Skip to content

Commit 89bd449

Browse files
zakahanzakahan
authored
fix: veadk tutorial & tls header (#201)
* fix: veadk_tutorial database * fix: veadk_tutorial cli remove * feat: tls header * fix: MODEL_EMBEDDING_API_BASE * fix: fix app_name
1 parent 48e61f5 commit 89bd449

File tree

2 files changed

+25
-82
lines changed

2 files changed

+25
-82
lines changed

‎veadk/tracing/telemetry/exporters/tls_exporter.py‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -51,6 +51,7 @@ def model_post_init(self, context: Any) -> None:
5151
"x-tls-otel-ak": self.config.access_key,
5252
"x-tls-otel-sk": self.config.secret_key,
5353
"x-tls-otel-region": self.config.region,
54+
"TraceTag": "veadk",
5455
}
5556
self.headers |= headers
5657

‎veadk_tutorial.ipynb‎

Lines changed: 24 additions & 82 deletions
Original file line numberDiff line numberDiff line change
@@ -479,35 +479,14 @@
479479
]
480480
},
481481
{
482+
"metadata": {},
482483
"cell_type": "markdown",
483-
"metadata": {
484-
"id": "_s35YbMcpXfd"
485-
},
486-
"source": [
487-
"VeADK 还支持你将短期记忆持久化存储在云端，未来的某一时刻你可以加载历史对话。\n",
488-
"\n",
489-
"在使用云端记忆之前，需要安装`database`相关的依赖："
490-
]
491-
},
492-
{
493-
"cell_type": "code",
494-
"execution_count": null,
495-
"metadata": {
496-
"id": "3J7csxCJt9H1"
497-
},
498-
"outputs": [],
499-
"source": [
500-
"%pip install veadk-python[database] --quiet"
501-
]
484+
"source": "VeADK 还支持你将短期记忆持久化存储在云端，未来的某一时刻你可以加载历史对话。"
502485
},
503486
{
487+
"metadata": {},
504488
"cell_type": "markdown",
505-
"metadata": {
506-
"id": "VWTlOcEJwBrh"
507-
},
508-
"source": [
509-
"使用 MySQL 作为短期记忆的数据库后端："
510-
]
489+
"source": "使用 MySQL 作为短期记忆的数据库后端："
511490
},
512491
{
513492
"cell_type": "code",
@@ -583,10 +562,7 @@
583562
"metadata": {
584563
"id": "k9wKEHeYxIUT"
585564
},
586-
"source": [
587-
"在使用记忆之前，需要安装`database`相关的依赖：\n",
588-
"\n"
589-
]
565+
"source": "如果您使用知识库、长期记忆等进阶功能，请进一步安装 veadk-python 中的扩展包："
590566
},
591567
{
592568
"cell_type": "code",
@@ -595,9 +571,7 @@
595571
"id": "VZIeRU1QxHrk"
596572
},
597573
"outputs": [],
598-
"source": [
599-
"%pip install veadk-python[database] --quiet"
600-
]
574+
"source": "%pip install veadk-python[extensions] --quiet"
601575
},
602576
{
603577
"cell_type": "markdown",
@@ -628,7 +602,7 @@
628602
"# 设置访问火山方舟的 Embedding 模型\n",
629603
"os.environ[\"MODEL_EMBEDDING_NAME\"] = \"doubao-embedding-text-240715\"\n",
630604
"os.environ[\"MODEL_EMBEDDING_API_BASE\"] = (\n",
631-
" \"https://ark.cn-beijing.volces.com/api/v3/embeddings\"\n",
605+
" \"https://ark.cn-beijing.volces.com/api/v3/\"\n",
632606
")\n",
633607
"os.environ[\"MODEL_EMBEDDING_DIM\"] = \"2560\"\n",
634608
"os.environ[\"MODEL_EMBEDDING_API_KEY\"] = \"\""
@@ -663,7 +637,7 @@
663637
"\n",
664638
"# 初始化一个长期记忆，采用 OpenSearch 向量化存储\n",
665639
"# 长期记忆是跨 Session 的\n",
666-
"long_term_memory = LongTermMemory(backend=\"opensearch\")\n",
640+
"long_term_memory = LongTermMemory(backend=\"opensearch\", app_name=app_name, user_id=user_id)\n",
667641
"\n",
668642
"agent = Agent(long_term_memory=long_term_memory)\n",
669643
"\n",
@@ -735,7 +709,7 @@
735709
"\n",
736710
"# 初始化一个长期记忆，采用 Viking Memory 存储\n",
737711
"# 长期记忆是跨 Session 的\n",
738-
"long_term_memory = LongTermMemory(backend=\"viking\")\n",
712+
"long_term_memory = LongTermMemory(backend=\"viking\", app_name=app_name, user_id=user_id)\n",
739713
"\n",
740714
"agent = Agent(long_term_memory=long_term_memory)\n",
741715
"\n",
@@ -809,9 +783,7 @@
809783
"metadata": {
810784
"id": "_jZauBoRztaU"
811785
},
812-
"source": [
813-
"由于知识库需要用到云端的向量化存储，因此在使用知识库之前，需要安装`database`相关的依赖："
814-
]
786+
"source": "如果您使用知识库、长期记忆等进阶功能，请进一步安装 veadk-python 中的扩展包："
815787
},
816788
{
817789
"cell_type": "code",
@@ -820,9 +792,7 @@
820792
"id": "xuozqr1Hzwjz"
821793
},
822794
"outputs": [],
823-
"source": [
824-
"%pip install veadk-python[database] --quiet"
825-
]
795+
"source": "%pip install veadk-python[extensions] --quiet"
826796
},
827797
{
828798
"cell_type": "markdown",
@@ -852,7 +822,7 @@
852822
"# 设置访问火山方舟的 Embedding 模型\n",
853823
"os.environ[\"MODEL_EMBEDDING_NAME\"] = \"doubao-embedding-text-240715\"\n",
854824
"os.environ[\"MODEL_EMBEDDING_API_BASE\"] = (\n",
855-
" \"https://ark.cn-beijing.volces.com/api/v3/embeddings\"\n",
825+
" \"https://ark.cn-beijing.volces.com/api/v3/\"\n",
856826
")\n",
857827
"os.environ[\"MODEL_EMBEDDING_DIM\"] = \"2560\"\n",
858828
"os.environ[\"MODEL_EMBEDDING_API_KEY\"] = \"\""
@@ -913,8 +883,6 @@
913883
}
914884
],
915885
"source": [
916-
"import os\n",
917-
"\n",
918886
"from veadk import Agent, Runner\n",
919887
"from veadk.knowledgebase.knowledgebase import KnowledgeBase\n",
920888
"from veadk.memory.short_term_memory import ShortTermMemory\n",
@@ -923,14 +891,9 @@
923891
"user_id = \"veadk_playground_user\"\n",
924892
"session_id = \"veadk_playground_session\"\n",
925893
"\n",
926-
"if os.path.exists(knowledgebase_file):\n",
927-
" with open(knowledgebase_file, \"r\", encoding=\"utf-8\") as f:\n",
928-
" knowledgebase_data = [\n",
929-
" line.strip() for line in f if line.strip()\n",
930-
" ] # 手动切片文档内容\n",
931894
"\n",
932-
"knowledgebase = KnowledgeBase(backend=\"opensearch\") # 指定 opensearch 后端\n",
933-
"knowledgebase.add(knowledgebase_data, app_name=app_name)\n",
895+
"knowledgebase = KnowledgeBase(backend=\"opensearch\", app_name=app_name) # 指定 opensearch 后端\n",
896+
"knowledgebase.add_from_files(files=[knowledgebase_file])\n",
934897
"\n",
935898
"agent = Agent(knowledgebase=knowledgebase)\n",
936899
"\n",
@@ -1025,10 +988,9 @@
1025988
"user_id = \"veadk_playground_user\"\n",
1026989
"session_id = \"veadk_playground_session\"\n",
1027990
"\n",
1028-
"knowledgebase = KnowledgeBase(backend=\"viking\") # 指定 viking 后端\n",
991+
"knowledgebase = KnowledgeBase(backend=\"viking\", app_name=app_name) # 指定 viking 后端\n",
1029992
"\n",
1030-
"with open(pdf_path, \"rb\") as f:\n",
1031-
" knowledgebase.add(f, app_name=app_name) # 直接添加文档，无需手动切片\n",
993+
"knowledgebase.add_from_files(files=[pdf_path]) # 直接添加文档，无需手动切片\n",
1032994
"\n",
1033995
"agent = Agent(knowledgebase=knowledgebase)"
1034996
]
@@ -1632,8 +1594,8 @@
16321594
"</pre>\n"
16331595
],
16341596
"text/plain": [
1635-
"✨ You're running DeepEval's latest \u001b[38;2;106;0;255mBase Evaluation \u001b[0m\u001b[1;38;2;106;0;255m[\u001b[0m\u001b[38;2;106;0;255mGEval\u001b[0m\u001b[1;38;2;106;0;255m]\u001b[0m\u001b[38;2;106;0;255m Metric\u001b[0m! \u001b[1;38;2;55;65;81m(\u001b[0m\u001b[38;2;55;65;81musing \u001b[0m\u001b[3;38;2;55;65;81mNone\u001b[0m\u001b[38;2;55;65;81m \u001b[0m\u001b[1;38;2;55;65;81m(\u001b[0m\u001b[38;2;55;65;81mLocal Model\u001b[0m\u001b[1;38;2;55;65;81m)\u001b[0m\u001b[38;2;55;65;81m, \u001b[0m\u001b[38;2;55;65;81mstrict\u001b[0m\u001b[38;2;55;65;81m=\u001b[0m\u001b[3;38;2;55;65;81mFalse\u001b[0m\u001b[38;2;55;65;81m, \u001b[0m\n",
1636-
"\u001b[38;2;55;65;81masync_mode\u001b[0m\u001b[38;2;55;65;81m=\u001b[0m\u001b[3;38;2;55;65;81mTrue\u001b[0m\u001b[1;38;2;55;65;81m)\u001b[0m\u001b[38;2;55;65;81m...\u001b[0m\n"
1597+
"✨ You're running DeepEval's latest \u001B[38;2;106;0;255mBase Evaluation \u001B[0m\u001B[1;38;2;106;0;255m[\u001B[0m\u001B[38;2;106;0;255mGEval\u001B[0m\u001B[1;38;2;106;0;255m]\u001B[0m\u001B[38;2;106;0;255m Metric\u001B[0m! \u001B[1;38;2;55;65;81m(\u001B[0m\u001B[38;2;55;65;81musing \u001B[0m\u001B[3;38;2;55;65;81mNone\u001B[0m\u001B[38;2;55;65;81m \u001B[0m\u001B[1;38;2;55;65;81m(\u001B[0m\u001B[38;2;55;65;81mLocal Model\u001B[0m\u001B[1;38;2;55;65;81m)\u001B[0m\u001B[38;2;55;65;81m, \u001B[0m\u001B[38;2;55;65;81mstrict\u001B[0m\u001B[38;2;55;65;81m=\u001B[0m\u001B[3;38;2;55;65;81mFalse\u001B[0m\u001B[38;2;55;65;81m, \u001B[0m\n",
1598+
"\u001B[38;2;55;65;81masync_mode\u001B[0m\u001B[38;2;55;65;81m=\u001B[0m\u001B[3;38;2;55;65;81mTrue\u001B[0m\u001B[1;38;2;55;65;81m)\u001B[0m\u001B[38;2;55;65;81m...\u001B[0m\n"
16371599
]
16381600
},
16391601
"metadata": {},
@@ -1646,7 +1608,7 @@
16461608
"</pre>\n"
16471609
],
16481610
"text/plain": [
1649-
"✨ You're running DeepEval's latest \u001b[38;2;106;0;255mTool Correctness Metric\u001b[0m! \u001b[1;38;2;55;65;81m(\u001b[0m\u001b[38;2;55;65;81musing \u001b[0m\u001b[3;38;2;55;65;81mNone\u001b[0m\u001b[38;2;55;65;81m, \u001b[0m\u001b[38;2;55;65;81mstrict\u001b[0m\u001b[38;2;55;65;81m=\u001b[0m\u001b[3;38;2;55;65;81mFalse\u001b[0m\u001b[38;2;55;65;81m, \u001b[0m\u001b[38;2;55;65;81masync_mode\u001b[0m\u001b[38;2;55;65;81m=\u001b[0m\u001b[3;38;2;55;65;81mTrue\u001b[0m\u001b[1;38;2;55;65;81m)\u001b[0m\u001b[38;2;55;65;81m...\u001b[0m\n"
1611+
"✨ You're running DeepEval's latest \u001B[38;2;106;0;255mTool Correctness Metric\u001B[0m! \u001B[1;38;2;55;65;81m(\u001B[0m\u001B[38;2;55;65;81musing \u001B[0m\u001B[3;38;2;55;65;81mNone\u001B[0m\u001B[38;2;55;65;81m, \u001B[0m\u001B[38;2;55;65;81mstrict\u001B[0m\u001B[38;2;55;65;81m=\u001B[0m\u001B[3;38;2;55;65;81mFalse\u001B[0m\u001B[38;2;55;65;81m, \u001B[0m\u001B[38;2;55;65;81masync_mode\u001B[0m\u001B[38;2;55;65;81m=\u001B[0m\u001B[3;38;2;55;65;81mTrue\u001B[0m\u001B[1;38;2;55;65;81m)\u001B[0m\u001B[38;2;55;65;81m...\u001B[0m\n"
16501612
]
16511613
},
16521614
"metadata": {},
@@ -1727,14 +1689,14 @@
17271689
"text/plain": [
17281690
"\n",
17291691
"\n",
1730-
"\u001b[38;2;5;245;141m✓\u001b[0m Evaluation completed 🎉! \u001b[1m(\u001b[0mtime taken: \u001b[1;36m24.\u001b[0m09s | token cost: \u001b[1;36m0.0\u001b[0m USD\u001b[1m)\u001b[0m\n",
1731-
"» Test Results \u001b[1m(\u001b[0m\u001b[1;36m1\u001b[0m total tests\u001b[1m)\u001b[0m:\n",
1732-
" » Pass Rate: \u001b[1;36m100.0\u001b[0m% | Passed: \u001b[1;32m1\u001b[0m | Failed: \u001b[1;31m0\u001b[0m\n",
1692+
"\u001B[38;2;5;245;141m✓\u001B[0m Evaluation completed 🎉! \u001B[1m(\u001B[0mtime taken: \u001B[1;36m24.\u001B[0m09s | token cost: \u001B[1;36m0.0\u001B[0m USD\u001B[1m)\u001B[0m\n",
1693+
"» Test Results \u001B[1m(\u001B[0m\u001B[1;36m1\u001B[0m total tests\u001B[1m)\u001B[0m:\n",
1694+
" » Pass Rate: \u001B[1;36m100.0\u001B[0m% | Passed: \u001B[1;32m1\u001B[0m | Failed: \u001B[1;31m0\u001B[0m\n",
17331695
"\n",
17341696
" ================================================================================ \n",
17351697
"\n",
17361698
"» What to share evals with your team, or a place for your test cases to live? ❤️ 🏡\n",
1737-
" » Run \u001b[1;32m'deepeval view'\u001b[0m to analyze and save testing results on \u001b[38;2;106;0;255mConfident AI\u001b[0m.\n",
1699+
" » Run \u001B[1;32m'deepeval view'\u001B[0m to analyze and save testing results on \u001B[38;2;106;0;255mConfident AI\u001B[0m.\n",
17381700
"\n",
17391701
"\n"
17401702
]
@@ -1923,26 +1885,6 @@
19231885
"## 云端部署"
19241886
]
19251887
},
1926-
{
1927-
"cell_type": "markdown",
1928-
"metadata": {
1929-
"id": "bejpQneN6XxA"
1930-
},
1931-
"source": [
1932-
"为体验部署相关功能，你需要安装依赖包："
1933-
]
1934-
},
1935-
{
1936-
"cell_type": "code",
1937-
"execution_count": null,
1938-
"metadata": {
1939-
"id": "JZQPRAe96W7y"
1940-
},
1941-
"outputs": [],
1942-
"source": [
1943-
"%pip install veadk-python[cli] --quiet"
1944-
]
1945-
},
19461888
{
19471889
"cell_type": "markdown",
19481890
"metadata": {
@@ -2120,7 +2062,7 @@
21202062
},
21212063
"language_info": {
21222064
"name": "python",
2123-
"version": "3.10.18"
2065+
"version": "3.10.17"
21242066
}
21252067
},
21262068
"nbformat": 4,

0 commit comments

Comments
 (0)