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 lamaiin
2024-05-11 15:34:51 +07:00
parent d88c613b0e
commit 2e9c21f243
5 changed files with 226 additions and 266 deletions
Download Patch File Download Diff File Expand all files Collapse all files

252
src/interface.jl
View File

@@ -126,7 +126,7 @@ function decisionMaker(a::T1, state::T2)::Dict{Symbol, Any} where {T1<:agent, T2
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
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
@@ -197,51 +197,49 @@ function decisionMaker(a::T1, state::T2)::Dict{Symbol, Any} where {T1<:agent, T2
)
)
@show outgoingMsg
attempt = 0
while true
attempt += 1
if attempt <= 5
try
response = GeneralUtils.sendReceiveMqttMsg(outgoingMsg)
_responseJsonStr = response[:response][:text]
expectedJsonExample =
"""
Here is an expected JSON format:
{
"thought": "...",
"action": {"name": "...", "input": "..."},
"observation": "..."
}
"""
responseJsonStr = jsoncorrection(a, _responseJsonStr, expectedJsonExample)
thoughtDict = copy(JSON3.read(responseJsonStr))
# check if dict has all required value
dummya::AbstractString = thoughtDict[:thought]
actionname::AbstractString = thoughtDict[:action][:name]
actioninput::AbstractString = thoughtDict[:action][:input]
for attempt in 1:5
try
response = GeneralUtils.sendReceiveMqttMsg(outgoingMsg)
_responseJsonStr = response[:response][:text]
expectedJsonExample =
"""
Here is an expected JSON format:
{
"thought": "...",
"action": {"name": "...", "input": "..."},
"observation": "..."
}
"""
responseJsonStr = jsoncorrection(a, _responseJsonStr, expectedJsonExample)
thoughtDict = copy(JSON3.read(responseJsonStr))
if actionname ∈ ["winestock", "chatbox", "recommendbox"]
# LLM use available function
else
error("DecisionMaker use wrong function")
end
return thoughtDict
catch e
io = IOBuffer()
showerror(io, e)
errorMsg = String(take!(io))
st = sprint((io, v) -> show(io, "text/plain", v), stacktrace(catch_backtrace()))
println("")
@warn "Error occurred: $errorMsg\n$st"
println("")
# check if dict has all required value
thought::AbstractString = thoughtDict[:thought]
actionname::AbstractString = thoughtDict[:action][:name]
actioninput::AbstractString = thoughtDict[:action][:input]
if actionname ∈ ["winestock", "chatbox", "recommendbox"]
# LLM use available function
elseif thought == ""
error("DecisionMaker has no thought")
elseif length(actioninput) == 0
error("DecisionMaker has no actioninput")
else
error("DecisionMaker use wrong function")
end
else
error("DecisionMaker failed to generate a thought")
return thoughtDict
catch e
io = IOBuffer()
showerror(io, e)
errorMsg = String(take!(io))
st = sprint((io, v) -> show(io, "text/plain", v), stacktrace(catch_backtrace()))
println("")
@warn "Attempt $attempt. Error occurred: $errorMsg\n$st"
println("")
end
end
error("DecisionMaker failed to generate a thought")
end
@@ -297,7 +295,22 @@ function progressValueEstimator(a::T1, state::T2)::Tuple{String, Integer} where
}
{"evaluation": "This trajectory is correct as it is reasonable to check an inventory for info provided in the question.
It is also better to have simple searches corresponding to a single entity, making this the best action.",
"score": 10}
"score": 10
}
{
"question": "Do you have an all-in-one pen with 4 colors and a pencil for sale?",
"thought_1": "Let me check our inventory first to see if I have it.",
"action_1": {"name": "inventory", "input": "pen with 4 color and a pencil."},
"observation_1": "I found {1: "Pilot Dr. grip 4-in-1 pen", 2: "Rotting pencil"}",
"thought_2": "Ok, I have what the user is asking. Let's tell the user.",
"action_2": {"name": "chatbox", "input": "Yes, we do have a Pilot Dr. grip 4-in-1 pen and a Rotting pencil"},
"observation_1": "This is not what I wanted."
}
{"evaluation": "This trajectory is incorrect as my search term should be related to a 4-colors pen with a pencil in it,
not a pen and a pencil seperately. A better search term should have been a 4-colors pen with a pencil, all-in-one.",
"score": 2
}
Let's begin!:
$(JSON3.write(state[:thoughtHistory]))
@@ -334,40 +347,34 @@ function progressValueEstimator(a::T1, state::T2)::Tuple{String, Integer} where
)
)
attempt = 0
while true
attempt += 1
if attempt <= 5
try
response = GeneralUtils.sendReceiveMqttMsg(outgoingMsg)
_responseJsonStr = response[:response][:text]
expectedJsonExample =
"""
Here is an expected JSON format:
{"evaluation": "...", "score": "..."}
"""
responseJsonStr = jsoncorrection(a, _responseJsonStr, expectedJsonExample)
evaluationDict = copy(JSON3.read(responseJsonStr))
for attempt in 1:5
try
response = GeneralUtils.sendReceiveMqttMsg(outgoingMsg)
_responseJsonStr = response[:response][:text]
expectedJsonExample =
"""
Here is an expected JSON format:
{"evaluation": "...", "score": "..."}
"""
responseJsonStr = jsoncorrection(a, _responseJsonStr, expectedJsonExample)
evaluationDict = copy(JSON3.read(responseJsonStr))
# check if dict has all required value
dummya::AbstractString = evaluationDict[:evaluation]
dummyb::Integer = evaluationDict[:score]
# check if dict has all required value
dummya::AbstractString = evaluationDict[:evaluation]
dummyb::Integer = evaluationDict[:score]
return (evaluationDict[:evaluation], evaluationDict[:score])
catch e
io = IOBuffer()
showerror(io, e)
errorMsg = String(take!(io))
st = sprint((io, v) -> show(io, "text/plain", v), stacktrace(catch_backtrace()))
println("")
@warn "Error occurred: $errorMsg\n$st"
println("")
end
else
error("progressValueEstimator failed to generate an evaluation")
return (evaluationDict[:evaluation], evaluationDict[:score])
catch e
io = IOBuffer()
showerror(io, e)
errorMsg = String(take!(io))
st = sprint((io, v) -> show(io, "text/plain", v), stacktrace(catch_backtrace()))
println("")
@warn "Attempt $attempt. Error occurred: $errorMsg\n$st"
println("")
end
end
error("progressValueEstimator failed to generate an evaluation")
end
@@ -392,55 +399,6 @@ julia>
function reflector(a::T1, state::T2)::String where {T1<:agent, T2<:AbstractDict}
# https://github.com/andyz245/LanguageAgentTreeSearch/blob/main/hotpot/hotpot.py
# _prompt =
# """
# You are an advanced reasoning agent that can improve based on self refection.
# You will be given the information related to the previous help you've done for a user.
# You were unsuccessful in helping the user either because you guessed the wrong answer with Finish[answer], or you used up your set number of reasoning steps.
# In a few sentences, Diagnose a possible reason for failure and devise a new, concise, high level plan that aims to mitigate the same failure.
# Use complete sentences.
# You should only respond in JSON format as describe below:
# {"reflection": "your relection"}
# Here are some examples:
# Previous Trial:
# {
# "question": "Hello, I would like a get a bottle of wine",
# "thought_1": "A customer wants to buy a bottle of wine. Before making a recommendation, I need to know more about their preferences.",
# "action_1": {"name": "chatbox", "input": "What is the occasion for which you're buying this wine?"},
# "observation_1": "We are holding a wedding party",
# "thought_2": "A wedding party, that's a great occasion! The customer might be looking for a celebratory drink. Let me ask some more questions to narrow down the options.",
# "action_2": {"name": "chatbox", "input": "What type of food will you be serving at the wedding?"},
# "observation_2": "It will be Thai dishes.",
# "thought_3": "With Thai food, I should recommend a wine that complements its spicy and savory flavors. And since it's a celebratory occasion, the customer might prefer a full-bodied wine.",
# "action_3": {"name": "chatbox", "input": "What is your budget for this bottle of wine?"},
# "observation_3": "I would spend up to 50 bucks.",
# "thought_4": "Now that I have some more information, it's time to narrow down the options.",
# "action_4": {"name": "winestock", "input": "red wine with full body, pairs well with spicy food, budget \$50"},
# "observation_4": "I found the following wines in our stock: \n{\n 1: El Enemigo Cabernet Franc 2019\n2: Tantara Chardonnay 2017\n\n}\n",
# "thought_5": "Now that I have a list of potential wines, I need to know more about the customer's taste preferences.",
# "action_5": {"name": "chatbox", "input": "What type of wine characteristics are you looking for? (e.g. t.e.g. tannin level, sweetness, intensity, acidity)"},
# "observation_5": "I like full-bodied Red wine with low tannin.",
# "thought_6": "Now that I have more information about the customer's preferences, it's time to make a recommendation.",
# "action_6": {"name": "recommendbox", "input": "El Enemigo Cabernet Franc 2019"},
# "observation_6": "I don't like the one you recommend. I want dry wine."
# }
# {
# "reflection": "I asked the user about the occasion, food type, and budget, and then searched for wine in the inventory right away. However, I should have asked the user for the specific wine type and their preferences in order to gather more information before making a recommendation."
# }
# Previous trial:
# $(JSON3.write(state[:thoughtHistory]))
# {"reflection"
# """
_prompt =
"""
You are a helpful sommelier working for a wine store.
@@ -475,7 +433,7 @@ function reflector(a::T1, state::T2)::String where {T1<:agent, T2<:AbstractDict}
"thought_5": "Now that I have a list of potential wines, I need to know more about the customer's taste preferences.",
"action_5": {"name": "chatbox", "input": "What type of wine characteristics are you looking for? (e.g. t.e.g. tannin level, sweetness, intensity, acidity)"},
"observation_5": "I like full-bodied Red wine with low tannin.",
"observation_5": "I like full-bodied red wine with low tannin.",
"thought_6": "Now that I have more information about the customer's preferences, it's time to make a recommendation.",
"action_6": {"name": "recommendbox", "input": "El Enemigo Cabernet Franc 2019"},
@@ -523,39 +481,33 @@ function reflector(a::T1, state::T2)::String where {T1<:agent, T2<:AbstractDict}
)
)
attempt = 0
while true
attempt += 1
if attempt <= 5
try
response = GeneralUtils.sendReceiveMqttMsg(outgoingMsg)
_responseJsonStr = response[:response][:text]
expectedJsonExample =
"""
Here is an expected JSON format:
{"reflection": "..."}
"""
responseJsonStr = jsoncorrection(a, _responseJsonStr, expectedJsonExample)
reflectionDict = copy(JSON3.read(responseJsonStr))
for attempt in 1:5
try
response = GeneralUtils.sendReceiveMqttMsg(outgoingMsg)
_responseJsonStr = response[:response][:text]
expectedJsonExample =
"""
Here is an expected JSON format:
{"reflection": "..."}
"""
responseJsonStr = jsoncorrection(a, _responseJsonStr, expectedJsonExample)
reflectionDict = copy(JSON3.read(responseJsonStr))
# check if dict has all required value
dummya::AbstractString = reflectionDict[:reflection]
# check if dict has all required value
dummya::AbstractString = reflectionDict[:reflection]
return reflectionDict[:reflection]
catch e
io = IOBuffer()
showerror(io, e)
errorMsg = String(take!(io))
st = sprint((io, v) -> show(io, "text/plain", v), stacktrace(catch_backtrace()))
println("")
@warn "Error occurred: $errorMsg\n$st"
println("")
end
else
error("reflector failed to generate a thought")
return reflectionDict[:reflection]
catch e
io = IOBuffer()
showerror(io, e)
errorMsg = String(take!(io))
st = sprint((io, v) -> show(io, "text/plain", v), stacktrace(catch_backtrace()))
println("")
@warn "Attempt $attempt. Error occurred: $errorMsg\n$st"
println("")
end
end
error("reflector failed to generate a thought")
end