The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.
Python agentic-memoryagentic-memory-systemagentsaiai-agentschatgptgenaillmlong-term-memorymemorymemory-managementpythonragstate-management
fix: bedrock llm, embeddings, tools, temporary creds (#3023)
Laith Al-Saadoon8139b5887f99
diff --git a/mem0/embeddings/aws_bedrock.py b/mem0/embeddings/aws_bedrock.pyindex 1679aeec0..d5ce21db6 100644--- a/mem0/embeddings/aws_bedrock.py+++ b/mem0/embeddings/aws_bedrock.py@@ -11,7 +11,6 @@ import numpy as npfrom mem0.configs.embeddings.base import BaseEmbedderConfigfrom mem0.embeddings.base import EmbeddingBase-from mem0.memory.utils import extract_jsonclass AWSBedrockEmbedding(EmbeddingBase):@@ -28,6 +27,7 @@ class AWSBedrockEmbedding(EmbeddingBase):# Get AWS config from environment variables or use defaultsaws_access_key = os.environ.get("AWS_ACCESS_KEY_ID", "")aws_secret_key = os.environ.get("AWS_SECRET_ACCESS_KEY", "")+ aws_session_token = os.environ.get("AWS_SESSION_TOKEN", "")aws_region = os.environ.get("AWS_REGION", "us-west-2")# Check if AWS config is provided in the config@@ -43,6 +43,7 @@ class AWSBedrockEmbedding(EmbeddingBase):region_name=aws_region,aws_access_key_id=aws_access_key if aws_access_key else None,aws_secret_access_key=aws_secret_key if aws_secret_key else None,+ aws_session_token=aws_session_token if aws_session_token else None,)def _normalize_vector(self, embeddings):@@ -75,7 +76,7 @@ class AWSBedrockEmbedding(EmbeddingBase):contentType="application/json",)- response_body = json.loads(extract_json(response.get("body").read()))+ response_body = json.loads(response.get("body").read())if provider == "cohere":embeddings = response_body.get("embeddings")[0]diff --git a/mem0/llms/aws_bedrock.py b/mem0/llms/aws_bedrock.pyindex 91a2806f5..8b2d2d194 100644--- a/mem0/llms/aws_bedrock.py+++ b/mem0/llms/aws_bedrock.py@@ -10,7 +10,7 @@ except ImportError:from mem0.configs.llms.base import BaseLlmConfigfrom mem0.llms.base import LLMBase-from mem0.memory.utils import extract_json+PROVIDERS = ["ai21", "amazon", "anthropic", "cohere", "meta", "mistral", "stability", "writer"]@@ -92,17 +92,15 @@ class AWSBedrockLLM(LLMBase):if response["output"]["message"]["content"]:for item in response["output"]["message"]["content"]:if "toolUse" in item:- processed_response["tool_calls"].append(- {- "name": item["toolUse"]["name"],- "arguments": item["toolUse"]["input"],- }- )+ processed_response["tool_calls"].append({+ "name": item["toolUse"]["name"],+ "arguments": item["toolUse"]["input"],+ })return processed_responseresponse_body = response.get("body").read().decode()- response_json = json.loads(extract_json(response_body))+ response_json = json.loads(response_body)return response_json.get("content", [{"text": ""}])[0].get("text", "")def _prepare_input(@@ -190,10 +188,7 @@ class AWSBedrockLLM(LLMBase):}for prop, details in function["parameters"].get("properties", {}).items():- new_tool["toolSpec"]["inputSchema"]["json"]["properties"][prop] = {- "type": details.get("type", "string"),- "description": details.get("description", ""),- }+ new_tool["toolSpec"]["inputSchema"]["json"]["properties"][prop] = detailsnew_tools.append(new_tool)