using JSON, Dates, UUIDs, PrettyPrinting, Base64, NATS, HTTP
using GeneralUtils, msghandler

config = JSON.parsefile("./appconfig.json")

agent_conn  = NATS.connect(config["nats_server_info"]["url"])

function text2text_instruct_llm(openai_msg::AbstractDict)
  payloads = [("msg", openai_msg, "dictionary")]  # List of tuples
  _, msg_envelope_json_str = msghandler.smartpack(
        config["externalService"]["servicesloadbalancer"]["nats"], 
        payloads;   
        msg_purpose="text2text",  
        broker_url=config["nats_server_info"]["url"],
        fileserver_url=config["externalService"]["fileserver"]["url"])

  reply = NATS.request(agent_conn, 
                      config["externalService"]["servicesloadbalancer"]["nats"], 
                      msg_envelope_json_str, timeout=120)

  incoming_env_json_str = String(reply.payload)
  incoming_env = msghandler.smartunpack(incoming_env_json_str)
  _llm_response = incoming_env["payloads"][1][2]
  llm_response = _llm_response["choices"][1]["message"]["content"]
  return llm_response
end




# 1. Read local file and encode to base64 string
image1_path = "test/large_image.png"
image1_bytes = read(image1_path)
image1_base64_string = base64encode(image1_bytes)

# 2. Match the MIME type according to your file extension (e.g., png, jpeg)
mime_type = "image/png" 
data1_uri = "data:$(mime_type);base64,$(image1_base64_string)"

# 3. Construct payload with the Data URI
openai_msg = Dict(
  "model" => "gemma-4-E4B-it-UD-Q4_K_XL",
  "messages" => [
    Dict(
      "role" => "user",
      "content" => [
        Dict("type" => "text", "text" => "Do you know this wine? Just give me brief intro."),
        Dict(
          "type" => "image_url",
          "image_url" => Dict("url" => data1_uri)
        )
      ]
    )
  ],
  "temperature" => 0.7
)

llm_response = text2text_instruct_llm(openai_msg)



# 1. Read local file and encode to base64 string
image2_path = "test/small_image.png"
image2_bytes = read(image2_path)
image2_base64_string = base64encode(image2_bytes)

# 2. Match the MIME type according to your file extension (e.g., png, jpeg)
mime_type = "image/png" 
data2_uri = "data:$(mime_type);base64,$(image2_base64_string)"


openai_msg = Dict(
  "model" => "gemma-4-E4B-it-UD-Q4_K_XL",
  "messages" => [
    Dict(
      "role" => "user",
      "content" => [
        Dict("type" => "text", "text" => "Do you know this wine? Just give me brief intro."),
        Dict(
          "type" => "image_url",
          "image_url" => Dict("url" => data1_uri)
        )
      ]
    ),
    Dict(
      "role" => "assistant",
      "content" => [
        Dict("type" => "text", "text" => "Yes, I do!\n\nThis is **Asolo Bella Principessa**, a high-quality Italian sparkling wine made from the Prosecco region.\n\n### 🥂 Brief Intro\n\n*   **What it is:** A Prosecco Superiore D.O.C.G., meaning it meets strict quality standards for a premium sparkling wine.\n*   **Style:** It is a **Sparkling White Wine** and is designated as **Extra Dry**. This means it is crisp, refreshing, and has a dry finish (not overly sweet).\n*   **Flavor Profile:** Expect bright, lively bubbles, often with notes of green apple, pear, and citrus.\n*   **Best For:** It's a versatile wine, perfect for celebratory toasts, enjoying with appetizers (like seafood or charcuterie), or simply as a refreshing aperitivo."),
      ]
    ),
    Dict(
      "role" => "user",
      "content" => [
        Dict("type" => "text", "text" => "How does this wine differ from earlier wine?"),
        Dict(
          "type" => "image_url",
          "image_url" => Dict("url" => data2_uri)
        )
      ]
    ),
  ],
  "temperature" => 0.7
)

llm_response = text2text_instruct_llm(openai_msg)