update
This commit is contained in:
@@ -1,41 +0,0 @@
|
||||
# This file is machine-generated - editing it directly is not advised
|
||||
|
||||
julia_version = "1.11.4"
|
||||
manifest_format = "2.0"
|
||||
project_hash = "71d91126b5a1fb1020e1098d9d492de2a4438fd2"
|
||||
|
||||
[[deps.Base64]]
|
||||
uuid = "2a0f44e3-6c83-55bd-87e4-b1978d98bd5f"
|
||||
version = "1.11.0"
|
||||
|
||||
[[deps.InteractiveUtils]]
|
||||
deps = ["Markdown"]
|
||||
uuid = "b77e0a4c-d291-57a0-90e8-8db25a27a240"
|
||||
version = "1.11.0"
|
||||
|
||||
[[deps.Logging]]
|
||||
uuid = "56ddb016-857b-54e1-b83d-db4d58db5568"
|
||||
version = "1.11.0"
|
||||
|
||||
[[deps.Markdown]]
|
||||
deps = ["Base64"]
|
||||
uuid = "d6f4376e-aef5-505a-96c1-9c027394607a"
|
||||
version = "1.11.0"
|
||||
|
||||
[[deps.Random]]
|
||||
deps = ["SHA"]
|
||||
uuid = "9a3f8284-a2c9-5f02-9a11-845980a1fd5c"
|
||||
version = "1.11.0"
|
||||
|
||||
[[deps.SHA]]
|
||||
uuid = "ea8e919c-243c-51af-8825-aaa63cd721ce"
|
||||
version = "0.7.0"
|
||||
|
||||
[[deps.Serialization]]
|
||||
uuid = "9e88b42a-f829-5b0c-bbe9-9e923198166b"
|
||||
version = "1.11.0"
|
||||
|
||||
[[deps.Test]]
|
||||
deps = ["InteractiveUtils", "Logging", "Random", "Serialization"]
|
||||
uuid = "8dfed614-e22c-5e08-85e1-65c5234f0b40"
|
||||
version = "1.11.0"
|
||||
@@ -1,2 +0,0 @@
|
||||
[deps]
|
||||
Test = "8dfed614-e22c-5e08-85e1-65c5234f0b40"
|
||||
@@ -0,0 +1,642 @@
|
||||
using Test
|
||||
using YiemAgent
|
||||
using YiemAgent.agentCore
|
||||
using YiemAgent.type
|
||||
using JSON
|
||||
|
||||
# Import the function from the private module scope
|
||||
import YiemAgent.agentCore: _extractToolCalls
|
||||
|
||||
@testset "_extractToolCalls" begin
|
||||
|
||||
# ------------------------------------------------------------------ #
|
||||
# Format 1: response["message"]["tool_calls"] (LMStudio.jl style) #
|
||||
# ------------------------------------------------------------------ #
|
||||
|
||||
@testset "single tool call via message format" begin
|
||||
response = Dict{String,Any}(
|
||||
"finish_reason" => "tool_calls",
|
||||
"index" => 0,
|
||||
"message" => Dict{String,Any}(
|
||||
"role" => "assistant",
|
||||
"content" => "",
|
||||
"reasoning_content" => "Let me check the weather.",
|
||||
"tool_calls" => Any[
|
||||
Dict{String,Any}(
|
||||
"type" => "function",
|
||||
"function" => Dict{String,Any}(
|
||||
"name" => "getWeather",
|
||||
"arguments" => "{\"city\":\"Bangkok, Thailand\"}",
|
||||
),
|
||||
"id" => "tc_001",
|
||||
)
|
||||
],
|
||||
),
|
||||
)
|
||||
has_toolcalls, tc_list, assistant_msg = _extractToolCalls(response)
|
||||
@test has_toolcalls == true
|
||||
@test length(tc_list) == 1
|
||||
@test tc_list[1].name == "getWeather"
|
||||
@test tc_list[1].id == "tc_001"
|
||||
@test tc_list[1].type == "function"
|
||||
@test tc_list[1].arguments["city"] == "Bangkok, Thailand"
|
||||
@test assistant_msg isa assistantMessage
|
||||
@test assistant_msg.role == "assistant"
|
||||
@test assistant_msg.stopReason == "tool_calls"
|
||||
@test length(assistant_msg.content) == 1
|
||||
@test assistant_msg.content[1] isa reasoningContent
|
||||
@test assistant_msg.content[1].text == "Let me check the weather."
|
||||
end
|
||||
|
||||
@testset "multiple tool calls via message format" begin
|
||||
response = Dict{String,Any}(
|
||||
"message" => Dict{String,Any}(
|
||||
"role" => "assistant",
|
||||
"content" => "",
|
||||
"tool_calls" => Any[
|
||||
Dict{String,Any}(
|
||||
"type" => "function",
|
||||
"function" => Dict{String,Any}(
|
||||
"name" => "getWeather",
|
||||
"arguments" => "{\"city\":\"Tokyo, Japan\"}",
|
||||
),
|
||||
"id" => "tc_001",
|
||||
),
|
||||
Dict{String,Any}(
|
||||
"type" => "function",
|
||||
"function" => Dict{String,Any}(
|
||||
"name" => "getTime",
|
||||
"arguments" => "{\"timezone\":\"Asia/Tokyo\"}",
|
||||
),
|
||||
"id" => "tc_002",
|
||||
),
|
||||
],
|
||||
),
|
||||
)
|
||||
has_toolcalls, tc_list, assistant_msg = _extractToolCalls(response)
|
||||
@test has_toolcalls == true
|
||||
@test length(tc_list) == 2
|
||||
@test tc_list[1].name == "getWeather"
|
||||
@test tc_list[1].arguments["city"] == "Tokyo, Japan"
|
||||
@test tc_list[2].name == "getTime"
|
||||
@test tc_list[2].arguments["timezone"] == "Asia/Tokyo"
|
||||
@test assistant_msg.role == "assistant"
|
||||
end
|
||||
|
||||
@testset "tool call with empty arguments string" begin
|
||||
response = Dict{String,Any}(
|
||||
"message" => Dict{String,Any}(
|
||||
"role" => "assistant",
|
||||
"tool_calls" => Any[
|
||||
Dict{String,Any}(
|
||||
"type" => "function",
|
||||
"function" => Dict{String,Any}(
|
||||
"name" => "listTools",
|
||||
"arguments" => "{}",
|
||||
),
|
||||
"id" => "tc_empty",
|
||||
),
|
||||
],
|
||||
),
|
||||
)
|
||||
has_toolcalls, tc_list, assistant_msg = _extractToolCalls(response)
|
||||
@test has_toolcalls == true
|
||||
@test length(tc_list) == 1
|
||||
@test tc_list[1].name == "listTools"
|
||||
@test tc_list[1].arguments == Dict{String,Any}()
|
||||
@test assistant_msg.stopReason == "end_turn"
|
||||
end
|
||||
|
||||
@testset "tool call with missing id falls back to uuid" begin
|
||||
response = Dict{String,Any}(
|
||||
"message" => Dict{String,Any}(
|
||||
"role" => "assistant",
|
||||
"tool_calls" => Any[
|
||||
Dict{String,Any}(
|
||||
"type" => "function",
|
||||
"function" => Dict{String,Any}(
|
||||
"name" => "getTime",
|
||||
"arguments" => "{\"city\":\"NYC\"}",
|
||||
),
|
||||
),
|
||||
],
|
||||
),
|
||||
)
|
||||
has_toolcalls, tc_list, assistant_msg = _extractToolCalls(response)
|
||||
@test has_toolcalls == true
|
||||
@test length(tc_list) == 1
|
||||
@test !isempty(tc_list[1].id)
|
||||
@test tc_list[1].name == "getTime"
|
||||
end
|
||||
|
||||
@testset "tool call with non-string arguments (pre-parsed dict)" begin
|
||||
response = Dict{String,Any}(
|
||||
"message" => Dict{String,Any}(
|
||||
"role" => "assistant",
|
||||
"tool_calls" => Any[
|
||||
Dict{String,Any}(
|
||||
"type" => "function",
|
||||
"function" => Dict{String,Any}(
|
||||
"name" => "getWeather",
|
||||
"arguments" => Dict{String,Any}("city" => "London", "units" => "fahrenheit"),
|
||||
),
|
||||
"id" => "tc_parsed",
|
||||
),
|
||||
],
|
||||
),
|
||||
)
|
||||
has_toolcalls, tc_list, assistant_msg = _extractToolCalls(response)
|
||||
@test has_toolcalls == true
|
||||
@test length(tc_list) == 1
|
||||
@test tc_list[1].arguments["city"] == "London"
|
||||
@test tc_list[1].arguments["units"] == "fahrenheit"
|
||||
end
|
||||
|
||||
@testset "tool call with api/provider/model/usage metadata" begin
|
||||
response = Dict{String,Any}(
|
||||
"api" => "openai",
|
||||
"provider" => "anthropic",
|
||||
"model" => "claude-3-opus",
|
||||
"message" => Dict{String,Any}(
|
||||
"role" => "assistant",
|
||||
"tool_calls" => Any[
|
||||
Dict{String,Any}(
|
||||
"type" => "function",
|
||||
"function" => Dict{String,Any}(
|
||||
"name" => "getTime",
|
||||
"arguments" => "{}",
|
||||
),
|
||||
"id" => "tc_meta",
|
||||
),
|
||||
],
|
||||
),
|
||||
)
|
||||
has_toolcalls, tc_list, assistant_msg = _extractToolCalls(response)
|
||||
@test has_toolcalls == true
|
||||
@test assistant_msg.api == "openai"
|
||||
@test assistant_msg.provider == "anthropic"
|
||||
@test assistant_msg.model == "claude-3-opus"
|
||||
end
|
||||
|
||||
# --------------------------------------------------------------- #
|
||||
# Format 2: response.content blocks (OpenAI API style) #
|
||||
# --------------------------------------------------------------- #
|
||||
|
||||
@testset "content blocks with tool_calls" begin
|
||||
response = Dict{String,Any}(
|
||||
"content" => Any[
|
||||
Dict{String,Any}("type" => "text", "text" => "Let me check."),
|
||||
Dict{String,Any}(
|
||||
"type" => "tool_calls",
|
||||
"tool_calls" => Any[
|
||||
Dict{String,Any}(
|
||||
"type" => "function",
|
||||
"function" => Dict{String,Any}(
|
||||
"name" => "getWeather",
|
||||
"arguments" => "{\"city\":\"Paris\"}",
|
||||
),
|
||||
"id" => "tc_block_1",
|
||||
),
|
||||
],
|
||||
),
|
||||
],
|
||||
)
|
||||
has_toolcalls, tc_list, assistant_msg = _extractToolCalls(response)
|
||||
@test has_toolcalls == true
|
||||
@test length(tc_list) == 1
|
||||
@test tc_list[1].name == "getWeather"
|
||||
@test tc_list[1].arguments["city"] == "Paris"
|
||||
# text block before tool_calls should be included in content
|
||||
@test length(assistant_msg.content) == 1
|
||||
@test assistant_msg.content[1].text == "Let me check."
|
||||
end
|
||||
|
||||
@testset "content blocks with tool_call (single-call format)" begin
|
||||
response = Dict{String,Any}(
|
||||
"content" => Any[
|
||||
Dict{String,Any}(
|
||||
"type" => "tool_call",
|
||||
"id" => "tc_single",
|
||||
"name" => "getTime",
|
||||
"arguments" => Dict{String,Any}("timezone" => "Europe/London"),
|
||||
),
|
||||
],
|
||||
)
|
||||
has_toolcalls, tc_list, assistant_msg = _extractToolCalls(response)
|
||||
@test has_toolcalls == true
|
||||
@test length(tc_list) == 1
|
||||
@test tc_list[1].name == "getTime"
|
||||
@test tc_list[1].id == "tc_single"
|
||||
@test tc_list[1].arguments["timezone"] == "Europe/London"
|
||||
end
|
||||
|
||||
@testset "content blocks with reasoning and text" begin
|
||||
response = Dict{String,Any}(
|
||||
"content" => Any[
|
||||
Dict{String,Any}("type" => "reasoning", "text" => "Thinking..."),
|
||||
Dict{String,Any}("type" => "text", "text" => "Here's the answer."),
|
||||
],
|
||||
)
|
||||
has_toolcalls, tc_list, assistant_msg = _extractToolCalls(response)
|
||||
@test has_toolcalls == false
|
||||
@test length(tc_list) == 0
|
||||
@test length(assistant_msg.content) == 2
|
||||
@test assistant_msg.content[1] isa reasoningContent
|
||||
@test assistant_msg.content[1].text == "Thinking..."
|
||||
@test assistant_msg.content[2] isa textContent
|
||||
@test assistant_msg.content[2].text == "Here's the answer."
|
||||
end
|
||||
|
||||
@testset "content blocks with text and tool_call (tool_call not in content)" begin
|
||||
response = Dict{String,Any}(
|
||||
"content" => Any[
|
||||
Dict{String,Any}("type" => "text", "text" => "Sure, I'll check."),
|
||||
Dict{String,Any}(
|
||||
"type" => "tool_call",
|
||||
"id" => "tc_mix",
|
||||
"name" => "getWeather",
|
||||
"arguments" => Dict{String,Any}("city" => "London"),
|
||||
),
|
||||
],
|
||||
)
|
||||
has_toolcalls, tc_list, assistant_msg = _extractToolCalls(response)
|
||||
@test has_toolcalls == true
|
||||
@test length(tc_list) == 1
|
||||
@test tc_list[1].name == "getWeather"
|
||||
# text block included, tool_call block excluded from content
|
||||
@test length(assistant_msg.content) == 1
|
||||
@test assistant_msg.content[1].text == "Sure, I'll check."
|
||||
end
|
||||
|
||||
# ------------------------------------------------------------------ #
|
||||
# assistantMessage construction #
|
||||
# ------------------------------------------------------------------ #
|
||||
|
||||
@testset "assistantMessage with error_message and errorMessage fallback" begin
|
||||
response = Dict{String,Any}(
|
||||
"error_message" => "rate limit",
|
||||
"content" => Any[Dict{String,Any}("type" => "text", "text" => "fail")],
|
||||
)
|
||||
has_toolcalls, tc_list, assistant_msg = _extractToolCalls(response)
|
||||
@test has_toolcalls == false
|
||||
@test assistant_msg.errorMessage == "rate limit"
|
||||
end
|
||||
|
||||
@testset "assistantMessage with usage tracking" begin
|
||||
response = Dict{String,Any}(
|
||||
"content" => Any[Dict{String,Any}("type" => "text", "text" => "hi")],
|
||||
"usage" => llmUsage(100, 50),
|
||||
)
|
||||
has_toolcalls, tc_list, assistant_msg = _extractToolCalls(response)
|
||||
@test assistant_msg.usage.inputTokens == 100
|
||||
@test assistant_msg.usage.outputTokens == 50
|
||||
end
|
||||
|
||||
@testset "assistantMessage with invalid usage defaults to zero" begin
|
||||
response = Dict{String,Any}(
|
||||
"content" => Any[Dict{String,Any}("type" => "text", "text" => "hi")],
|
||||
"usage" => "invalid",
|
||||
)
|
||||
has_toolcalls, tc_list, assistant_msg = _extractToolCalls(response)
|
||||
@test assistant_msg.usage.inputTokens == 0
|
||||
@test assistant_msg.usage.outputTokens == 0
|
||||
end
|
||||
|
||||
@testset "reasoning_content as textContent" begin
|
||||
response = Dict{String,Any}(
|
||||
"reasoning_content" => textContent("internal thought"),
|
||||
"content" => Any[Dict{String,Any}("type" => "text", "text" => "output")],
|
||||
)
|
||||
has_toolcalls, tc_list, assistant_msg = _extractToolCalls(response)
|
||||
@test length(assistant_msg.content) == 2
|
||||
@test assistant_msg.content[1] isa reasoningContent
|
||||
@test assistant_msg.content[1].text == "internal thought"
|
||||
@test assistant_msg.content[2] isa textContent
|
||||
@test assistant_msg.content[2].text == "output"
|
||||
end
|
||||
|
||||
# ------------------------------------------------------------------ #
|
||||
# No tool call cases #
|
||||
# ------------------------------------------------------------------ #
|
||||
|
||||
@testset "no tool calls found" begin
|
||||
response = Dict{String,Any}(
|
||||
"content" => Any[
|
||||
Dict{String,Any}("type" => "text", "text" => "Hello world."),
|
||||
],
|
||||
)
|
||||
has_toolcalls, tc_list, assistant_msg = _extractToolCalls(response)
|
||||
@test has_toolcalls == false
|
||||
@test length(tc_list) == 0
|
||||
@test assistant_msg.stopReason == "end_turn"
|
||||
end
|
||||
|
||||
@testset "empty message" begin
|
||||
response = Dict{String,Any}()
|
||||
has_toolcalls, tc_list, assistant_msg = _extractToolCalls(response)
|
||||
@test has_toolcalls == false
|
||||
@test length(tc_list) == 0
|
||||
@test assistant_msg.role == "assistant"
|
||||
@test assistant_msg.stopReason == "end_turn"
|
||||
@test length(assistant_msg.content) == 0
|
||||
end
|
||||
|
||||
@testset "message with empty tool_calls array" begin
|
||||
response = Dict{String,Any}(
|
||||
"message" => Dict{String,Any}(
|
||||
"role" => "assistant",
|
||||
"tool_calls" => Any[],
|
||||
),
|
||||
)
|
||||
has_toolcalls, tc_list, assistant_msg = _extractToolCalls(response)
|
||||
@test has_toolcalls == false
|
||||
@test length(tc_list) == 0
|
||||
@test assistant_msg.role == "assistant"
|
||||
end
|
||||
|
||||
@testset "message field is not a Dict" begin
|
||||
response = Dict{String,Any}(
|
||||
"message" => "not a dict",
|
||||
"content" => Any[Dict{String,Any}("type" => "text", "text" => "fallback")],
|
||||
)
|
||||
has_toolcalls, tc_list, assistant_msg = _extractToolCalls(response)
|
||||
@test has_toolcalls == false
|
||||
@test length(tc_list) == 0
|
||||
@test length(assistant_msg.content) == 1
|
||||
end
|
||||
|
||||
@testset "Format 1 takes priority over Format 2" begin
|
||||
response = Dict{String,Any}(
|
||||
"message" => Dict{String,Any}(
|
||||
"role" => "assistant",
|
||||
"tool_calls" => Any[
|
||||
Dict{String,Any}(
|
||||
"type" => "function",
|
||||
"function" => Dict{String,Any}(
|
||||
"name" => "getWeather",
|
||||
"arguments" => "{\"city\":\"Format1\"}",
|
||||
),
|
||||
"id" => "tc_fmt1",
|
||||
),
|
||||
],
|
||||
),
|
||||
"content" => Any[
|
||||
Dict{String,Any}(
|
||||
"type" => "tool_call",
|
||||
"id" => "tc_fmt2",
|
||||
"name" => "getTime",
|
||||
"arguments" => Dict{String,Any}("city" => "Format2"),
|
||||
),
|
||||
],
|
||||
)
|
||||
has_toolcalls, tc_list, assistant_msg = _extractToolCalls(response)
|
||||
@test has_toolcalls == true
|
||||
@test length(tc_list) == 1
|
||||
@test tc_list[1].name == "getWeather"
|
||||
end
|
||||
|
||||
# ------------------------------------------------------------------ #
|
||||
# Edge cases #
|
||||
# ------------------------------------------------------------------ #
|
||||
|
||||
@testset "tool call with null arguments" begin
|
||||
response = Dict{String,Any}(
|
||||
"message" => Dict{String,Any}(
|
||||
"role" => "assistant",
|
||||
"tool_calls" => Any[
|
||||
Dict{String,Any}(
|
||||
"type" => "function",
|
||||
"function" => Dict{String,Any}(
|
||||
"name" => "getTime",
|
||||
"arguments" => nothing,
|
||||
),
|
||||
"id" => "tc_null",
|
||||
),
|
||||
],
|
||||
),
|
||||
)
|
||||
has_toolcalls, tc_list, assistant_msg = _extractToolCalls(response)
|
||||
@test has_toolcalls == true
|
||||
@test length(tc_list) == 1
|
||||
@test tc_list[1].name == "getTime"
|
||||
end
|
||||
|
||||
@testset "tool call with missing function key" begin
|
||||
response = Dict{String,Any}(
|
||||
"message" => Dict{String,Any}(
|
||||
"role" => "assistant",
|
||||
"tool_calls" => Any[
|
||||
Dict{String,Any}(
|
||||
"type" => "function",
|
||||
"id" => "tc_nofunc",
|
||||
),
|
||||
],
|
||||
),
|
||||
)
|
||||
has_toolcalls, tc_list, assistant_msg = _extractToolCalls(response)
|
||||
@test has_toolcalls == true
|
||||
@test length(tc_list) == 1
|
||||
@test tc_list[1].name == ""
|
||||
end
|
||||
|
||||
@testset "tool call with missing name in function block" begin
|
||||
response = Dict{String,Any}(
|
||||
"message" => Dict{String,Any}(
|
||||
"role" => "assistant",
|
||||
"tool_calls" => Any[
|
||||
Dict{String,Any}(
|
||||
"type" => "function",
|
||||
"function" => Dict{String,Any}("arguments" => "{}"),
|
||||
"id" => "tc_noname",
|
||||
),
|
||||
],
|
||||
),
|
||||
)
|
||||
has_toolcalls, tc_list, assistant_msg = _extractToolCalls(response)
|
||||
@test has_toolcalls == true
|
||||
@test length(tc_list) == 1
|
||||
@test tc_list[1].name == ""
|
||||
end
|
||||
|
||||
@testset "message format with JSON.Object (JSON.parse result)" begin
|
||||
json_str = JSON.json(Dict(
|
||||
"message" => Dict(
|
||||
"role" => "assistant",
|
||||
"tool_calls" => [
|
||||
Dict(
|
||||
"type" => "function",
|
||||
"function" => Dict("name" => "getWeather", "arguments" => "{\"city\":\"Test\"}"),
|
||||
"id" => "tc_jsonobj",
|
||||
),
|
||||
],
|
||||
),
|
||||
))
|
||||
parsed = JSON.parse(json_str)
|
||||
has_toolcalls, tc_list, assistant_msg = _extractToolCalls(parsed)
|
||||
@test has_toolcalls == true
|
||||
@test length(tc_list) == 1
|
||||
@test tc_list[1].name == "getWeather"
|
||||
@test tc_list[1].arguments["city"] == "Test"
|
||||
end
|
||||
|
||||
@testset "tool_calls block with mixed content types (text + tool_calls)" begin
|
||||
response = Dict{String,Any}(
|
||||
"content" => Any[
|
||||
Dict{String,Any}("type" => "text", "text" => "I'll check both."),
|
||||
Dict{String,Any}(
|
||||
"type" => "tool_calls",
|
||||
"tool_calls" => Any[
|
||||
Dict{String,Any}(
|
||||
"type" => "function",
|
||||
"function" => Dict{String,Any}(
|
||||
"name" => "getWeather",
|
||||
"arguments" => "{\"city\":\"London\"}",
|
||||
),
|
||||
"id" => "tc_mix1",
|
||||
),
|
||||
Dict{String,Any}(
|
||||
"type" => "function",
|
||||
"function" => Dict{String,Any}(
|
||||
"name" => "getTime",
|
||||
"arguments" => "{\"timezone\":\"UTC\"}",
|
||||
),
|
||||
"id" => "tc_mix2",
|
||||
),
|
||||
],
|
||||
),
|
||||
],
|
||||
)
|
||||
has_toolcalls, tc_list, assistant_msg = _extractToolCalls(response)
|
||||
@test has_toolcalls == true
|
||||
@test length(tc_list) == 2
|
||||
@test tc_list[1].name == "getWeather"
|
||||
@test tc_list[2].name == "getTime"
|
||||
@test length(assistant_msg.content) == 1
|
||||
@test assistant_msg.content[1].text == "I'll check both."
|
||||
end
|
||||
|
||||
@testset "tool_call block without arguments field" begin
|
||||
response = Dict{String,Any}(
|
||||
"content" => Any[
|
||||
Dict{String,Any}(
|
||||
"type" => "tool_call",
|
||||
"id" => "tc_noargs",
|
||||
"name" => "getTime",
|
||||
),
|
||||
],
|
||||
)
|
||||
has_toolcalls, tc_list, assistant_msg = _extractToolCalls(response)
|
||||
@test has_toolcalls == true
|
||||
@test length(tc_list) == 1
|
||||
@test tc_list[1].arguments == Dict{String,Any}()
|
||||
end
|
||||
|
||||
@testset "tool_calls block with empty tool_calls array" begin
|
||||
response = Dict{String,Any}(
|
||||
"content" => Any[
|
||||
Dict{String,Any}(
|
||||
"type" => "tool_calls",
|
||||
"tool_calls" => Any[],
|
||||
),
|
||||
],
|
||||
)
|
||||
has_toolcalls, tc_list, assistant_msg = _extractToolCalls(response)
|
||||
@test has_toolcalls == false
|
||||
@test length(tc_list) == 0
|
||||
end
|
||||
|
||||
@testset "tool_calls block with non-AbstractDict elements" begin
|
||||
response = Dict{String,Any}(
|
||||
"content" => Any[
|
||||
Dict{String,Any}(
|
||||
"type" => "tool_calls",
|
||||
"tool_calls" => Any["not a dict", 42, nothing],
|
||||
),
|
||||
],
|
||||
)
|
||||
has_toolcalls, tc_list, assistant_msg = _extractToolCalls(response)
|
||||
@test has_toolcalls == false
|
||||
@test length(tc_list) == 0
|
||||
end
|
||||
|
||||
@testset "content field is not a Vector" begin
|
||||
response = Dict{String,Any}(
|
||||
"content" => "not a vector",
|
||||
)
|
||||
has_toolcalls, tc_list, assistant_msg = _extractToolCalls(response)
|
||||
@test has_toolcalls == false
|
||||
@test length(tc_list) == 0
|
||||
@test length(assistant_msg.content) == 0
|
||||
end
|
||||
|
||||
@testset "Dict-based response with all metadata fields" begin
|
||||
response = Dict{String,Any}(
|
||||
"api" => "openai",
|
||||
"provider" => "anthropic",
|
||||
"model" => "claude-3-sonnet",
|
||||
"content" => Any[
|
||||
Dict{String,Any}(
|
||||
"type" => "tool_call",
|
||||
"id" => "tc_meta",
|
||||
"name" => "getTime",
|
||||
"arguments" => Dict{String,Any}("city" => "Seoul"),
|
||||
),
|
||||
],
|
||||
)
|
||||
has_toolcalls, tc_list, assistant_msg = _extractToolCalls(response)
|
||||
@test has_toolcalls == true
|
||||
@test length(tc_list) == 1
|
||||
@test tc_list[1].name == "getTime"
|
||||
@test tc_list[1].arguments["city"] == "Seoul"
|
||||
@test assistant_msg.api == "openai"
|
||||
@test assistant_msg.provider == "anthropic"
|
||||
@test assistant_msg.model == "claude-3-sonnet"
|
||||
end
|
||||
|
||||
@testset "default role is assistant" begin
|
||||
response = Dict{String,Any}(
|
||||
"content" => Any[Dict{String,Any}("type" => "text", "text" => "no role specified")],
|
||||
)
|
||||
has_toolcalls, tc_list, assistant_msg = _extractToolCalls(response)
|
||||
@test assistant_msg.role == "assistant"
|
||||
end
|
||||
|
||||
@testset "tool call with custom role in message format" begin
|
||||
response = Dict{String,Any}(
|
||||
"message" => Dict{String,Any}(
|
||||
"role" => "custom_role",
|
||||
"tool_calls" => Any[
|
||||
Dict{String,Any}(
|
||||
"type" => "function",
|
||||
"function" => Dict{String,Any}(
|
||||
"name" => "getWeather",
|
||||
"arguments" => "{}",
|
||||
),
|
||||
"id" => "tc_role",
|
||||
),
|
||||
],
|
||||
),
|
||||
)
|
||||
has_toolcalls, tc_list, assistant_msg = _extractToolCalls(response)
|
||||
@test assistant_msg.role == "custom_role"
|
||||
end
|
||||
|
||||
@testset "image content block handling" begin
|
||||
response = Dict{String,Any}(
|
||||
"content" => Any[
|
||||
Dict{String,Any}(
|
||||
"type" => "image_url",
|
||||
"image_url" => Dict("url" => "data:image/png;base64,abc123"),
|
||||
),
|
||||
Dict{String,Any}("type" => "text", "text" => "What is this?"),
|
||||
],
|
||||
)
|
||||
has_toolcalls, tc_list, assistant_msg = _extractToolCalls(response)
|
||||
@test has_toolcalls == false
|
||||
@test length(assistant_msg.content) == 2
|
||||
@test assistant_msg.content[1] isa textContent
|
||||
@test assistant_msg.content[1].text == ""
|
||||
@test assistant_msg.content[2].text == "What is this?"
|
||||
end
|
||||
|
||||
end
|
||||
@@ -1,296 +0,0 @@
|
||||
using Revise
|
||||
using JSON, JSON3, Dates, UUIDs, PrettyPrinting, LibPQ, Base64, DataFrames
|
||||
using YiemAgent, GeneralUtils
|
||||
using Base.Threads
|
||||
|
||||
# ---------------------------------------------- 100 --------------------------------------------- #
|
||||
|
||||
|
||||
|
||||
# load config
|
||||
config = JSON.parsefile("/appfolder/app/dev/YiemAgent/test/config.json")
|
||||
# config = copy(JSON.parsefile("../mountvolume/config.json"))
|
||||
|
||||
|
||||
function executeSQL(sql::T) where {T<:AbstractString}
|
||||
host = config[:externalservice][:wineDB][:host]
|
||||
port = config[:externalservice][:wineDB][:port]
|
||||
dbname = config[:externalservice][:wineDB][:dbname]
|
||||
user = config[:externalservice][:wineDB][:user]
|
||||
password = config[:externalservice][:wineDB][:password]
|
||||
DBconnection = LibPQ.Connection("host=$host port=$port dbname=$dbname user=$user password=$password")
|
||||
result = LibPQ.execute(DBconnection, sql)
|
||||
close(DBconnection)
|
||||
return result
|
||||
end
|
||||
|
||||
function executeSQLVectorDB(sql)
|
||||
host = config[:externalservice][:SQLVectorDB][:host]
|
||||
port = config[:externalservice][:SQLVectorDB][:port]
|
||||
dbname = config[:externalservice][:SQLVectorDB][:dbname]
|
||||
user = config[:externalservice][:SQLVectorDB][:user]
|
||||
password = config[:externalservice][:SQLVectorDB][:password]
|
||||
DBconnection = LibPQ.Connection("host=$host port=$port dbname=$dbname user=$user password=$password")
|
||||
result = LibPQ.execute(DBconnection, sql)
|
||||
close(DBconnection)
|
||||
return result
|
||||
end
|
||||
|
||||
function text2textInstructLLM(prompt::String; maxattempt::Integer=3, modelsize::String="medium",
|
||||
llmkwargs=Dict(
|
||||
:num_ctx => 32768,
|
||||
:temperature => 0.1,
|
||||
)
|
||||
)
|
||||
msgMeta = GeneralUtils.generate_msgMeta(
|
||||
config[:externalservice][:loadbalancer][:mqtttopic];
|
||||
msgPurpose="inference",
|
||||
senderName="yiemagent",
|
||||
senderId=sessionId,
|
||||
receiverName="text2textinstruct_$modelsize",
|
||||
mqttBrokerAddress=config[:mqttServerInfo][:broker],
|
||||
mqttBrokerPort=config[:mqttServerInfo][:port],
|
||||
)
|
||||
|
||||
outgoingMsg = Dict(
|
||||
:msgMeta => msgMeta,
|
||||
:payload => Dict(
|
||||
:text => prompt,
|
||||
:kwargs => llmkwargs
|
||||
)
|
||||
)
|
||||
|
||||
response = nothing
|
||||
for attempts in 1:maxattempt
|
||||
_response = GeneralUtils.sendReceiveMqttMsg(outgoingMsg; timeout=180, maxattempt=maxattempt)
|
||||
payload = _response[:response]
|
||||
if _response[:success] && payload[:text] !== nothing
|
||||
response = _response[:response][:text]
|
||||
break
|
||||
else
|
||||
println("\n<text2textInstructLLM()> attempt $attempts/$maxattempt failed ", @__FILE__, ":", @__LINE__, " $(Dates.now())")
|
||||
pprintln(outgoingMsg)
|
||||
println("</text2textInstructLLM()> attempt $attempts/$maxattempt failed ", @__FILE__, ":", @__LINE__, " $(Dates.now())\n")
|
||||
sleep(3)
|
||||
end
|
||||
end
|
||||
|
||||
return response
|
||||
end
|
||||
|
||||
# get text embedding from a LLM service
|
||||
function getEmbedding(text::T) where {T<:AbstractString}
|
||||
msgMeta = GeneralUtils.generate_msgMeta(
|
||||
config[:externalservice][:loadbalancer][:mqtttopic];
|
||||
msgPurpose="embedding",
|
||||
senderName="yiemagent",
|
||||
senderId=sessionId,
|
||||
receiverName="textembedding",
|
||||
mqttBrokerAddress=config[:mqttServerInfo][:broker],
|
||||
mqttBrokerPort=config[:mqttServerInfo][:port],
|
||||
)
|
||||
|
||||
outgoingMsg = Dict(
|
||||
:msgMeta => msgMeta,
|
||||
:payload => Dict(
|
||||
:text => [text] # must be a vector of string
|
||||
)
|
||||
)
|
||||
|
||||
response = GeneralUtils.sendReceiveMqttMsg(outgoingMsg; timeout=120, maxattempt=3)
|
||||
embedding = response[:response][:embeddings]
|
||||
return embedding
|
||||
end
|
||||
|
||||
function findSimilarTextFromVectorDB(text::T1, tablename::T2, embeddingColumnName::T3,
|
||||
vectorDB::Function; limit::Integer=1
|
||||
)::DataFrame where {T1<:AbstractString, T2<:AbstractString, T3<:AbstractString}
|
||||
# get embedding from LLM service
|
||||
embedding = getEmbedding(text)[1]
|
||||
# check whether there is close enough vector already store in vectorDB. if no, add, else skip
|
||||
sql = """
|
||||
SELECT *, $embeddingColumnName <-> '$embedding' as distance
|
||||
FROM $tablename
|
||||
ORDER BY distance LIMIT $limit;
|
||||
"""
|
||||
response = vectorDB(sql)
|
||||
df = DataFrame(response)
|
||||
return df
|
||||
end
|
||||
|
||||
function similarSQLVectorDB(query; maxdistance::Integer=100)
|
||||
tablename = "sqlllm_decision_repository"
|
||||
# get embedding of the query
|
||||
df = findSimilarTextFromVectorDB(query, tablename,
|
||||
"function_input_embedding", executeSQLVectorDB)
|
||||
# println(df[1, [:id, :function_output]])
|
||||
row, col = size(df)
|
||||
distance = row == 0 ? Inf : df[1, :distance]
|
||||
# distance = 100 # CHANGE this is for testing only
|
||||
if row != 0 && distance < maxdistance
|
||||
# if there is usable SQL, return it.
|
||||
output_b64 = df[1, :function_output_base64] # pick the closest match
|
||||
output_str = String(base64decode(output_b64))
|
||||
rowid = df[1, :id]
|
||||
println("\n~~~ found similar sql. row id $rowid, distance $distance ", @__FILE__, ":", @__LINE__, " $(Dates.now())")
|
||||
return (dict=output_str, distance=distance)
|
||||
else
|
||||
println("\n~~~ similar sql not found, max distance $maxdistance ", @__FILE__, ":", @__LINE__, " $(Dates.now())")
|
||||
return (dict=nothing, distance=nothing)
|
||||
end
|
||||
end
|
||||
|
||||
function insertSQLVectorDB(query::T1, SQL::T2; maxdistance::Integer=3) where {T1<:AbstractString, T2<:AbstractString}
|
||||
tablename = "sqlllm_decision_repository"
|
||||
# get embedding of the query
|
||||
# query = state[:thoughtHistory][:question]
|
||||
df = findSimilarTextFromVectorDB(query, tablename,
|
||||
"function_input_embedding", executeSQLVectorDB)
|
||||
row, col = size(df)
|
||||
distance = row == 0 ? Inf : df[1, :distance]
|
||||
if row == 0 || distance > maxdistance # no close enough SQL stored in the database
|
||||
query_embedding = getEmbedding(query)[1]
|
||||
query = replace(query, "'" => "")
|
||||
sql_base64 = base64encode(SQL)
|
||||
sql_ = replace(SQL, "'" => "")
|
||||
|
||||
sql = """
|
||||
INSERT INTO $tablename (function_input, function_output, function_output_base64, function_input_embedding) VALUES ('$query', '$sql_', '$sql_base64', '$query_embedding');
|
||||
"""
|
||||
# println("\n~~~ added new decision to vectorDB ", @__FILE__, ":", @__LINE__, " $(Dates.now())")
|
||||
# println(sql)
|
||||
_ = executeSQLVectorDB(sql)
|
||||
end
|
||||
end
|
||||
|
||||
|
||||
function similarSommelierDecision(recentevents::T1; maxdistance::Integer=3
|
||||
)::Union{AbstractDict, Nothing} where {T1<:AbstractString}
|
||||
tablename = "sommelier_decision_repository"
|
||||
# find similar
|
||||
println("\n~~~ search vectorDB for this: $recentevents ", @__FILE__, " ", @__LINE__)
|
||||
df = findSimilarTextFromVectorDB(recentevents, tablename,
|
||||
"function_input_embedding", executeSQLVectorDB)
|
||||
row, col = size(df)
|
||||
distance = row == 0 ? Inf : df[1, :distance]
|
||||
if row != 0 && distance < maxdistance
|
||||
# if there is usable decision, return it.
|
||||
rowid = df[1, :id]
|
||||
println("\n~~~ found similar decision. row id $rowid, distance $distance ", @__FILE__, " ", @__LINE__)
|
||||
output_b64 = df[1, :function_output_base64] # pick the closest match
|
||||
_output_str = String(base64decode(output_b64))
|
||||
output = copy(JSON.parsefile(_output_str))
|
||||
return output
|
||||
else
|
||||
println("\n~~~ similar decision not found, max distance $maxdistance ", @__FILE__, " ", @__LINE__)
|
||||
return nothing
|
||||
end
|
||||
end
|
||||
|
||||
|
||||
function insertSommelierDecision(recentevents::T1, decision::T2; maxdistance::Integer=5
|
||||
) where {T1<:AbstractString, T2<:AbstractDict}
|
||||
tablename = "sommelier_decision_repository"
|
||||
# find similar
|
||||
df = findSimilarTextFromVectorDB(recentevents, tablename,
|
||||
"function_input_embedding", executeSQLVectorDB)
|
||||
row, col = size(df)
|
||||
distance = row == 0 ? Inf : df[1, :distance]
|
||||
if row == 0 || distance > maxdistance # no close enough SQL stored in the database
|
||||
recentevents_embedding = getEmbedding(recentevents)[1]
|
||||
recentevents = replace(recentevents, "'" => "")
|
||||
decision_json = JSON.json(decision)
|
||||
decision_base64 = base64encode(decision_json)
|
||||
decision = replace(decision_json, "'" => "")
|
||||
|
||||
sql = """
|
||||
INSERT INTO $tablename (function_input, function_output, function_output_base64, function_input_embedding) VALUES ('$recentevents', '$decision', '$decision_base64', '$recentevents_embedding');
|
||||
"""
|
||||
println("\n~~~ added new decision to vectorDB ", @__FILE__, " ", @__LINE__)
|
||||
println(sql)
|
||||
_ = executeSQLVectorDB(sql)
|
||||
else
|
||||
println("~~~ similar decision previously cached, distance $distance ", @__FILE__, " ", @__LINE__)
|
||||
end
|
||||
end
|
||||
|
||||
|
||||
sessionId = "12345"
|
||||
|
||||
externalFunction = (
|
||||
getEmbedding=getEmbedding,
|
||||
text2textInstructLLM=text2textInstructLLM,
|
||||
executeSQL=executeSQL,
|
||||
similarSQLVectorDB=similarSQLVectorDB,
|
||||
insertSQLVectorDB=insertSQLVectorDB,
|
||||
similarSommelierDecision=similarSommelierDecision,
|
||||
insertSommelierDecision=insertSommelierDecision,
|
||||
)
|
||||
|
||||
|
||||
|
||||
a = YiemAgent.sommelier(
|
||||
externalFunction;
|
||||
name="Ton",
|
||||
id=sessionId, # agent instance id
|
||||
retailername="Yiem",
|
||||
)
|
||||
|
||||
while true
|
||||
print("\nyour respond: ")
|
||||
user_answer = readline()
|
||||
response = YiemAgent.conversation(agent;
|
||||
userinput=Dict(:text=> user_answer),
|
||||
maximumMsg=50)
|
||||
println("\n$response")
|
||||
end
|
||||
|
||||
|
||||
# response = YiemAgent.conversation(a, Dict(:text=> "I want to get a French red wine under 100."))
|
||||
|
||||
|
||||
"""
|
||||
hello I want to get a bottle of red wine for my boss. I have a budget around 50 dollars. Show me some options.
|
||||
|
||||
I have no idea about his wine taste but he likes spicy food.
|
||||
|
||||
|
||||
"""
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
@@ -1,159 +0,0 @@
|
||||
using Revise
|
||||
using YiemAgent, GeneralUtils, JSON3, DataStructures
|
||||
|
||||
thoughtDict = OrderedDict(
|
||||
:Question=> "Hello, I would like a get a bottle of wine",
|
||||
:Thought_1=> "The customer wants to buy a bottle of wine, but we need more information about their preferences.",
|
||||
:Action_1=> Dict(
|
||||
:name=> "chatbox",
|
||||
:input=> "What occasion are you buying the wine for?",
|
||||
),
|
||||
:Observation_1=> "We are having a wedding pary this weekend.",
|
||||
|
||||
:Thought_2=> "A wedding party is a great occasion to have a good bottle of wine.",
|
||||
:Action_2=> Dict(
|
||||
:name=> "chatbox",
|
||||
:input=> "What type of food will you be serving with the wine?",
|
||||
),
|
||||
:Observation_2=> "I think it is Thai dishes",
|
||||
|
||||
:Thought_3=> "Now that I know the occasion and food, I need to ask about the budget.",
|
||||
:Action_3=> Dict(
|
||||
:name=> "chatbox",
|
||||
:input=> "What is your budget for this wine?",
|
||||
),
|
||||
:Observation_3=> "50 bucks",
|
||||
|
||||
:Thought_4=> "With a budget of \$50, we have a wide range of options. Now that I know it's a wedding party and Thai dishes, I need to ask about the type of wine they prefer.",
|
||||
:Action_4=> Dict(
|
||||
:name=> "chatbox",
|
||||
:input=> "What type of wine are you looking for? (Red, White, Sparkling, Rose, Dessert, Fortified)",
|
||||
),
|
||||
:Observation_4=> "Sparkling please.",
|
||||
|
||||
:Thought_5=> "Now that I know the occasion, food, budget and preferred type of wine, it's time to check our inventory for the best matching wine.",
|
||||
:Action_5=> Dict(
|
||||
:name=> "winestock",
|
||||
:input=> "wine with budget \$50, Thai dishes, sparkling, wedding party",
|
||||
),
|
||||
:Observation_5=> "I found the following wine in stock {1 : Zena Crown Vista, 2 : Schrader Cabernet Sauvignon}",
|
||||
|
||||
:Thought_6=> "Now that I have all the information, it's time to recommend a wine that fits their preferences.",
|
||||
:Action_6=> Dict(
|
||||
:name=> "recommendation",
|
||||
:input=> "I recommend Zena Crown Vista for its sparkling and affordable price.",
|
||||
),
|
||||
:Observation_6=> "I don't like it. Do you have another option?",
|
||||
)
|
||||
|
||||
_thoughtJsonStr = JSON.json(thoughtDict)
|
||||
thoughtJsonStr = _thoughtJsonStr[1:end-1] # remove } at the end
|
||||
# @show thoughtJsonStr
|
||||
|
||||
_, latestThoughtIndice = GeneralUtils.findHighestIndexKey(thoughtDict, "Thought")
|
||||
nextThoughtIndice = latestThoughtIndice + 1
|
||||
|
||||
_prompt =
|
||||
"""
|
||||
You are a helpful sommelier working for a wine store.
|
||||
Your goal is to reccommend the best wine from your inventory that match the user preferences.
|
||||
|
||||
You must follow the following criteria:
|
||||
1) Get to know what occasion the user is buying wine for
|
||||
2) Get to know what food the user will have with wine
|
||||
3) Get to know how much the user willing to spend
|
||||
4) Get to know type of wine the user is looking for e.g. Red, White, Sparkling, Rose, Dessert, Fortified
|
||||
5) Get to know what characteristics of wine the user is looking for
|
||||
e.g. tannin, sweetness, intensity, acidity
|
||||
6) Check your inventory for the best wine that match the user preference
|
||||
7) Recommend wine to the user
|
||||
|
||||
You should only respond with interleaving Thought, Action, Observation steps.
|
||||
Thought can reason about the current situation, and Action can be three types:
|
||||
1) winestock[query], which you can use to find wine in your inventory. The more input data the better.
|
||||
2) chatbox[text], which you can use to interact with the user.
|
||||
3) recommendation[answer], which returns your wine reccommendation to the user.
|
||||
|
||||
You should only respond in JSON format as describe below:
|
||||
{
|
||||
"Thought": "your reasoning",
|
||||
"Action": {"name": "action to take", "input": "Action input"},
|
||||
"Observation": "result of the action"
|
||||
}
|
||||
|
||||
Here are some examples:
|
||||
{
|
||||
"Question": "I would like to buy a sedan with 8 seats.",
|
||||
"Thought_1": "Our showroom carries various vehicle model. But I'm not sure whether we have a models that fits the user demand, I need to check our inventory.",
|
||||
"Action_1": {"name": "inventory", "input": "sedan with 8 seats."},
|
||||
"Observation_1": "Several model has 8 seats. Available color are black, red green"
|
||||
}
|
||||
{
|
||||
"Thought_2": "I have to ask the user what color he likes.",
|
||||
"Action_2": {"name": "chatbox", "input": "Which color do you like?"}
|
||||
"Observation_2": "I'll take black."
|
||||
}
|
||||
{
|
||||
"Thought_3": "There is only one model that fits the user preference. It's Yiem model A",
|
||||
"Action_3": {"name": "recommendation", "input": "I recommend a Yiem model A"}
|
||||
}
|
||||
|
||||
Let's begin!
|
||||
|
||||
$(JSON.json(thoughtDict))
|
||||
{Thought_$nextThoughtIndice
|
||||
"""
|
||||
|
||||
prompt = YiemAgent.formatLLMtext_llama3instruct("system", _prompt)
|
||||
@show prompt
|
||||
msgMeta = Dict(:requestResponse => nothing,
|
||||
:msgPurpose => nothing,
|
||||
:receiverId => nothing,
|
||||
:getPost => nothing,
|
||||
:msgId => "4c7111e0-c30e-44c3-8f85-1c8b3f03a8be",
|
||||
:acknowledgestatus => nothing,
|
||||
:replyToMsgId => nothing,
|
||||
:msgFormatVersion => nothing,
|
||||
:mqttServerInfo => Dict(:port => 1883, :broker => "mqtt.yiem.cc"),
|
||||
:sendTopic => "/loadbalancer/requestingservice",
|
||||
:receiverName => "text2textinstruct",
|
||||
:replyTopic => nothing,
|
||||
:senderName => "decisionMaker",
|
||||
:senderSelfnote => nothing,
|
||||
:senderId => "testingSessionID",
|
||||
:timeStamp => "2024-05-04T08:06:23.561"
|
||||
)
|
||||
|
||||
outgoingMsg = Dict(
|
||||
:msgMeta=> msgMeta,
|
||||
:payload=> Dict(
|
||||
:text=> prompt,
|
||||
)
|
||||
)
|
||||
|
||||
|
||||
|
||||
_response = GeneralUtils.sendReceiveMqttMsg(outgoingMsg)
|
||||
thoughtJsonStr = _response[:response][:text]
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
@@ -1,87 +0,0 @@
|
||||
using Revise # remove when this package is completed
|
||||
using YiemAgent, GeneralUtils, JSON3, MQTTClient, Dates, UUIDs, DataStructures
|
||||
using Base.Threads
|
||||
|
||||
# ---------------------------------------------- 100 --------------------------------------------- #
|
||||
|
||||
config = copy(JSON.parsefile("config.json"))
|
||||
|
||||
instanceInternalTopic = config[:serviceInternalTopic][:mqtttopic] * "/1"
|
||||
|
||||
client, connection = MakeConnection(config[:mqttServerInfo][:broker],
|
||||
config[:mqttServerInfo][:port])
|
||||
|
||||
receiveUserMsgChannel = Channel{Dict}(4)
|
||||
receiveInternalMsgChannel = Channel{Dict}(4)
|
||||
|
||||
msgMeta = GeneralUtils.generate_msgMeta(
|
||||
"N/A",
|
||||
replyTopic = config[:servicetopic][:mqtttopic] # ask frontend reply to this instance_chat_topic
|
||||
)
|
||||
|
||||
agentConfig = Dict(
|
||||
:mqttServerInfo=> config[:mqttServerInfo],
|
||||
:receivemsg=> Dict(
|
||||
:prompt=> config[:servicetopic][:mqtttopic], # topic to receive prompt i.e. frontend send msg to this topic
|
||||
:internal=> instanceInternalTopic,
|
||||
),
|
||||
:externalservice=> config[:externalservice],
|
||||
)
|
||||
|
||||
# Instantiate an agent
|
||||
tools=Dict( # update input format
|
||||
"askbox"=> Dict(
|
||||
:description => "<askbox tool description>Useful for when you need to ask the user for more context. Do not ask the user their own question.</askbox tool description>",
|
||||
:input => """<input>Input is a text in JSON format.</input><input example>{\"Q1\": \"How are you doing?\", \"Q2\": \"How may I help you?\"}</input example>""",
|
||||
:output => "" ,
|
||||
:func => nothing,
|
||||
),
|
||||
# "winestock"=> Dict(
|
||||
# :description => "<winestock tool description>A handy tool for searching wine in your inventory that match the user preferences.</winestock tool description>",
|
||||
# :input => """<input>Input is a JSON-formatted string that contains a detailed and precise search query.</input><input example>{\"wine type\": \"rose\", \"price\": \"max 35\", \"sweetness level\": \"sweet\", \"intensity level\": \"light bodied\", \"Tannin level\": \"low\", \"Acidity level\": \"low\"}</input example>""",
|
||||
# :output => """<output>Output are wines that match the search query in JSON format.""",
|
||||
# :func => ChatAgent.winestock,
|
||||
# ),
|
||||
"finalanswer"=> Dict(
|
||||
:description => "<tool description>Useful for when you are ready to recommend wines to the user.</tool description>",
|
||||
:input => """<input format>{\"finalanswer\": \"some text\"}.</input format><input example>{\"finalanswer\": \"I recommend Zena Crown Vista\"}</input example>""",
|
||||
:output => "" ,
|
||||
:func => nothing,
|
||||
),
|
||||
)
|
||||
|
||||
a = YiemAgent.sommelier(
|
||||
receiveUserMsgChannel,
|
||||
receiveInternalMsgChannel,
|
||||
agentConfig,
|
||||
name= "assistant",
|
||||
id= "testingSessionID", # agent instance id
|
||||
tools=tools,
|
||||
)
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
input =
|
||||
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)
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
@@ -1,119 +0,0 @@
|
||||
using Revise
|
||||
using YiemAgent, GeneralUtils, JSON3, DataStructures, LibPQ
|
||||
using SQLLLM
|
||||
|
||||
|
||||
# _prompt =
|
||||
# """
|
||||
# You are a helpful assistant.
|
||||
# answer the following question:
|
||||
# From the following CSV text:
|
||||
# "{\"tabledescription\":[\"The customer table stores information about customers. It includes details such as first name, last name, display name, username, password, gender, country, telephone number, email, birthdate, additional_search_term, other attributes (in JSON format) and a description.\",\"The wine table stores information about different wines. It includes details namely id, name, brand, manufacturer, region, country, wine_type, grape_variety, serving_temperature, intensity, sweetness, tannin, acidity, fizziness, additional_search_term, other attributes (in JSON format) and a description.\",\"The wine_food table represents the association between wines and food items. It estab" ⋯ 477 bytes ⋯ "ed to retailer names, usernames, passwords, addresses, contact persons, telephone numbers, email addresses, additional_search_term, other attributes (in JSON format) and a description.\",\"The retailer_wine table represents the relationship between retailers and wines. It stores information about the wines available from which retailers, including vintage, their price, and the currency.\",\"The retailer_food table represents the relationship between retailers and food items. It stores information about the food items available from which retailers, including their price and the currency.\"],\"tablename\":[\"customer\",\"wine\",\"wine_food\",\"food\",\"retailer\",\"retailer_wine\",\"retailer_food\"]}"
|
||||
# What is the description of table wine?
|
||||
# """
|
||||
|
||||
# prompt = YiemAgent.formatLLMtext_llama3instruct("system", _prompt)
|
||||
# @show prompt
|
||||
# msgMeta = Dict(:requestResponse => nothing,
|
||||
# :msgPurpose => nothing,
|
||||
# :receiverId => nothing,
|
||||
# :getPost => nothing,
|
||||
# :msgId => "4c7111e0-c30e-44c3-8f85-1c8b3f03a8be",
|
||||
# :acknowledgestatus => nothing,
|
||||
# :replyToMsgId => nothing,
|
||||
# :msgFormatVersion => nothing,
|
||||
# :mqttServerInfo => Dict(:port => 1883, :broker => "mqtt.yiem.cc"),
|
||||
# :sendTopic => "/loadbalancer/requestingservice",
|
||||
# :receiverName => "text2textinstruct",
|
||||
# :replyTopic => nothing,
|
||||
# :senderName => "decisionMaker",
|
||||
# :senderSelfnote => nothing,
|
||||
# :senderId => "testingSessionID",
|
||||
# :timeStamp => "2024-05-04T08:06:23.561"
|
||||
# )
|
||||
|
||||
# outgoingMsg = Dict(
|
||||
# :msgMeta=> msgMeta,
|
||||
# :payload=> Dict(
|
||||
# :text=> prompt,
|
||||
# )
|
||||
# )
|
||||
|
||||
|
||||
|
||||
# _response = GeneralUtils.sendReceiveMqttMsg(outgoingMsg)
|
||||
# result = _response[:response][:text]
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
DBconnection = LibPQ.Connection("host=192.168.88.12 port=5432 dbname=yiem_wine_assistant user=yiem password=yiem@Postgres_0.0")
|
||||
|
||||
tableinfo, df1, df2, df3 = SQLLLM.tableinfo(DBconnection, "wine")
|
||||
|
||||
|
||||
_prompt =
|
||||
"""
|
||||
You are a helpful assistant helping to answer user question from a database table.
|
||||
|
||||
$tableinfo
|
||||
|
||||
Are there any chardonnay?
|
||||
"""
|
||||
|
||||
prompt = YiemAgent.formatLLMtext_llama3instruct("system", _prompt)
|
||||
@show prompt
|
||||
msgMeta = Dict(:requestResponse => nothing,
|
||||
:msgPurpose => nothing,
|
||||
:receiverId => nothing,
|
||||
:getPost => nothing,
|
||||
:msgId => "4c7111e0-c30e-44c3-8f85-1c8b3f03a8be",
|
||||
:acknowledgestatus => nothing,
|
||||
:replyToMsgId => nothing,
|
||||
:msgFormatVersion => nothing,
|
||||
:mqttServerInfo => Dict(:port => 1883, :broker => "mqtt.yiem.cc"),
|
||||
:sendTopic => "/loadbalancer/requestingservice",
|
||||
:receiverName => "text2textinstruct",
|
||||
:replyTopic => nothing,
|
||||
:senderName => "decisionMaker",
|
||||
:senderSelfnote => nothing,
|
||||
:senderId => "testingSessionID",
|
||||
:timeStamp => "2024-05-04T08:06:23.561"
|
||||
)
|
||||
|
||||
outgoingMsg = Dict(
|
||||
:msgMeta=> msgMeta,
|
||||
:payload=> Dict(
|
||||
:text=> prompt,
|
||||
)
|
||||
)
|
||||
|
||||
|
||||
|
||||
_response = GeneralUtils.sendReceiveMqttMsg(outgoingMsg)
|
||||
result2 = _response[:response][:text]
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
@@ -0,0 +1,5 @@
|
||||
using Test
|
||||
using YiemAgent
|
||||
|
||||
include("toolTest.jl")
|
||||
include("_extractToolCalls.jl")
|
||||
@@ -1,223 +0,0 @@
|
||||
|
||||
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(sender_id::String, openai_msg::Dict{String, Any})
|
||||
payloads = [("msg", openai_msg, "dictionary")] # List of tuples
|
||||
_, msg_envelope_json_str = msghandler.smartpack(
|
||||
config["externalservice"]["servicesloadbalancer"]["nats"],
|
||||
payloads;
|
||||
sender_id=sender_id,
|
||||
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,$(image1_base64_string)"
|
||||
|
||||
# 3. Construct payload with the Data URI
|
||||
openai_msg = Dict(
|
||||
"model" => "gemma-4-E4B-it-UD-Q4_K_XL",
|
||||
"messages" => [
|
||||
Dict(
|
||||
"role" => "user",
|
||||
"content" => [
|
||||
Dict("type" => "text", "text" => "Do you know this wine? Just give me brief intro."),
|
||||
Dict(
|
||||
"type" => "image_url",
|
||||
"image_url" => Dict("url" => data1_uri)
|
||||
)
|
||||
]
|
||||
)
|
||||
],
|
||||
"temperature" => 0.7
|
||||
)
|
||||
|
||||
llm_response = text2text_instruct_llm(openai_msg)
|
||||
|
||||
|
||||
|
||||
# 1. Read local file and encode to base64 string
|
||||
image2_path = "test/large_image.png"
|
||||
image2_bytes = read(image2_path)
|
||||
image2_base64_string = base64encode(image2_bytes)
|
||||
|
||||
# 2. Match the MIME type according to your file extension (e.g., png, jpeg)
|
||||
mime_type = "image/png"
|
||||
data2_uri = "data:$(mime_type);base64,$(image2_base64_string)"
|
||||
|
||||
systemmsg =
|
||||
"""
|
||||
# Store Policy
|
||||
- Generally speaking, the store inventory has some wines from France, the United States, Australia, Spain, and Italy, but you won't know exactly until you check your inventory.
|
||||
- If you found wines in the store's database, they are in stock.
|
||||
- You can only recommend wines that are currently in our inventory
|
||||
- Before searching the database for wine, ensure you have at least the following information: 1) budget, 2) wine type, and 3) occasion. Additional details are always helpful. If the user is unsure, provide relevant information and gather insights to make reasonable inferences.
|
||||
- Ask the user one question at a time.
|
||||
- Do not ask the user about wine's flavor e.g. floral, citrusy, nutty or some thing similar as these terms cannot be used to search the database.
|
||||
- Once the user has selected their wine, if you haven't already, ask the user whether they need any further assistance. Do not offer any additional services.
|
||||
- Only end the conversation when the user explicitly intends to do so. When ending, ensure a polite farewell and an invitation to return in the future.
|
||||
- Spicy foods should be paired only with light red wines.
|
||||
- We do not sell organic, sustainable, gluten-free, and sulfite-free wine. Inform the user imediately if they are looking for these types of wines. Do not sell our wines as such.
|
||||
- Gift box, gift card, and custom messages are available. Inform the user to contact our sales team.
|
||||
|
||||
# Store Guidelines
|
||||
- Greeting the customer warmly by ask them how could you help. Do not ask any other questions during this greeting.
|
||||
- Customer may provide images for you to look up.
|
||||
- Encourage the customer to explore different options and try new things.
|
||||
- If you are unable to locate the desired item in the database after 2 attempts, it may not be available in your inventory. In such cases, inform the user that the item is unavailable and suggest an alternative instead.
|
||||
- Your store carries only wine.
|
||||
- Vintage 0 means non-vintage.
|
||||
- Start searching the database as broadly as possible within the given information boundary to maximize the chances of finding. Avoid unnecessary parameters unless specified by the user. Refine the search subsequently.
|
||||
|
||||
# Situation
|
||||
Your customer is coming into the store
|
||||
|
||||
# Role
|
||||
Your name is Janie. You are a helpful sommelier for website-based Yiem Wine's wine store. You are working under your mentor supervision.
|
||||
|
||||
# Objective
|
||||
1. Establish a connection with the customer by talking to them politely and showing your enthusiasm for their wine preferences.
|
||||
2. Provide relevant information and guide them to select the best wines only from your store's inventory that align with their preferences.
|
||||
|
||||
# Responsibility Includes
|
||||
1. According to the store's policy and guidelines, make an informed decision about what you need to do to achieve the objective
|
||||
2. Keep the conversation with the customer going smoothly
|
||||
3. Obey your mentor's suggestions.
|
||||
|
||||
# Responsibility Does NOT Include
|
||||
|
||||
1. Requesting the user to place an order, make a purchase, or confirm the order. These are the job of our sales team at the store.
|
||||
2. Processing sales orders or engaging in any other sales-related activities. These are the job of our sales team at the store.
|
||||
3. Answering questions or offering additional services beyond those related to your store's wine recommendations such as discounts, quantity, rewards programs, promotions, delivery options, shipping, boxes, gift wrapping, packaging, personalized messages or something similar. These are the job of our sales team at the store.
|
||||
|
||||
# You should then respond to the user with interleaving plan, action_name, action_input
|
||||
1) plan: Based on the current situation, state a complete action plan to complete the task and rationale. Be specific.
|
||||
2) action_name: (Typically corresponds to the execution of the first step in your plan) Can be one of the available_actions name
|
||||
3) action_input: The input to the action you are about to perform according to your plan.
|
||||
After the action is executed you gets "action_result". It is the output from the action you selected.
|
||||
|
||||
# You should only respond in JSON format as described below
|
||||
"plan": "...",
|
||||
"action_name": "...",
|
||||
"action_input": "..."
|
||||
|
||||
# Available Actions
|
||||
- **CHAT_BOX** which you can use to talk with the user.
|
||||
- **SEARCH_WINE_DATABASE** allows you to check information about wines you want in your inventory's database. The input is text that specify supported search criteria includeing: retailer_name, wine price, winery, name, vintage, region, country, type, grape varietal, tasting notes, occasion, food pairing, intensity, tannin, sweetness, and acidity.
|
||||
- Example query 1: "Dry, full-bodied red wine from 1) region: Burgundy, country: France or 2) region: Tuscany, country: Italy. Grape varietal: Merlot or Syrah. price 100 to 1000 USD."
|
||||
- Example query 2: "Red or white wine, medium tannin, price under 700 USD"
|
||||
- Example query 3: "white wine, region: Tuscany or Bordeaux, country: Italy or France
|
||||
- **PRESENT_WINE_GUIDELINE** which you can use to check the store guidelines about how to present wines you have found to the user. The input is "nothing" keyword. The output is the guidelines that you can follow.
|
||||
- **END_CONVER_GUIDELINE** which you can use to check the store guidelines about how to end the conversation with the user. The input is "nothing" keyword. The output is the guidelines that you can follow.
|
||||
"""
|
||||
|
||||
|
||||
openai_msg = Dict(
|
||||
"model" => "gemma-4-E4B-it-UD-Q4_K_XL",
|
||||
"messages" => [
|
||||
Dict(
|
||||
"role" => "system",
|
||||
"content" => [
|
||||
Dict("type" => "text", "text" => systemmsg),
|
||||
]
|
||||
),
|
||||
Dict(
|
||||
"role" => "user",
|
||||
"content" => [
|
||||
Dict("type" => "text", "text" => "Do you know this wine? Just give me brief intro."),
|
||||
]
|
||||
),
|
||||
Dict(
|
||||
"role" => "assistant",
|
||||
"content" => [
|
||||
Dict("type" => "text", "text" =>
|
||||
"""
|
||||
" <plan>I will greet the customer warmly as Janie, acknowledge their request to find a similar wine for their wedding party based on the image, identify the wine type and country (Italian Sparkling Wine), and then use the SEARCH_WINE_DATABASE action to search the inventory for suitable options.</plan>\n <action_name>CHAT_BOX</action_name>\n <action_input>Hello! I'm Janie, and I'd be delighted to help you find the perfect wine for your wedding party. That beautiful wine in the image appears to be an Italian sparkling wine, which is wonderful for a celebration like a wedding! Since you have an unlimited budget, I can certainly look for some truly exceptional options. To start, I will check our inventory for similar Italian sparkling wines that are perfect for a wedding celebration.</action_input><action_result> User response in the next message </action_result>"
|
||||
"""
|
||||
),
|
||||
]
|
||||
),
|
||||
Dict(
|
||||
"role" => "user",
|
||||
"content" => [
|
||||
Dict("type" => "text", "text" => "ok"),
|
||||
]
|
||||
),
|
||||
],
|
||||
"temperature" => 0.7
|
||||
)
|
||||
|
||||
llm_response = text2text_instruct_llm(openai_msg)
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
# ---------------------------------------------- 100 --------------------------------------------- #
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
-401
@@ -1,401 +0,0 @@
|
||||
using JSON, Dates, UUIDs, PrettyPrinting, LibPQ, Base64, DataFrames, DataStructures, HTTP, Base64,
|
||||
NATS, Base.Threads
|
||||
using YiemAgent, GeneralUtils, msghandler
|
||||
|
||||
function text2text_instruct_llm(sender_id::String, openai_msg::Dict{String, Any})
|
||||
payloads = [("msg", openai_msg, "dictionary")] # List of tuples
|
||||
_, msg_envelope_json_str = msghandler.smartpack(
|
||||
config["externalservice"]["servicesloadbalancer"]["nats"],
|
||||
payloads;
|
||||
sender_id=sender_id,
|
||||
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
|
||||
|
||||
""" get a single text embedding from a LLM service
|
||||
Example
|
||||
text = ["hello"]
|
||||
embedding = get_embedding(text)
|
||||
"""
|
||||
function get_embedding(text::AbstractArray{String})
|
||||
documents_dict = Dict("documents" => text)
|
||||
payloads = [("documents", documents_dict, "dictionary")]
|
||||
_, msg_envelope_json_str = msghandler.smartpack(
|
||||
config["externalservice"]["servicesloadbalancer"]["nats"],
|
||||
payloads;
|
||||
msg_purpose="embedding",
|
||||
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)
|
||||
embedding_response = incoming_env["payloads"][1][2]
|
||||
|
||||
return embedding_response
|
||||
end
|
||||
|
||||
""" sql = "SELECT * FROM wine;"
|
||||
result = execute_sql_winedb(sql)
|
||||
"""
|
||||
function execute_sql_winedb(sql::T) where {T<:AbstractString}
|
||||
host_url, _port = split(config["externalservice"]["sommpanion_db"]["url"], ':')
|
||||
port = parse(Int, _port)
|
||||
dbname = "winedb"
|
||||
user = config["externalservice"]["sommpanion_db"]["user"]
|
||||
password = config["externalservice"]["sommpanion_db"]["password"]
|
||||
db_connection = LibPQ.Connection("host=$host_url port=$port dbname=$dbname user=$user password=$password")
|
||||
result = nothing
|
||||
try
|
||||
result = LibPQ.execute(db_connection, sql)
|
||||
catch e
|
||||
LibPQ.close(db_connection)
|
||||
end
|
||||
|
||||
LibPQ.close(db_connection)
|
||||
return result
|
||||
end
|
||||
|
||||
""" find similar sql from vector database
|
||||
sql = "SELECT * FROM wine;"
|
||||
result, distance = similar_sql_vectordb(sql)
|
||||
"""
|
||||
function similar_sql_vectordb(sql::T; maxdistance::Number=0.2) where {T<:AbstractString}
|
||||
tablename = "sqlllm_decision_repository"
|
||||
# get embedding of the query
|
||||
df = find_similar_text_from_vectordb(sql, tablename,
|
||||
"function_input_embedding", execute_sql_vectordb)
|
||||
# println(df[1, [:id, :function_output]])
|
||||
row, col = size(df)
|
||||
distance = row == 0 ? Inf : df[1, :distance]
|
||||
if row != 0 && distance < maxdistance
|
||||
# if there is usable SQL, return it.
|
||||
output_b64 = df[1, :function_output_base64] # pick the closest match
|
||||
output_str = String(base64decode(output_b64))
|
||||
rowid = df[1, :id]
|
||||
println("\n--| similar sql found. row id $rowid, distance $distance ", @__FILE__, ":", @__LINE__, " $(Dates.now())")
|
||||
pprintln(output_str)
|
||||
return (result=output_str, distance=distance)
|
||||
else
|
||||
println("\n--| similar sql not found, max distance $maxdistance ", @__FILE__, ":", @__LINE__, " $(Dates.now())")
|
||||
return (result=nothing, distance=nothing)
|
||||
end
|
||||
end
|
||||
|
||||
""" insert query and sql into vector database
|
||||
query = "get all wines from wine table"
|
||||
sql = "SELECT * FROM wine;"
|
||||
insert_sql_vectordb(query, sql)
|
||||
"""
|
||||
function insert_sql_vectordb(query::T1, SQL::T2; maxdistance::Number=3
|
||||
) where {T1<:AbstractString, T2<:AbstractString}
|
||||
|
||||
tablename = "sqlllm_decision_repository"
|
||||
# get embedding of the query
|
||||
# query = state[:thoughtHistory][:question]
|
||||
df = find_similar_text_from_vectordb(query, tablename,
|
||||
"function_input_embedding", execute_sql_vectordb)
|
||||
row, col = size(df)
|
||||
distance = row == 0 ? Inf : df[1, :distance]
|
||||
if row == 0 || distance > maxdistance # no close enough SQL stored in the database
|
||||
_query_embedding = get_embedding([query])
|
||||
_query_embedding = GeneralUtils.dictify(_query_embedding)
|
||||
# println("\n--- _query_embedding() ", @__FILE__, ":", @__LINE__, " $(Dates.now())")
|
||||
# println(_query_embedding)
|
||||
# println("---\n")
|
||||
query_embedding = _query_embedding["data"][1]["embedding"]
|
||||
query = replace(query, "'" => "")
|
||||
sql_base64 = base64encode(SQL)
|
||||
sql_ = replace(SQL, "'" => "")
|
||||
|
||||
sql =
|
||||
"""
|
||||
INSERT INTO $tablename (function_input, function_output, function_output_base64, function_input_embedding) VALUES ('$query', '$sql_', '$sql_base64', '$query_embedding');
|
||||
"""
|
||||
# println("\n--| added new decision to vectorDB ", @__FILE__, ":", @__LINE__, " $(Dates.now())")
|
||||
# println(sql)
|
||||
_ = execute_sql_vectordb(sql)
|
||||
end
|
||||
end
|
||||
|
||||
""" execute sql against vectordb
|
||||
sql = "SELECT * FROM wine;"
|
||||
result = execute_sql_vectordb(sql)
|
||||
"""
|
||||
function execute_sql_vectordb(sql::T) where {T<:AbstractString}
|
||||
host_url, _port = split(config["externalservice"]["sommpanion_vectordb"]["url"], ':')
|
||||
port = parse(Int, _port)
|
||||
dbname = config["externalservice"]["sommpanion_vectordb"]["dbname"]
|
||||
user = config["externalservice"]["sommpanion_vectordb"]["user"]
|
||||
password = config["externalservice"]["sommpanion_vectordb"]["password"]
|
||||
DBconnection = LibPQ.Connection("host=$host_url port=$port dbname=$dbname user=$user password=$password")
|
||||
result = LibPQ.execute(DBconnection, sql)
|
||||
close(DBconnection)
|
||||
return result
|
||||
end
|
||||
|
||||
""" search similar decision llm made from vectordb
|
||||
"""
|
||||
function similar_sommelier_decision(recentevents::T1; maxdistance::Integer=3
|
||||
)::Union{AbstractDict, Nothing} where {T1<:AbstractString}
|
||||
|
||||
tablename = "sommelier_decision_repository"
|
||||
# find similar
|
||||
df = find_similar_text_from_vectordb(recentevents, tablename,
|
||||
"function_input_embedding", execute_sql_vectordb)
|
||||
row, col = size(df)
|
||||
distance = row == 0 ? Inf : df[1, :distance]
|
||||
if row != 0 && distance < maxdistance
|
||||
# if there is usable decision, return it.
|
||||
rowid = df[1, :id]
|
||||
println("\n--| found similar decision. row id $rowid, distance $distance ", @__FILE__, " ", @__LINE__)
|
||||
output_b64 = df[1, :function_output_base64] # pick the closest match
|
||||
_output_str = String(base64decode(output_b64))
|
||||
output = copy(JSON.read(_output_str))
|
||||
return output
|
||||
else
|
||||
println("\n--| similar decision not found, max distance $maxdistance ", @__FILE__, " ", @__LINE__)
|
||||
return nothing
|
||||
end
|
||||
end
|
||||
|
||||
""" search similar text from vectordb
|
||||
"""
|
||||
function find_similar_text_from_vectordb(text::T1, tablename::T2, embeddingColumnName::T3,
|
||||
vectorDB::Function; limit::Integer=1
|
||||
)::DataFrame where {T1<:AbstractString, T2<:AbstractString, T3<:AbstractString}
|
||||
# get embedding from LLM service
|
||||
_embedding = get_embedding([text])
|
||||
_embedding = _embedding["data"][1]["embedding"]
|
||||
_embedding = "$_embedding"
|
||||
|
||||
embedding = _embedding[4:end]
|
||||
|
||||
# check whether there is close enough vector already store in vectorDB. if no, add, else skip
|
||||
sql = """
|
||||
SELECT *, $embeddingColumnName <-> '$embedding' as distance
|
||||
FROM $tablename
|
||||
ORDER BY distance LIMIT $limit;
|
||||
"""
|
||||
response = vectorDB(sql)
|
||||
df = DataFrame(response)
|
||||
|
||||
return df
|
||||
end
|
||||
|
||||
""" insert decision llm made to vectordb
|
||||
"""
|
||||
function insert_sommelier_decision(recentevents::T1, decision::T2; maxdistance::Integer=5
|
||||
) where {T1<:AbstractString, T2<:AbstractDict}
|
||||
tablename = "sommelier_decision_repository"
|
||||
# find similar
|
||||
df = find_similar_text_from_vectordb(recentevents, tablename,
|
||||
"function_input_embedding", execute_sql_vectordb)
|
||||
row, col = size(df)
|
||||
distance = row == 0 ? Inf : df[1, :distance]
|
||||
if row == 0 || distance > maxdistance # no close enough SQL stored in the database
|
||||
_embedding = get_embedding([recentevents])[1]
|
||||
recentevents_embedding = _embedding["data"][1]["embedding"]
|
||||
recentevents = replace(recentevents, "'" => "")
|
||||
decision_json = JSON.json(decision)
|
||||
decision_base64 = base64encode(decision_json)
|
||||
decision = replace(decision_json, "'" => "")
|
||||
|
||||
sql =
|
||||
"""
|
||||
INSERT INTO $tablename (function_input, function_output, function_output_base64, function_input_embedding) VALUES ('$recentevents', '$decision', '$decision_base64', '$recentevents_embedding');
|
||||
"""
|
||||
println("\n--| added new decision to vectorDB ", @__FILE__, " ", @__LINE__)
|
||||
println(sql)
|
||||
_ = execute_sql_vectordb(sql)
|
||||
else
|
||||
println("--| similar decision previously cached, distance $distance ", @__FILE__, " ", @__LINE__)
|
||||
end
|
||||
end
|
||||
|
||||
config = JSON.parsefile("./appconfig.json")
|
||||
sessionId = "0"
|
||||
backend_session_topic = "sommpanion.testsubject"
|
||||
agent_ch = Channel(8)
|
||||
agent_conn = NATS.connect(config["nats_server_info"]["url"])
|
||||
|
||||
sub2 = NATS.subscribe(agent_conn, backend_session_topic) do msg
|
||||
put!(agent_ch, msg)
|
||||
end
|
||||
|
||||
agent_context = YiemAgent.agentcontext(
|
||||
text2text_instruct_llm,
|
||||
get_embedding,
|
||||
execute_sql_winedb,
|
||||
similar_sql_vectordb,
|
||||
insert_sql_vectordb,
|
||||
similar_sommelier_decision,
|
||||
insert_sommelier_decision
|
||||
)
|
||||
|
||||
# can't instantiate
|
||||
agent = YiemAgent.sommelier(
|
||||
agent_context;
|
||||
name="Janie",
|
||||
id=sessionId, # agent instance id
|
||||
retailername="Yiem Wine Ltd.",
|
||||
llmFormatName=""
|
||||
)
|
||||
|
||||
|
||||
image1_path = "test/large_image.png"
|
||||
image1_bytes = read(image1_path)
|
||||
image1_base64_string = base64encode(image1_bytes)
|
||||
mime_type = "image/png"
|
||||
data1_uri = "data:$(mime_type);base64,$(image1_base64_string)"
|
||||
|
||||
# 1. Read local file and encode to base64 string
|
||||
image2_path = "test/small_image.png"
|
||||
image2_bytes = read(image2_path)
|
||||
image2_base64_string = base64encode(image2_bytes)
|
||||
mime_type = "image/png"
|
||||
data2_uri = "data:$(mime_type);base64,$(image2_base64_string)"
|
||||
|
||||
# 3. Construct payload with the Data URI
|
||||
message = Dict(
|
||||
"role" => "user",
|
||||
"content" => [
|
||||
Dict("type" => "text", "text" => "Do you know type of wine in the image?"),
|
||||
Dict(
|
||||
"type" => "image_url",
|
||||
"image_url" => Dict("url" => data1_uri)
|
||||
)
|
||||
]
|
||||
)
|
||||
|
||||
result = YiemAgent.conversation(agent; userinput=message)
|
||||
println("\n$result")
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
# message = Dict(
|
||||
# "role" => "user",
|
||||
# "content" => [
|
||||
# Dict("type" => "text", "text" =>
|
||||
# "
|
||||
# เป็นงานเลี้ยงทั่วไป
|
||||
# "),
|
||||
# ]
|
||||
# )
|
||||
|
||||
# result = YiemAgent.conversation(agent; userinput=message)
|
||||
# println("\n$result")
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
# message = Dict(
|
||||
# "role" => "user",
|
||||
# "content" => [
|
||||
# Dict("type" => "text", "text" => "no thanks. that's all"),
|
||||
# ]
|
||||
# )
|
||||
|
||||
# result = YiemAgent.conversation(agent; userinput=message)
|
||||
# println("\n$result")
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
# message = Dict(
|
||||
# "role" => "user",
|
||||
# "content" => [
|
||||
# Dict("type" => "text", "text" => "What about this wine?"),
|
||||
# Dict(
|
||||
# "type" => "image_url",
|
||||
# "image_url" => Dict("url" => data2_uri)
|
||||
# )
|
||||
# ]
|
||||
# )
|
||||
|
||||
# result = YiemAgent.conversation(agent; userinput=message)
|
||||
# println("\n$result")
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
Reference in New Issue
Block a user