tencentcloud-cls-sdk-langchain

腾讯云 CLS（日志服务）LangChain/LangGraph 可观测插件。

自动采集 LangChain/LangGraph 应用的调用链路，生成 6 层 Span 层级模型，直接上报到 CLS。

安装

pip install tencentcloud-cls-sdk-langchain

插件不包含 LangChain/LangGraph 本身，如未安装请先：pip install langchain langgraph langchain-openai

快速接入

1. 配置 CLS 凭据（一次性）

python -m tencentcloud_cls_sdk_langchain.cls_config init

按提示输入 CLS 接入点、Topic ID、SecretId/SecretKey，配置保存到 .env。

2. 代码接入

在应用启动代码中加入 3 行：

from opentelemetry.sdk.trace import TracerProvider
from opentelemetry.sdk.trace.export import BatchSpanProcessor
from tencentcloud_cls_sdk_langchain import LangChainInstrumentor
from tencentcloud_cls_sdk_langchain.cls_cloud_exporter import CLSCloudExporter

provider = TracerProvider()
provider.add_span_processor(BatchSpanProcessor(CLSCloudExporter()))
LangChainInstrumentor().instrument(tracer_provider=provider)

# 下面正常写你的 LangChain/LangGraph 代码，无需任何改动

3. 验证

运行应用后约 30 秒，到 CLS 控制台 → 日志主题 → 检索分析，应能看到 6 类 Span。

Span 层级模型

entry (应用入口)
 └─ session (对话窗口)
     └─ agent (每次提问)
         └─ step (每轮 ReAct)
             ├─ chat (LLM 调用)
             └─ tool (工具调用)

环境变量

配置命令 cls_config init 会自动写入 .env，也可以手动设置：

变量	必填	说明
`CLS_ENDPOINT`	是	CLS API 接入点
`CLS_TOPIC_ID`	是	CLS 日志主题 ID
`CLS_SECRET_ID`	是	腾讯云 SecretId
`CLS_SECRET_KEY`	是	腾讯云 SecretKey
`CLS_SERVICE_NAME`	否	服务名称（默认 `langchain-app`）

License

Apache-2.0

Metadata

Release files for tencentcloud-cls-sdk-langchain 1.0.5

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for tencentcloud-cls-sdk-langchain 1.0.5
File	Size	Uploaded	Provenance
tencentcloud_cls_sdk_langchain-1.0.5.tar.gz	25.6 kB	Jun 30, 2026	Without provenance	Details

Built distribution (wheel)

Table of built distributions (wheels) for tencentcloud-cls-sdk-langchain 1.0.5
File	Interpreter	ABI	Platform	Reset
tencentcloud_cls_sdk_langchain-1.0.5-py3-none-any.whl 28.6 kB Jun 30, 2026 Without provenance	Python 3	none	any	Details

Total release size: 54.2 kB

Release files / tencentcloud_cls_sdk_langchain-1.0.5.tar.gz

Download URL	tencentcloud_cls_sdk_langchain-1.0.5.tar.gz
Size	25.6 kB
Tags	Source
SHA-256 checksum How to use checksums	`973ff0f0126d4f1dadd251f1b66a44df9bb68f2071f7cc74fdc334ff3766d991`
BLAKE2b-256 checksum How to use checksums	`7529067f1634fbbc0a409d4dfc3b1ca917a261b489c3c9a0dff1d91225f126c7`
Upload date	Jun 30, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/6.2.0 CPython/3.11.9`

Release files / tencentcloud_cls_sdk_langchain-1.0.5-py3-none-any.whl

Download URL	tencentcloud_cls_sdk_langchain-1.0.5-py3-none-any.whl
Size	28.6 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`3182fd35c523a841d1aa21508ccf0f71eb08f369bcc0a870490d48b6106acc81`
BLAKE2b-256 checksum How to use checksums	`998eaff96930c47265cd687bd882843e7f189a082df7b785f8ae69d04e006df6`
Upload date	Jun 30, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/6.2.0 CPython/3.11.9`

Security for tencentcloud-cls-sdk-langchain 1.0.5

Report project as malware

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.