AWS bedrock documentation change
Summary
Added 'Client-side tool calling' support and new 'Capabilities and Features' section documenting security features, removed sample code blocks
Security assessment
Added documentation for security features like Guardrails and Abuse Detection but no evidence of addressing a specific vulnerability. Sample code removal is unrelated to security
Diff
diff --git a/bedrock/latest/userguide/model-card-mistral-ai-mistral-large.md b/bedrock/latest/userguide/model-card-mistral-ai-mistral-large.md index 306e0ce1b..f23e6748a 100644 --- a//bedrock/latest/userguide/model-card-mistral-ai-mistral-large.md +++ b//bedrock/latest/userguide/model-card-mistral-ai-mistral-large.md @@ -55,0 +56 @@ Mistral Large is Mistral AI's flagship model with strong reasoning, multilingual + *  [Client-side tool calling](https://docs.aws.amazon.com/bedrock/latest/userguide/tool-use.html) @@ -118,9 +118,0 @@ Your AWS account has default quotas to maintain the performance of the service a -Responses/Chat Completions API - - - - pip install boto3 openai - -Invoke/Converse API - - @@ -132,10 +123,0 @@ Invoke/Converse API -Responses/Chat Completions API - - - - OPENAI_API_KEY="<provide your Bedrock API key>" - OPENAI_BASE_URL="https://bedrock-mantle.<your-region>.api.aws/v1" - -Invoke/Converse API - - @@ -147,28 +128,0 @@ Invoke/Converse API -Responses API - - - - from openai import OpenAI - - client = OpenAI() - - response = client.responses.create( - model="mistral.mistral-large-3-675b-instruct", - input="Can you explain the features of Amazon Bedrock?" - ) - print(response) - -Chat Completions API - - - - from openai import OpenAI - - client = OpenAI() - - response = client.chat.completions.create( - model="mistral.mistral-large-3-675b-instruct", - messages=[{"role": "user", "content": "Can you explain the features of Amazon Bedrock?"}] - ) - print(response) -