auto-coder 0.1.187__py3-none-any.whl → 0.1.189__py3-none-any.whl

{auto_coder-0.1.187.dist-info → auto_coder-0.1.189.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: auto-coder
-Version: 0.1.187
+Version: 0.1.189
 Summary: AutoCoder: AutoCoder
 Author: allwefantasy
 Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
@@ -26,7 +26,7 @@ Requires-Dist: tabulate
 Requires-Dist: jupyter-client
 Requires-Dist: prompt-toolkit
 Requires-Dist: tokenizers
-Requires-Dist: byzerllm[saas] >=0.1.137
+Requires-Dist: byzerllm[saas] >=0.1.138
 Requires-Dist: patch
 Requires-Dist: diff-match-patch
 Requires-Dist: GitPython

{auto_coder-0.1.187.dist-info → auto_coder-0.1.189.dist-info}/RECORD

@@ -1,13 +1,13 @@
 autocoder/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 autocoder/auto_coder.py,sha256=tSNXFMJSrffagFi4egZJp8XZH9trSCwQjOdXKyHVqwo,37106
 autocoder/auto_coder_lang.py,sha256=Rtupq6N3_HT7JRhDKdgCBcwRaiAnyCOR_Gsp4jUomrI,3229
-autocoder/auto_coder_rag.py,sha256=EsUR48qiW9gxoN0Bc_zELtLLpA7nNKGnAS4-DmTv0R0,16408
+autocoder/auto_coder_rag.py,sha256=GFPp02FE8x14pmmRxIpbkdx5ll-zYyPK3SACjhSeZ8A,16578
 autocoder/auto_coder_server.py,sha256=qRY88mkBnqSGFDcwYE5gwpe2WPhIw1nEH6LdbjCQhQk,20306
 autocoder/chat_auto_coder.py,sha256=1jCx-J83mj_8JnojYSTfPjYide-thbmsFbr12E_kgcQ,81773
 autocoder/chat_auto_coder_lang.py,sha256=QYtu5gWEQmWKVovR_qUZ8plySZarNFX_Onk-1vN9IiA,8524
 autocoder/command_args.py,sha256=ftWw6HnFUZPiQPt1oV-SfpHQe69XN3knaFy1lpROBcU,26854
 autocoder/lang.py,sha256=e-07rYTgimpxS8sm-AxKSmH4kKQX4N05YFHJBg9trVs,12598
-autocoder/version.py,sha256=eFC6_uO8qUnYHjch9ljwwGRsBsamPqNnAO0JPrxjgE8,23
+autocoder/version.py,sha256=nsvyU8Y0k8OLDacF-I4MlHVaJQan-Qhexb6JJR0ZyT4,23
 autocoder/agent/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 autocoder/agent/auto_tool.py,sha256=DBzip-P_T6ZtT2eHexPcusmKYD0h7ufzp7TLwXAY10E,11554
 autocoder/agent/coder.py,sha256=dnITYHqkcOip8zV4lywbkYNH9w7Q3qyYaUArJ4WPrTs,866
@@ -17,7 +17,7 @@ autocoder/agent/project_reader.py,sha256=-MWRqsr7O4mvU0PIpAhOUBb29htZAvA37pa_GeE
 autocoder/chat/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 autocoder/common/JupyterClient.py,sha256=O-wi6pXeAEYhAY24kDa0BINrLYvKS6rKyWe98pDClS0,2816
 autocoder/common/ShellClient.py,sha256=fM1q8t_XMSbLBl2zkCNC2J9xuyKN3eXzGm6hHhqL2WY,2286
-autocoder/common/__init__.py,sha256=luP0Rl-dFwlZjj56MOs51EHWCIEk6QnrjWN3CGTwFcw,10469
+autocoder/common/__init__.py,sha256=CceR1pHKhPPl-y_vHgjf-p8pe4xgeOI_CTjkUrTN2hM,10510
 autocoder/common/anything2images.py,sha256=0ILBbWzY02M-CiWB-vzuomb_J1hVdxRcenAfIrAXq9M,25283
 autocoder/common/audio.py,sha256=Kn9nWKQddWnUrAz0a_ZUgjcu4VUU_IcZBigT7n3N3qc,7439
 autocoder/common/cleaner.py,sha256=NU72i8C6o9m0vXExab7nao5bstBUsfJFcj11cXa9l4U,1089
@@ -62,7 +62,7 @@ autocoder/rag/api_server.py,sha256=zokIlDJlk7ucRorSLQm80uICO1mecfmn4J2zVqEBskE,6
 autocoder/rag/doc_filter.py,sha256=Ha0Yae_G_hF72YzvrO7NoDZcG18K4hRcqGAEqfrIwAs,9330
 autocoder/rag/document_retriever.py,sha256=_jCbCEX0I-5UPWuHocESaWHatQcv1r_DqA0yOfOAiZ0,9092
 autocoder/rag/llm_wrapper.py,sha256=xRbTBpLUH43Ah5jplL8WWWU-kjKfNgEJoUntLGBq5F4,2484
-autocoder/rag/long_context_rag.py,sha256=C01LYNk0nDRDeMpBkroWMZcLCcD2JlOvUEOLOndC3XI,22129
+autocoder/rag/long_context_rag.py,sha256=tBWJVW4djvPxikOxOUm4nR_bdor1Lfmoig4-XYZ2xDc,22242
 autocoder/rag/rag_config.py,sha256=8LwFcTd8OJWWwi1_WY4IzjqgtT6RyE2j4PjxS5cCTDE,802
 autocoder/rag/rag_entry.py,sha256=V1RJ8RGqM30DNPmzymv64rZjNRGWn6kfc8sRy_LECg0,2451
 autocoder/rag/raw_rag.py,sha256=yS2Ur6kG0IRjhCj2_VonwxjY_xls_E62jO5Gz5j2nqE,2952
@@ -101,9 +101,9 @@ autocoder/utils/request_event_queue.py,sha256=r3lo5qGsB1dIjzVQ05dnr0z_9Z3zOkBdP1
 autocoder/utils/request_queue.py,sha256=nwp6PMtgTCiuwJI24p8OLNZjUiprC-TsefQrhMI-yPE,3889
 autocoder/utils/rest.py,sha256=3tXA8KZG6jKz_tddHNLGx77Icee88WcUeesfNsgPno4,8790
 autocoder/utils/tests.py,sha256=BqphrwyycGAvs-5mhH8pKtMZdObwhFtJ5MC_ZAOiLq8,1340
-auto_coder-0.1.187.dist-info/LICENSE,sha256=HrhfyXIkWY2tGFK11kg7vPCqhgh5DcxleloqdhrpyMY,11558
-auto_coder-0.1.187.dist-info/METADATA,sha256=3VUP6MJh-ZxgNoT7FASzF-VqmFqPmxD75v2DurycKhA,2352
-auto_coder-0.1.187.dist-info/WHEEL,sha256=GV9aMThwP_4oNCtvEC2ec3qUYutgWeAzklro_0m4WJQ,91
-auto_coder-0.1.187.dist-info/entry_points.txt,sha256=0nzHtHH4pNcM7xq4EBA2toS28Qelrvcbrr59GqD_0Ak,350
-auto_coder-0.1.187.dist-info/top_level.txt,sha256=Jqc0_uJSw2GwoFQAa9iJxYns-2mWla-9ok_Y3Gcznjk,10
-auto_coder-0.1.187.dist-info/RECORD,,
+auto_coder-0.1.189.dist-info/LICENSE,sha256=HrhfyXIkWY2tGFK11kg7vPCqhgh5DcxleloqdhrpyMY,11558
+auto_coder-0.1.189.dist-info/METADATA,sha256=283-6tH5ORiOAVCGzI-j5QXMvamNveZnIxo6UhGzHfE,2352
+auto_coder-0.1.189.dist-info/WHEEL,sha256=GV9aMThwP_4oNCtvEC2ec3qUYutgWeAzklro_0m4WJQ,91
+auto_coder-0.1.189.dist-info/entry_points.txt,sha256=0nzHtHH4pNcM7xq4EBA2toS28Qelrvcbrr59GqD_0Ak,350
+auto_coder-0.1.189.dist-info/top_level.txt,sha256=Jqc0_uJSw2GwoFQAa9iJxYns-2mWla-9ok_Y3Gcznjk,10
+auto_coder-0.1.189.dist-info/RECORD,,

autocoder/auto_coder_rag.py

@@ -261,6 +261,12 @@ def main(input_args: Optional[List[str]] = None):
         action="store_true",
         help="Enable slow inference without deep thought",
     )
+    serve_parser.add_argument(
+        "--inference_compute_precision",
+        type=int,
+        default=6,
+        help="The precision of the inference compute",
+    )
 
     serve_parser.add_argument(
         "--enable_hybrid_index",

autocoder/common/__init__.py

@@ -317,6 +317,7 @@ class AutoCoderArgs(pydantic.BaseModel):
     disable_inference_enhance: Optional[bool] = False
     inference_deep_thought: Optional[bool] = False
     inference_slow_without_deep_thought: Optional[bool] = False
+    inference_compute_precision: int = 6
     without_contexts: Optional[bool] = False
 
     class Config:

autocoder/rag/long_context_rag.py

@@ -524,11 +524,12 @@ class LongContextRAG:
                 f"Start to send to model {target_model} with {request_tokens} tokens"
             )
 
-            if LLMComputeEngine is not None:
+            if LLMComputeEngine is not None and not self.args.disable_inference_enhance:
                 llm_compute_engine = LLMComputeEngine(
                     llm=self.llm,
                     inference_enhance=not self.args.disable_inference_enhance,
                     inference_deep_thought=self.args.inference_deep_thought,
+                    precision=self.args.inference_compute_precision,
                     debug=False,
                 )
                 new_conversations = llm_compute_engine.process_conversation(

autocoder/version.py

@@ -1 +1 @@
-__version__ = "0.1.187"
+__version__ = "0.1.189"