agentic platform - working with REST API

When working with the REST API call in agentic platform, it can be challenging because some of the docs are not updated. 

To help you get the REST API right, you can curl this endpoint It will list out all methods and parameter to pass to other services. 

curl -H "Authorization: Bearer $(gcloud auth print-access-token)" -H "Content-Type: application/json" https://us-central1-aiplatform.googleapis.com/v1/projects/project-YOUR-PROJECT-ID/locations/us-central1/reasoningEngines/REASONING_ENGINE_ID

Some details include :-

classMethods - has been deprecated - Use async_get_session instead

list_sessions - has been deprecated - Use async_list_sessions instead

create_session - has been deprecated - Use async_create_session instead


To get sessions 

curl -H "Authorization: Bearer $(gcloud auth print-access-token)" -H "Content-Type: application/json" https://us-central1-aiplatform.clients6.google.com/v1beta1/projects/YOUR-PROJECT-ID/locations/us-central1/reasoningEngines/YOUR-REASONING-ENGINE/sessions

To create sessions

curl -H "Authorization: Bearer $(gcloud auth print-access-token)" -X POST -H "Content-Type: applica

tion/json" https://us-central1-aiplatform.clients6.google.com/v1beta1/projects/YOUR-PROJECT-IDlocations/us-central1/reasoningEngines/YOUR-REASONING-ENGINE/sessions -d '{userId: "demo-user"}'

Or you can use this 

 curl -H "Authorization: Bearer $(gcloud auth print-access-token)" -X POST -H "Content-Type: application/json" https://us-central1-aiplatform.clients6.google.com/v1beta1/projects/YOUR-PROJECT-ID/locations/us-central1/reasoningEngines/YOUR-REASONING-ENGINE:query -d '

   {"class_method": "create_session", "input": {"user_id": "test2"}}'

🔥  To post query to the endpoint (please note: we are using streamQuery instead of query) 

This query is a static example, you need to replace with the actual user_id and session_id you got in previous steps. 

curl -H "Authorization: Bearer $(gcloud auth print-access-token)" -X POST -H "Content-Type: application/json" https://us-central1-aiplatform.googleapis.com/v1/projects/YOUR-PROJECT-ID/locations/us-central1/reasoningEngines/YOUR-REASONING-ENGINE:streamQuery?alt=sse -d '{

"class_method": "stream_query",

"input": {

"user_id": "your-user-id-step1",

"session_id": "session-id-step-1",

"message": "What data do you have?"

}

}'

An example output shown here:- 








Comments

Post a Comment

Popular posts from this blog

vllm : Failed to infer device type

Trying to run vllm without gpu will typicaly lands you into this issue. To resolve this issue: we can use set these both. Setting one does not work for me. So i had to configure both settings below:- 1.  environment variable CUDA_VISIBLE_DEVICES = "" 2. in the command line, change to use device cpu and remove  tensor-parallel-size. For example, python3 -m vllm.entrypoints.openai.api_server --port 8080 --model deepseek-ai/DeepSeek-R1 --device cpu --trust-remote-code --max-model-len 4096" References https://docs.vllm.ai/en/latest/getting_started/troubleshooting.html#failed-to-infer-device-type
Read more

android studio kotlin source is null error

Image
This org.jetbrains.kotlin.util.FileAnalysisException with a java.lang.IllegalArgumentException: source must not be null is a known issue that can sometimes occur with the Kotlin compiler. It seems to be related to how the compiler analyzes certain source code structures. When this happens, you need to go clean your project and do another rebuild.  For my case, I was trying to test out the databinding = true feature. 
Read more

gemini cli getting file not defined error

Image
 While trying to run gemini cli on my windows linux subsystem, i bump into this error here - "/Roaming/npm/node_modules/@google/gemini-cli/node_modules/undici/lib/web/webidl/index.js:512 webidl.is.File = webidl.util.MakeTypeAssertion(File)"  "ReferenceError: File is not defined" In Node.js, there’s no built-in File (until very recent Node 20+ with experimental WHATWG APIs). So, unless polyfilled, File is undefined, leading to the ReferenceError. And to resolve this, I had to upgrade to node 22 (might work for node 20) and then I was able to run it.
Read more