ton/YiemAgent
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update

Browse Source
This commit is contained in:
narawat
2026-06-24 08:47:36 +07:00
parent f6eaf4751b
commit 906afc6422
6 changed files with 244 additions and 194 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
test/prompttest_1.jl
View File

@@ -66,7 +66,7 @@ tools=Dict( # update input format
input =
OrderedDict{Symbol, Any}(:question => "Hello, I would like a get a bottle of wine", :thought_1 => "It's great that the user is looking for a bottle of wine. To give them a personalized recommendation, I need to know more about their preferences.", :action_1 => Dict{Symbol, Any}(:name => "chatbox", :input => "What occasion are you planning to use this wine for?"), :observation_1 => "We are holding a wedding party", :thought_2 => "A wedding party is a great occasion for a special bottle of wine. I need to know what type of food will be served, and how much the user is willing to spend.", :action_2 => Dict{Symbol, Any}(:name => "chatbox", :input => "What type of food will you be serving at the wedding?"), :observation_2 => "It will be Thai dishes.", :thought_3 => "The type of wine that pairs well with Thai dishes is usually a crisp and refreshing white wine, but I also need to consider the budget and personal preferences.", :action_3 => Dict{Symbol, Any}(:name => "chatbox", :input => "How much are you willing to spend on this bottle of wine?"), :observation_3 => "I would spend up to 50 bucks.", :thought_4 => "I have a good idea of the occasion, food, and budget. Now I need to know what type of wine the user is looking for.", :action_4 => Dict{Symbol, Any}(:name => "chatbox", :input => "What type of wine are you usually looking for? Red, White, Sparkling, Rose, Dessert or Fortified?"), :observation_4 => "I like full-bodied Red wine with low tannin.", :thought_5 => "Now that I have all the necessary information, I can start searching for a suitable wine in our inventory.", :action_5 => Dict{Symbol, Any}(:name => "winestock", :input => "red wine with low tannins"), :observation_5 => "I found the following wines in our stock: \n{\n 1: El Enemigo Cabernet Franc 2019\n2: Tantara Chardonnay 2017\n\n}\n", :thought_6 => "Now that I have the information about the wine, it's time to make a recommendation.", :action_6 => Dict{Symbol, Any}(:name => "recommendbox", :input => "El Enemigo Cabernet Franc 2019"), :observation_6 => "I don't like the one you recommend. I want dry wine.")
OrderedDict{String, Any}(:question => "Hello, I would like a get a bottle of wine", :thought_1 => "It's great that the user is looking for a bottle of wine. To give them a personalized recommendation, I need to know more about their preferences.", :action_1 => Dict{String, Any}(:name => "chatbox", :input => "What occasion are you planning to use this wine for?"), :observation_1 => "We are holding a wedding party", :thought_2 => "A wedding party is a great occasion for a special bottle of wine. I need to know what type of food will be served, and how much the user is willing to spend.", :action_2 => Dict{String, Any}(:name => "chatbox", :input => "What type of food will you be serving at the wedding?"), :observation_2 => "It will be Thai dishes.", :thought_3 => "The type of wine that pairs well with Thai dishes is usually a crisp and refreshing white wine, but I also need to consider the budget and personal preferences.", :action_3 => Dict{String, Any}(:name => "chatbox", :input => "How much are you willing to spend on this bottle of wine?"), :observation_3 => "I would spend up to 50 bucks.", :thought_4 => "I have a good idea of the occasion, food, and budget. Now I need to know what type of wine the user is looking for.", :action_4 => Dict{String, Any}(:name => "chatbox", :input => "What type of wine are you usually looking for? Red, White, Sparkling, Rose, Dessert or Fortified?"), :observation_4 => "I like full-bodied Red wine with low tannin.", :thought_5 => "Now that I have all the necessary information, I can start searching for a suitable wine in our inventory.", :action_5 => Dict{String, Any}(:name => "winestock", :input => "red wine with low tannins"), :observation_5 => "I found the following wines in our stock: \n{\n 1: El Enemigo Cabernet Franc 2019\n2: Tantara Chardonnay 2017\n\n}\n", :thought_6 => "Now that I have the information about the wine, it's time to make a recommendation.", :action_6 => Dict{String, Any}(:name => "recommendbox", :input => "El Enemigo Cabernet Franc 2019"), :observation_6 => "I don't like the one you recommend. I want dry wine.")
result = YiemAgent.jsoncorrection(a, input)

108
test/runtests.jl
View File

@@ -0,0 +1,108 @@
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)