Dockerfile and pulumi stack for infra

agent/Dockerfile

@@ -0,0 +1,13 @@
+FROM public.ecr.aws/lambda/python:3.13
+
+# Copy requirements.txt
+COPY requirements.txt ${LAMBDA_TASK_ROOT}
+
+# Install the specified packages
+RUN pip install -r requirements.txt
+
+# Copy function code
+COPY agent.py ${LAMBDA_TASK_ROOT}
+
+# Set the CMD to your handler (could also be done as a parameter override outside of the Dockerfile)
+CMD ["agent.hello" ]

agent/agent.py

@@ -1,3 +1,4 @@
+import json
 from langchain_core.tools import tool
 from langchain.agents.output_parsers import ReActJsonSingleInputOutputParser
 from langchain_core.prompts import ChatPromptTemplate,MessagesPlaceholder, PromptTemplate
@@ -16,7 +17,15 @@ from langchain_core.agents import AgentAction, AgentFinish
 from langchain.agents.output_parsers import ReActSingleInputOutputParser
 from langchain.tools import Tool
 import os
-llm = ChatBedrock(
+def find_tool_by_name(tools: list[Tool],tool_name:str):
+    for tool in tools:
+        if tool.name==tool_name:
+            print(tool.name)
+            print("\n\n")
+            return tool
+    raise ValueError(f"Tool with name {tool_name} not found")
+def agent_call(event,context):
+    llm = ChatBedrock(
     model_id="arn:aws:bedrock:us-east-1:654654422992:application-inference-profile/d9blf0g3fzqz",
     region_name="us-east-1",
     aws_access_key_id=os.environ["AWS_ACCESS_KEY_ID"],
@@ -25,18 +34,12 @@ llm = ChatBedrock(
     model_kwargs={"temperature": 0.2, 'max_tokens': 1000,},
     provider='anthropic'
 )
-retriever = AmazonKnowledgeBasesRetriever(
+    retriever = AmazonKnowledgeBasesRetriever(
     knowledge_base_id="RBD9TI5HYU",
     region_name="us-east-1",
     retrieval_config={"vectorSearchConfiguration": {"numberOfResults": 4}},
     
 )
-def find_tool_by_name(tools: list[Tool],tool_name:str):
-    for tool in tools:
-        if tool.name==tool_name:
-            return tool
-    raise ValueError(f"Tool with name {tool_name} not found")
-if __name__=="__main__":
     print("Hello React Langhain")
     tools=[retriever.as_tool()]
     template="""Você é um assistente para alunos de diversos campus diferentes do instituto federal de são paulo, sua função é responder perguntas 
@@ -62,13 +65,12 @@ Question: {input}
 Chat history:{chat_history}
 Thought: {agent_scratchpad}
 """
-
     prompt=PromptTemplate.from_template(template=template).partial(tools=render_text_description(tools), tool_names=','.join([t.name for t in tools]))
     #llm=ChatOpenAI(model="gpt-4o-mini",temperature=0,stop_sequences=["\nObservation:"])
     intermediate_steps=[]
 
-    agent= {"input": lambda x:x["input"],"agent_scratchpad": lambda x:format_log_to_str(x["agent_scratchpad"]),"chat_history":lambda x:x["chat_history"]}|prompt | llm
-    agent_step: Union[AgentAction,AgentFinish]=agent.invoke({"input": "Quanto é o valor do auxilio moradia?","agent_scratchpad":intermediate_steps,"chat_history":{"role":"user","content":""}})
+    agent= {"input": lambda x:x["input"],"agent_scratchpad": lambda x:format_log_to_str(x["agent_scratchpad"]),"chat_history":lambda x:x["chat_history"]}|prompt | llm|ReActJsonSingleInputOutputParser()
+    agent_step: Union[AgentAction,AgentFinish]=agent.invoke({"input": "Que dia é hoje?","agent_scratchpad":intermediate_steps,"chat_history":{"role":"user","content":"sou do campus sao paulo"}})
     #print(agent_step)
     if isinstance(agent_step,AgentAction):
         tool_name=agent_step.tool
@@ -77,5 +79,10 @@ Thought: {agent_scratchpad}
         observation=tool_to_use.func(str(tool_input))
         print(f"{observation=}")
         intermediate_steps.append((agent_step,str(observation)))
-    agent_step: Union[AgentAction,AgentFinish]=agent.invoke({"input": "Quanto é o valor do auxiliomoradia?","agent_scratchpad":intermediate_steps,"chat_history":{"role":"user","content":""}})
-    print(agent_step)
+    agent_step: Union[AgentAction,AgentFinish]=agent.invoke({"input": "Quanto é o valor do auxilio moradia?","agent_scratchpad":intermediate_steps,"chat_history":{"role":"user","content":"sou do campus sao paulo"}})
+    return agent_step
+def hello(event,context):
+    return{
+        "statusCode":200,
+        "body":json.dumps("hello_world")
+    }

agent/requirements.txt

@@ -0,0 +1,4 @@
+langchain_core
+langchain
+langchain_aws
+

infra/Pulumi.dev.yaml

@@ -1,2 +0,0 @@
-config:
-  aws:region: us-east-1

infra/Pulumi.ifsp_chatbot_ecr.yaml

@@ -0,0 +1,9 @@
+config:
+  ifsp-chatbot-poc:entity_extraction_dev: ecr
+  ifsp-chatbot-poc:environment: dev
+  ifsp-chatbot-poc:ecr:
+    entity_extraction:
+      image_mutability: MUTABLE
+      name: br-edu-ifsp-ifsp-ret-ecr-chatbot-editais-dev
+  ifsp-chatbot-poc:project: chatbot-editais
+  aws:region: us-east-1

infra/__main__.py

@@ -1,22 +1,34 @@
 """An AWS Python Pulumi program"""
 
 import pulumi
-from pulumi_aws import aws
+import pulumi_aws as aws
 from pulumi_aws import s3
-import pulumi_aws_apigateway as apigateway
 import json
-role = aws.iam.Role("mylambda-role",
-    assume_role_policy=json.dumps({
-        "Version": "2012-10-17",
-        "Statement": [{
-            "Effect": "Allow",
-            "Principal": { "Service": "lambda.amazonaws.com" },
-            "Action": "sts:AssumeRole"
-        }]
-    })
-)
+caller_identity = aws.get_caller_identity()
+account_id = caller_identity.account_id
+
+config = pulumi.Config()
+project = config.require("project")
+environment = config.require("environment")
+
+ecr_config = config.require_object("ecr")["entity_extraction"]
+
+ecr_repo = aws.ecr.Repository(ecr_config['name'],
+    name=ecr_config['name'],
+    encryption_configurations=[{
+        "encryption_type": "AES256",
+    }],
+    image_scanning_configuration={
+        "scan_on_push": False,
+    },
+    image_tag_mutability=ecr_config['image_mutability'],
+    opts = pulumi.ResourceOptions(protect=True))
+
+
+pulumi.export("url", pulumi.Output.concat("ECR REPO ID:", ecr_repo.id))
+
 # Create an AWS resource (S3 Bucket)
-bucket = s3.Bucket('br-edu-ifsp-ifsp-ret-s3-bucket-chatbot-editais-d',
+"""bucket = s3.Bucket('br-edu-ifsp-ifsp-ret-s3-bucket-chatbot-editais-d',
                    tags={
                        "nome":"bucket-chatbot-editais",
                        "ambiente":"dev",
@@ -31,20 +43,7 @@ bucket = s3.Bucket('br-edu-ifsp-ifsp-ret-s3-bucket-chatbot-editais-d',
                        "ia":"sim",
                        "modelo":"claude-sonnet-4"
                    })
-f = aws.lambda_.Function("mylambda",
-    runtime=aws.lambda_.Runtime.PYTHON3D8,
-    code=pulumi.AssetArchive({
-        ".": pulumi.FileArchive("./handler"),
-    }),
-    timeout=300,
-    handler="handler.handler",
-    role=role.arn,
-    opts=pulumi.ResourceOptions(depends_on=[policy]),
-)
 
-api = apigateway.RestAPI('api', routes=[
-    apigateway.RouteArgs(path="/", method="GET", event_handler=f),
-])
 
 # Export the name of the bucket
-pulumi.export('bucket_name', bucket.id)
+pulumi.export('bucket_name', bucket.id)"""