Issue with ChatBedrockConverse and Bedrock Claude Model: ValidationException on Blank Text Field #5960
Comments
dosubot
bot
added
the
auto:bug
|
Hey @Jalmeida1994! 👋 I'm here to help you out with any bugs, questions, or contributions while we wait for a human maintainer. Let's squash those bugs together! To resolve the Here's an example of how you can invoke the import { ChatBedrockConverse } from "@langchain/aws";
import { HumanMessage } from "@langchain/core/messages";
const model = new ChatBedrockConverse({
model: "anthropic.claude-3-sonnet-20240229-v1:0",
region: "us-east-1",
credentials: {
accessKeyId: process.env.BEDROCK_AWS_ACCESS_KEY_ID!,
secretAccessKey: process.env.BEDROCK_AWS_SECRET_ACCESS_KEY!,
},
});
const messages = [
new HumanMessage({ content: "Print hello world" }),
new HumanMessage({ content: "What is the weather today?" })
];
const res = await model.invoke(messages);
console.log(res);Ensure that each Additionally, the |
|
Hey @dosu, you friendly bot! I understand the need to ensure that all messages passed to the invoke method contain non-empty content. However, the issue arises from the agent itself adding the empty content message. The content is empty because of the When the agent is set to use a tool, it stops and returns the tool that it will use. It executes the tool correctly, but in the messages history, we get a ToolMessage with the correct content. However, before that, we receive an AIMessage indicating tool usage but with empty content. Example of the message history: "HumanMessage": {
"lc_serializable": true,
"lc_kwargs": {
"content": "Use a tool please",
"additional_kwargs": {},
"response_metadata": {}
},
"lc_namespace": [ "langchain_core", "messages" ],
"content": "Use a tool please",
"name": "undefined",
"additional_kwargs": {},
"response_metadata": {},
"id": "undefined"
},
{
"AIMessage": {
"lc_serializable": true,
"lc_kwargs": {
"content": "",
"tool_calls": [{ "id": "tooluse_e68eeY31Rju83TWq5n-e1A", "name": "retrieve_internal_documents", "args": {}}],
"response_metadata": {
"$metadata": { "httpStatusCode": 200, "requestId": "fba07d1c-cfda-4609-a603-ad589da3374a", "attempts": 1, "totalRetryDelay": 0 },
"metrics": { "latencyMs": 1718 },
"stopReason": "tool_use",
"usage": { "inputTokens": 446, "outputTokens": 56, "totalTokens": 502 }
},
"usage_metadata": { "input_tokens": 446, "output_tokens": 56, "total_tokens": 502 },
"id": "fba07d1c-cfda-4609-a603-ad589da3374a",
"invalid_tool_calls": [],
"additional_kwargs": {}
}
}
},
"ToolMessage": {
"lc_serializable": true,
"lc_kwargs": {
"content": "bla bla"
<rest of correct output from tool>This issue didn't occur with |
|
The issue you're encountering with To address this, you can filter out any import { ChatBedrockConverse } from "@langchain/aws";
import { HumanMessage, AIMessage } from "@langchain/core/messages";
const model = new ChatBedrockConverse({
model: "anthropic.claude-3-sonnet-20240229-v1:0",
region: "us-east-1",
credentials: {
accessKeyId: process.env.BEDROCK_AWS_ACCESS_KEY_ID!,
secretAccessKey: process.env.BEDROCK_AWS_SECRET_ACCESS_KEY!,
},
});
const filterEmptyMessages = (messages) => {
return messages.filter(message => {
if (message instanceof AIMessage && !message.content) {
return false;
}
return true;
});
};
const messages = [
new HumanMessage({ content: "Use a tool please" }),
new AIMessage({
content: "",
tool_calls: [{ id: "tooluse_e68eeY31Rju83TWq5n-e1A", name: "retrieve_internal_documents", args: {} }],
response_metadata: {
$metadata: { httpStatusCode: 200, requestId: "fba07d1c-cfda-4609-a603-ad589da3374a", attempts: 1, totalRetryDelay: 0 },
metrics: { latencyMs: 1718 },
stopReason: "tool_use",
usage: { inputTokens: 446, outputTokens: 56, totalTokens: 502 }
},
usage_metadata: { input_tokens: 446, output_tokens: 56, total_tokens: 502 },
id: "fba07d1c-cfda-4609-a603-ad589da3374a",
invalid_tool_calls: [],
additional_kwargs: {}
}),
new HumanMessage({ content: "What is the weather today?" })
];
const filteredMessages = filterEmptyMessages(messages);
const res = await model.invoke(filteredMessages);
console.log(res);This code filters out any |
|
We tried filtering out any AIMessage objects with empty content before invoking the model. However, we encounter another issue when we do this. Here’s the error message we receive: It seems that when a ToolMessage is present as the last message, the Converse API does not generate a completion because the last message needs to be a human message - or maybe it's a completely unrelated issue ahah. This behavior didn't occur with |
|
+1 |
1 similar comment
|
+1 |
|
Same issue as @Jalmeida1994 when a ToolMessage is present as the last message |
|
FYI - not related to langchain but I had this problem when using the Bedrock Converse API. Switched to raw InvokeModel API and didnt have this anymore |
|
@dsunjka if you don't mind, would you please be so kind to share your code snippet that solved this problem? |
|
Was this fix also made to Python client? |
Checked other resources
Example Code
Maybe any example from LanggraphJS Examples that uses tools, but with "ChatBedrockConverse" and model "anthropic.claude-3-sonnet-20240229-v1:0"?
Error Message and Stack Trace (if applicable)
Error in CompletionController.generateCompletion() The text field in the ContentBlock object at messages.1.content.0 is blank. Add text to the text field, and try again.","name":"ValidationException","stack":"ValidationException: The text field in the ContentBlock object at messages.1.content.0 is blank. Add text to the text field, and try again.\n at de_ValidationExceptionRes (/Users/test/code/bot/node_modules/.pnpm/@AWS-SDK+client-bedrock-runtime@3.606.0/node_modules/@aws-sdk/client-bedrock-runtime/dist-cjs/index.js:1082:21)\n at de_CommandError (/Users/test/code/bot/node_modules/.pnpm/@AWS-SDK+client-bedrock-runtime@3.606.0/node_modules/@aws-sdk/client-bedrock-runtime/dist-cjs/index.js:937:19)\n at processTicksAndRejections (node:internal/process/task_queues:95:5)\n at async /Users/test/code/bot/node_modules/.pnpm/@smithy+middleware-serde@3.0.3/node_modules/@smithy/middleware-serde/dist-cjs/index.js:35:20\n at async /Users/test/code/bot/node_modules/.pnpm/@smithy+core@2.2.4/node_modules/@smithy/core/dist-cjs/index.js:165:18\n at async /Users/test/code/bot/node_modules/.pnpm/@smithy+middleware-retry@3.0.7/node_modules/@smithy/middleware-retry/dist-cjs/index.js:320:38\n at async /Users/test/code/bot/node_modules/.pnpm/@AWS-SDK+middleware-logger@3.598.0/node_modules/@aws-sdk/middleware-logger/dist-cjs/index.js:34:22\n at async ChatBedrockConverse.generateNonStreaming (/Users/test/code/bot/node_modules/.pnpm/@langchain+aws@0.0.1@AWS-SDK+client-sso-oidc@3.606.0_@aws-sdk+client-sts@3.606.0__@aws-sdk+c_wops3cctew2kpyygicqzgjk7su/node_modules/@langchain/aws/dist/chat_models.cjs:222:26)\n at async Promise.allSettled (index 0)\n at async ChatBedrockConverse.generateUncached (/Users/test/code/bot/node_modules/.pnpm/@langchain+core@0.2.12_langchain@0.2.8@AWS-SDK+credential-provider-node@3.600.0_@aws-sdk+cli_6wi7pugnjf7kzne7hkijzr5xv4/node_modules/@langchain/core/dist/language_models/chat_models.cjs:177:29)","timestamp":"2024-07-02T13:59:04.567Z
Description
I'm encountering an issue when invoking the Bedrock Claude model via the Converse API using LangChain's
ChatBedrockConverse. The error message is:This issue does not occur when using
ChatOpenAIorBedrockChat. It seems specific toChatBedrockConverse.Steps to Reproduce:
ValidationExceptiondue to a blanktextfield in theContentBlockobject.Expected Behavior:
The model should handle tool usage without resulting in empty content messages, or the API should handle such cases gracefully - which I know it's not with Langchain.
Actual Behavior:
The process fails with a
ValidationExceptionwhen an empty content message is encountered.Additional Information:
ChatBedrockConverse.The model returned the following errors: Your API request included an 'assistant' message in the final position, which would pre-fill the 'assistant' response. When using tools, pre-filling the 'assistant' response is not supported.Example AI message with empty content calling a tool:
{ "AIMessage": { "lc_serializable": true, "lc_kwargs": { "content": "", "tool_calls": [{ "id": "tooluse_e68eeY31Rju83TWq5n-e1A", "name": "retrieve_internal_documents", "args": {}}], "response_metadata": { "$metadata": { "httpStatusCode": 200, "requestId": "fba07d1c-cfda-4609-a603-ad589da3374a", "attempts": 1, "totalRetryDelay": 0 }, "metrics": { "latencyMs": 1718 }, "stopReason": "tool_use", "usage": { "inputTokens": 446, "outputTokens": 56, "totalTokens": 502 } }, "usage_metadata": { "input_tokens": 446, "output_tokens": 56, "total_tokens": 502 }, "id": "fba07d1c-cfda-4609-a603-ad589da3374a", "invalid_tool_calls": [], "additional_kwargs": {} } } }PS: If you feel this issue might be better shared with the LangGraph JS maintainers or if it involves specific nuances of the AWS Bedrock Converse API, please let me know. I initially reported it here since ChatBedrockConverse is hosted within LangChain.
System Info
The text was updated successfully, but these errors were encountered: