Skip to content

The agent engineering platform.

docs: fix Anthropic, OpenAI docstrings (#33566)

Mason Daugherty241a382fba5c
diff --git a/libs/partners/anthropic/langchain_anthropic/chat_models.py b/libs/partners/anthropic/langchain_anthropic/chat_models.py
index 348a0fb336..eb2b50b4a0 100644
--- a/libs/partners/anthropic/langchain_anthropic/chat_models.py
+++ b/libs/partners/anthropic/langchain_anthropic/chat_models.py
@@ -1186,7 +1186,8 @@ class ChatAnthropic(BaseChatModel):
See [Claude documentation](https://docs.claude.com/en/docs/build-with-claude/prompt-caching#1-hour-cache-duration-beta)
for detail.
- Extended context windows (beta):
+ !!! note title="Extended context windows (beta)"
+
Claude Sonnet 4 supports a 1-million token context window, available in beta for
organizations in usage tier 4 and organizations with custom rate limits.
@@ -1221,7 +1222,8 @@ class ChatAnthropic(BaseChatModel):
for detail.
- Token-efficient tool use (beta):
+ !!! note title="Token-efficient tool use (beta)"
+
See LangChain [docs](https://python.langchain.com/docs/integrations/chat/anthropic/)
for more detail.
@@ -1257,7 +1259,8 @@ class ChatAnthropic(BaseChatModel):
Total tokens: 408
```
- Context management:
+ !!! note title="Context management"
+
Anthropic supports a context editing feature that will automatically manage the
model's context window (e.g., by clearing tool results).
@@ -1276,7 +1279,8 @@ class ChatAnthropic(BaseChatModel):
response = model_with_tools.invoke("Search for recent developments in AI")
```
- Built-in tools:
+ !!! note title="Built-in tools"
+
See LangChain [docs](https://python.langchain.com/docs/integrations/chat/anthropic/#built-in-tools)
for more detail.
@@ -1402,7 +1406,7 @@ class ChatAnthropic(BaseChatModel):
response = model_with_tools.invoke("What are my interests?")
```
- Response metadata
+ !!! note title="Response metadata"
```python
ai_msg = model.invoke(messages)
diff --git a/libs/partners/openai/langchain_openai/embeddings/azure.py b/libs/partners/openai/langchain_openai/embeddings/azure.py
index d9d13be528..1c854dbf29 100644
--- a/libs/partners/openai/langchain_openai/embeddings/azure.py
+++ b/libs/partners/openai/langchain_openai/embeddings/azure.py
@@ -72,12 +72,11 @@ class AzureOpenAIEmbeddings(OpenAIEmbeddings): # type: ignore[override]
Embed multiple texts:
```python
input_texts = ["Document 1...", "Document 2..."]
+ vectors = embed.embed_documents(input_texts)
+ print(len(vectors))
+ # The first 3 coordinates for the first vector
+ print(vectors[0][:3])
```
- vectors = embed.embed_documents(input_texts)
- print(len(vectors))
- # The first 3 coordinates for the first vector
- print(vectors[0][:3])
-
```python
2
[-0.024603435769677162, -0.007543657906353474, 0.0039630369283258915]