(
+                f"#{slide[0]}\n{slide[1]}\n\n" for slide in slides)
             v = [
                 SourceCode(
                     module_name=f"##File: {file_path}",
@@ -123,7 +127,8 @@ def process_file_local(file_path: str) -> List[SourceCode]:
             ]
         logger.info(f"Load file {file_path} in {time.time() - start_time}")
         return v
-    except Exception as e:
+    except (BaseException, Exception) as e:
         logger.error(f"Error processing file {file_path}: {str(e)}")
+        logger.error(f"Error type: {type(e).__name__}")
         traceback.print_exc()
-        return []
+        return []

autocoder/version.py

@@ -1 +1 @@
-__version__ = "0.1.208"
+__version__ = "0.1.209"