[bot] Add AI21 Labs Python SDK integration for chat completions and embeddings instrumentation (54,424 weekly downloads)

未关闭

#442 创建于 2026年5月18日 1 条评论 0 个 reaction 已指派 0 人在 GitHub 查看

维护者通常 1 天内回复

还没有人认领这个 Issue。

评估

难度: 4/5
预计耗时: 3-5 天
新手友好度: 48/100

Issue 类型: 功能
描述清晰度: 基本清楚
活跃度: 冷清
技术栈: python
领域: observability

调研方向

首先比较 py/src/braintrust/integrations/ 下的 OpenAI 或 Mistral 集成模式，然后检查 py/noxfile.py 以及 issue 中所列的集成注册和版本管理文件。实现对同步和异步 chat completions、streaming 及 embeddings 的覆盖，包括文档中说明的元数据，并添加该集成的测试、注册、版本条目和依赖矩阵条目。

由索引模型根据 Issue 内容生成。

描述

bot-automation new-integration

Summary

The AI21 Python SDK (ai21) is the official Python client for AI21 Labs' inference platform, which provides the Jamba model family — hybrid SSM-Transformer models optimized for long-context tasks and high throughput. Its AI21Client and AsyncAI21Client expose client.chat.completions.create() and client.embed.create() APIs. This repository has zero instrumentation for any AI21 SDK surface — no integration directory, no wrapper, no patcher, no auto_instrument() support.

AI21's Python SDK uses its own client class (ai21.AI21Client), which is not a subclass of openai.OpenAI, so wrap_openai() cannot be used with it. The pattern is the same as Groq, Mistral, and OpenRouter — OpenAI-compatible endpoint but a distinct Python client requiring a dedicated integration. Users who follow AI21's official documentation and pip install ai21 get zero Braintrust tracing.

What needs to be instrumented

The ai21 package exposes these execution surfaces via AI21Client and AsyncAI21Client, none of which are instrumented:

Chat completions (highest priority)

SDK Method	Description	Streaming	Return type
`client.chat.completions.create()`	Chat completions with tool calling, structured output, and document grounding	`stream=True` returns `Stream[ChatCompletionChunk]`	`ChatCompletion`

Response shape is OpenAI-compatible: ChatCompletion has choices, usage (prompt_tokens, completion_tokens, total_tokens), model, id — standard span metrics extraction follows the OpenAI pattern.

Streaming: stream=True returns a Stream[ChatCompletionChunk] iterator. The integration must handle the streaming span lifecycle.

Embeddings

SDK Method	Description	Return type
`client.embed.create()`	Text embeddings generation for semantic search and RAG	`EmbedResponse`

Both sync (AI21Client) and async (AsyncAI21Client) clients exist with identical method signatures.

Implementation notes

Stainless-generated SDK (v3.x): The ai21 v3.x package (current major version) is generated by Stainless (same toolchain as OpenAI, Groq, Mistral). The client structure mirrors the OpenAI SDK, so the patcher/wrapper pattern from the OpenAI or Mistral integration can serve as a close structural reference.

chat.completions.create() parameters relevant for span metadata: model, temperature, max_tokens, top_p, frequency_penalty, presence_penalty, n, stop, tools, tool_choice, response_format, documents (AI21-specific grounding feature).

Document grounding: The documents parameter is AI21-specific and allows grounding responses in provided documents. This should be captured in span input metadata when present.

Model family: Jamba 1.6 Large and Jamba 1.6 Mini are the primary models. Response model field should be captured in span metadata.

No coverage in any instrumentation layer

No integration directory (py/src/braintrust/integrations/ai21/)
No wrapper function (e.g. wrap_ai21())
No patcher in any existing integration
No nox test session (test_ai21)
No version entry in py/src/braintrust/integrations/versioning.py
No mention in py/src/braintrust/integrations/__init__.py
No entry in [tool.braintrust.matrix] in py/pyproject.toml

A grep for ai21 across py/src/braintrust/ returns zero matches.

Braintrust docs status

not_found — AI21 is not listed on the Braintrust integrations directory or the tracing guide.

Upstream references

AI21 Python SDK on PyPI: https://pypi.org/project/ai21/
AI21 Python SDK on GitHub: https://github.com/AI21Labs/ai21-python
AI21 API reference: https://docs.ai21.com/reference/
AI21 Chat Completions docs: https://docs.ai21.com/reference/jamba-15-api-ref
AI21 Embeddings docs: https://docs.ai21.com/reference/embeddings-ref
AI21 SDK quickstart: https://docs.ai21.com/docs/quickstart

Local repo files inspected

py/src/braintrust/integrations/ — no ai21/ directory exists on main
py/src/braintrust/wrappers/ — no AI21 wrapper
py/noxfile.py — no test_ai21 session
py/src/braintrust/integrations/__init__.py — AI21 not listed in integration registry
py/src/braintrust/integrations/versioning.py — no AI21 version matrix
py/pyproject.toml — no AI21 entries in [tool.braintrust.matrix]
Full repo grep for "ai21" across py/src/braintrust/ — zero matches

主要语言: Python
星标: 21
派生: 23
平均合并: 20 小时 2 分钟
30 天内合并 PR: 95

环境准备

提供 Dockerfile 或 Docker Compose 文件
没有 Pull Request 模板
阅读贡献指南

从这里开始

先读完整个 Issue，再读项目的贡献指南。
在 Issue 下留言说明你要接手 —— 这能避免两个人做同样的事。
Fork 仓库，在一个分支上完成修改。
提交 Pull Request，并在描述里引用这个 Issue 编号。

braintrustdata/braintrust-sdk-python 的其他 Issue

Temporal: add `workflow.Info.original_execution_run_id` to workflow span metadata
未关闭
- 哪里不对？
feature python

难度 2/5 1-3 小时新手友好度 76/100

braintrustdata/braintrust-sdk-python#868 · 2026年10月5日创建

维护者通常 1 天内回复
Mistral: record `usage.service_tier` as metadata
未关闭
- 哪里不对？
feature integration: mistral python

难度 2/5 1-3 小时新手友好度 75/100

braintrustdata/braintrust-sdk-python#867 · 2026年10月5日创建

维护者通常 1 天内回复
[bot] Google GenAI: streaming responses drop `url_context_metadata` that non-streaming responses preserve
可能已有人在做 @Kayvan-Zahiri 于 7 天前认领。未关闭
- 哪里不对？
难度 2/5 1-3 小时新手友好度 86/100

braintrustdata/braintrust-sdk-python#774 · 2026年9月16日创建

维护者通常 1 天内回复
pydantic-ai: capture web-search and grounding counts from `RequestUsage.details`
未关闭
- 哪里不对？
feature python

难度 3/5 1-2 天新手友好度 72/100

braintrustdata/braintrust-sdk-python#866 · 2026年10月5日创建

维护者通常 1 天内回复
google-adk: instrument `Workflow` nodes and workflow tool calls
未关闭
- 哪里不对？
feature python

难度 4/5 3-5 天新手友好度 55/100

braintrustdata/braintrust-sdk-python#863 · 2026年10月5日创建

维护者通常 1 天内回复

查看 braintrustdata/braintrust-sdk-python 的全部 Issue

相似的 Issue

`list_eval_logs()` and the dataframe functions ignore `INSPECT_LOG_DIR` set after import
未关闭
- 哪里不对？
难度 2/5 1-3 小时新手友好度 78/100

UKGovernmentBEIS/inspect_ai#5781 · 2026年10月8日创建

维护者通常 2 天内回复
Bump .cicd to wamp-cicd 4c2f9ac: `just land` refuses open A18 decisions, `just where` lists them
未关闭
- 哪里不对？
难度 1/5 1 小时以内新手友好度 82/100

crossbario/cfxdb#139 · 2026年10月8日创建
Bump .cicd to wamp-cicd 4c2f9ac: `just land` refuses open A18 decisions, `just where` lists them
未关闭
- 哪里不对？
难度 1/5 1 小时以内新手友好度 84/100

crossbario/txaio#241 · 2026年10月8日创建
[HONESTY] Populated Radar with a failed source shows no disclosure (partial render reads as complete) — follow-up to #1889
未关闭
- 哪里不对？
UX

难度 2/5 1-3 小时新手友好度 82/100

mediajunkie/piper-morgan-product#1963 · 2026年10月8日创建
Missing `top_level.txt` causing erroneous warning in pycharm
未关闭
- 哪里不对？
难度 2/5 1-3 小时新手友好度 64/100

jazzband/docopt-ng#80 · 2026年10月8日创建

更多 Python Issue

[bot] Add AI21 Labs Python SDK integration for chat completions and embeddings instrumentation (54,424 weekly downloads)

哪里不对？

评估

调研方向

描述

Summary

What needs to be instrumented

Chat completions (highest priority)

Embeddings

Implementation notes

No coverage in any instrumentation layer

Braintrust docs status

Upstream references

Local repo files inspected

环境准备

从这里开始

braintrustdata/braintrust-sdk-python 的其他 Issue

哪里不对？

哪里不对？

哪里不对？

哪里不对？

哪里不对？

相似的 Issue

哪里不对？

哪里不对？

哪里不对？

哪里不对？

哪里不对？

把新 issue 发到你的邮箱