-
Hi, thanks for working on this library.
Currently trying to use any of the Claude 3 models gives an error e.g. '"claude-3-haiku-20240307" is not supported on this API. Please use the Messages API i…
-
### Issue
Thanks for the latest updates and support for caching on Sonnet, this is great. I have a few files (code guidelines for example) that I load for most projects, and this is a great improvem…
-
Released today: https://www.anthropic.com/claude/haiku
No image support yet.
-
### Bug Description
我使用了第三方中转API，其给出的可用模型名称有很多与预设模型名称相同。这家的中转方式是，无论是谁家的模型，一律使用OpenAI API。因此，当我想要调用claude-3-opus-20240229时，不能使用预设的opus，只能输入自定义模型名。但当我在设置的自定义模型名输入框输入精确的claude-3-opus-20240229时，此选项不会出现。当…
-
### Issue
It would be good to be able to have enhanced interaction with the chat history. This is already implemented for user input, but would be good for the output as well.
At the moment you …
-
**Describe the bug**
When running evals on images with Anthropic or Bedrock the encoded image (base64 string) is passed as text to Claude instead of as an image block.
**To Reproduce**
Run either…
-
https://docs.anthropic.com/en/docs/build-with-claude/pdf-support
> The new Claude 3.5 Sonnet (`claude-3-5-sonnet-20241022`) model now supports PDF input and understands both text and visual content…
-
Hi, I have a question for the multimodal work. When I set the engine as Yi-vision from 01-ai, it shows the error as follows
```
ValueError: The engine provided is not multimodal. Please provide a m…
-
The following code:
```python
import boto3
from langchain_aws import ChatBedrockConverse
boto3.setup_default_session(profile_name="genai-dev", region_name="us-east-1")
llm = ChatBedrockConverse…
-