Aiden Dai

Since there are a lot of benefits of using Graviton instances in AWS, in both EC2 or EKS. It would be Nice to support running this container image in ARM...

Request to add support to automatically detect the format (fields) based on heading columns for CSV or TSV. For example, I have below CSV (delimited by space) content as the...

@dlvenable I think both ways work for me. It makes more sense to me to parse each line in the source as in #251 . At least there is no...

I want to request supports for below two special use cases in the `parse_json` processsor. - Case 1: Be able to filter based on Json path For example, here is...

Hi @xinlaoda The cause of your failure is because you deployed the solution in ap-southeast-1 and this tool assumed the region of the source bucket is ap-southeast-1. We can't support...

unfortunately, the bedrock SDK does not provide any info about the token usage for mistral/mixtral model when using `invoke_model` so far. Other models are fine. You can switch on the...

It's a parameter in openAI chat completion API. See https://cookbook.openai.com/examples/how_to_stream_completions for more details.

This is now supported with the new bedrock api. Please try it again.

Thanks Michael for the issue. Currently, there is no plan to add support of using SSL by default. However, you can fully customize the solution once it's deployed on AWS...

我测试了下， 是因为 bedrock 返回content 为空， 如下所示： ```'message': {'role': 'assistant', 'content': []}}, 'stopReason': 'end_turn',``` 针对这种情况就返回为空： ``` {"id":"chatcmpl-a3aa1356","created":1723196261,"model":"anthropic.claude-3-5-sonnet-20240620-v1:0","system_fingerprint":"fp","choices":[{"index":0,"finish_reason":"stop","logprobs":null,"message":{"role":"assistant"}}],"object":"chat.completion","usage":{"prompt_tokens":112,"completion_tokens":4,"total_tokens":116}} ``` fix 代码见： https://github.com/aws-samples/bedrock-access-gateway/commit/2950c15ecb3ef53db077f6c726451084320828ae