update

Reviewed-on: #2

Manifest.toml

@@ -1,6 +1,6 @@
 # This file is machine-generated - editing it directly is not advised
 
-julia_version = "1.11.3"
+julia_version = "1.11.4"
 manifest_format = "2.0"
 project_hash = "9e0d7dca51b949f2ffa5477b895b90988ec62529"
 
@@ -202,7 +202,7 @@ version = "1.11.0"
 deps = ["CSV", "DataFrames", "DataStructures", "Dates", "Distributions", "JSON3", "MQTTClient", "PrettyPrinting", "Random", "SHA", "UUIDs"]
 path = "../GeneralUtils"
 uuid = "c6c72f09-b708-4ac8-ac7c-2084d70108fe"
-version = "0.2.2"
+version = "0.2.3"
 
 [[deps.HTTP]]
 deps = ["Base64", "CodecZlib", "ConcurrentUtilities", "Dates", "ExceptionUnwrapping", "Logging", "LoggingExtras", "MbedTLS", "NetworkOptions", "OpenSSL", "PrecompileTools", "Random", "SimpleBufferStream", "Sockets", "URIs", "UUIDs"]
@@ -306,7 +306,7 @@ version = "1.19.3+0"
 deps = ["GeneralUtils", "JSON3", "PrettyPrinting"]
 path = "../LLMMCTS"
 uuid = "d76c5a4d-449e-4835-8cc4-dd86ec44f241"
-version = "0.1.3"
+version = "0.1.4"
 
 [[deps.LaTeXStrings]]
 git-tree-sha1 = "dda21b8cbd6a6c40d9d02a73230f9d70fed6918c"
@@ -471,7 +471,7 @@ version = "0.3.27+1"
 [[deps.OpenLibm_jll]]
 deps = ["Artifacts", "Libdl"]
 uuid = "05823500-19ac-5b8b-9628-191a04bc5112"
-version = "0.8.1+2"
+version = "0.8.1+4"
 
 [[deps.OpenSSL]]
 deps = ["BitFlags", "Dates", "MozillaCACerts_jll", "OpenSSL_jll", "Sockets"]

Project.toml

@@ -1,7 +1,7 @@
 name = "SQLLLM"
 uuid = "2ebc79c7-cc10-4a3a-9665-d2e1d61e63d3"
 authors = ["narawat lamaiin <narawat@outlook.com>"]
-version = "0.2.3"
+version = "0.2.4"
 
 [deps]
 CSV = "336ed68f-0bac-5ca0-87d4-7b16caf5d00b"

src/llmfunction.jl

@@ -1,10 +1,10 @@
 module llmfunction
 
 export listAllTable_json, listAllTable_str, tableinfo, getdata, finalAnswerBox,
-  getTableNameFromSQL, extractContent_dataframe, SQLexecution
+  getTableNameFromSQL, extractContent_dataframe, SQLexecution, compareState
 
 using HTTP, JSON3, URIs, Random, PrettyPrinting, UUIDs, LibPQ, Tables, DataFrames, CSV,
-  DataStructures, StatsBase
+  DataStructures, StatsBase, Dates
 using GeneralUtils, LLMMCTS
 using ..util
 
@@ -36,7 +36,7 @@ julia> result = response[:result]
 # Signature
 """
 function listAllTable_json(executeSQL::Function
-)::NamedTuple{(:result, :success),Tuple{DataFrame,Bool}}
+  )::NamedTuple{(:result, :success),Tuple{DataFrame,Bool}}
 
   sql = """
         SELECT 
@@ -347,8 +347,9 @@ end
 
 # Signature
 """
-function getdata_decisionMaker(state::Dict, context::Dict, text2textInstructLLM::Function
+function getdata_decisionMaker(state::Dict, context::Dict, text2textInstructLLM::Function,
-)::NamedTuple{(:thought, :code, :success, :errormsg),Tuple{Union{String,Nothing},Union{String,Nothing},Bool,Union{String,Nothing}}}
+  llmFormatName::String
+  )::NamedTuple{(:thought, :code, :success, :errormsg),Tuple{Union{String,Nothing},Union{String,Nothing},Bool,Union{String,Nothing}}}
 
   Hints = "None"
 
@@ -366,17 +367,14 @@ function getdata_decisionMaker(state::Dict, context::Dict, text2textInstructLLM:
   - Text information in the database is sometimes stored in lower case. If your search returns empty, try using lower case to search.
 
   You should then respond to the user with:
-  1) Comprehension: 
+  1) Plan: Step-by-step instructions of how to complete the task.
-      - State your comprehension about the current situation.
-  3) Plan: Step-by-step instructions of how to complete the task.
       - Focus on improving the code from the last round.
       - Do not create any table in the database.
-  4) Code:
+  2) Code:
       - Write new improved code.
       - Do not wrap the code and no comment as it will be executed directly without any modification against the database.
 
   You should only respond in format as described below and nothing more:
-  Comprehension: ...
   Plan: 
     1) ...
     2) ... 
@@ -406,12 +404,14 @@ function getdata_decisionMaker(state::Dict, context::Dict, text2textInstructLLM:
       ]
 
     # put in model format
-    prompt = GeneralUtils.formatLLMtext(_prompt; formatname="qwen")
+    prompt = GeneralUtils.formatLLMtext(_prompt, llmFormatName)
     try
-      response = text2textInstructLLM(prompt)
+      response = text2textInstructLLM(prompt, modelsize="medium")
+      response = GeneralUtils.deFormatLLMtext(response, llmFormatName)
+      think, response = GeneralUtils.extractthink(response)
       
-      header = ["Comprehension:", "Plan:", "Code:"]
+      header = ["Plan:", "Code:"]
-      dictkey = ["comprehension", "plan", "code"]
+      dictkey = ["plan", "code"]
 
       responsedict = GeneralUtils.textToDict(response, header; 
                                             dictKey=dictkey, symbolkey=true)
@@ -517,9 +517,9 @@ function SQLexecution(executeSQL::Function, sql::T
     tablesize = size(df)
     row, column = tablesize
     if row == 0
-      error("The resulting table has 0 row. Possible causes: 1) Your search criteria might be too specific. Relaxing some conditions could yield better results. Remember, you can always refine your search later. 2) There could be a typo in your search query. 3) You might be searching in the wrong place.")
+      error("\nThe resulting table has 0 row. Please try again.")
     elseif column > 30
-      error("SQL execution failed. An unexpected error occurred. Please try again.")
+      error("\nSQL execution failed. An unexpected error occurred. Please try again.")
     end
 
     df1 =
@@ -560,8 +560,9 @@ end
 
 # Signature
 """
-function extractContent_dataframe(df::DataFrame, text2textInstructLLM::Function, action::String
+function extractContent_dataframe(df::DataFrame, text2textInstructLLM::Function, action::String,
-)::String
+  llmFormatName::String
+  )::String
   tablesize = size(df)
   row = tablesize[1]
   column = tablesize[2]
@@ -627,22 +628,26 @@ function extractContent_dataframe(df::DataFrame, text2textInstructLLM::Function,
     ]
 
   # put in model format
-  prompt = GeneralUtils.formatLLMtext(_prompt; formatname="qwen")
+  prompt = GeneralUtils.formatLLMtext(_prompt, llmFormatName)
   header = ["About_resulting_table:", "Search_summary:"]
   dictkey = ["about_resulting_table", "search_summary"]
 
   for i in 1:5
-    response = text2textInstructLLM(prompt)
+    response = text2textInstructLLM(prompt, modelsize="medium")
+    response = GeneralUtils.deFormatLLMtext(response, llmFormatName)
+    think, response = GeneralUtils.extractthink(response)
 
-    kw = []
+    # check whether response has all header
-    # use for loop and detect_keyword function to get the exact variation of each keyword in the text then push to kw list
+    detected_kw = GeneralUtils.detectKeywordVariation(header, response)
-    for keyword in header
+    missingkeys = [k for (k, v) in detected_kw if v === nothing]
-      detected = GeneralUtils.detect_keyword(keyword, response)
+    if !isempty(missingkeys)
-      push!(kw, detected)
+      errornote = "$missingkeys are missing from your previous response"
-    end
+      println("\nERROR SQLLLM extractContent_dataframe() $errornote ", @__FILE__, ":", @__LINE__, " $(Dates.now())")
-    if nothing ∈ kw
+      continue
-      println("Some keywords are missing, Required keywords=$header, Response keywords=$kw ", @__FILE__, ":", @__LINE__, " $(Dates.now())")
+    elseif sum([length(i) for i in values(detected_kw)]) > length(header)
-      continue  # try again next loop
+      errornote = "\nYour previous attempt has duplicated points according to the required response format"
+      println("\nERROR SQLLLM extractContent_dataframe() $errornote ", @__FILE__, ":", @__LINE__, " $(Dates.now())")
+      continue
     end
 
     responsedict = GeneralUtils.textToDict(response, header; 
@@ -734,7 +739,9 @@ julia> result = SQLLLM.getTableNameFromSQL(sql, text2textInstructLLM)
 
 # Signature
 """
-function getTableNameFromSQL(sql::T, text2textInstructLLM::Function)::Vector{String} where {T<:AbstractString}
+function getTableNameFromSQL(sql::T, text2textInstructLLM::Function,
+  llmFormatName::String
+  )::Vector{String} where {T<:AbstractString}
   systemmsg = """
               Extract table name out of the user query.
 
@@ -762,13 +769,14 @@ function getTableNameFromSQL(sql::T, text2textInstructLLM::Function)::Vector{Str
     ]
 
   # put in model format
-  prompt = GeneralUtils.formatLLMtext(_prompt; formatname="qwen")
+  prompt = GeneralUtils.formatLLMtext(_prompt, llmFormatName)
   header = ["Table_name:"]
   dictkey = ["table_name"]
 
   for attempt in 1:5
     try
-      response = text2textInstructLLM(prompt)
+      response = text2textInstructLLM(prompt, modelsize="medium")
+      response = GeneralUtils.deFormatLLMtext(response, llmFormatName)
       responsedict = GeneralUtils.textToDict(response, header; 
                                             dictKey=dictkey, symbolkey=true)
       response = copy(JSON3.read(responsedict[:table_name]))
@@ -788,6 +796,174 @@ function getTableNameFromSQL(sql::T, text2textInstructLLM::Function)::Vector{Str
 end
 
 
+""" Compare multiple solution attempts and select the most accurate one.
+
+This function evaluates multiple solution attempts for a given question and determines which attempt 
+provides the most accurate and relevant response. It uses an LLM to analyze and compare the attempts,
+considering their actions and observations.
+
+# Arguments
+- `question::String`
+  The original question or task that was attempted to be solved
+- `highValueStateList::Vector{Dict}`
+  List of states containing different solution attempts and their results
+- `text2textInstructLLM::Function`
+  A function that handles communication to LLM service
+
+# Returns
+- `Integer`
+  The index of the selected best response (1-based indexing)
+
+# Example
+```jldoctest
+julia> 
+```
+
+# Notes
+- The function makes up to 10 attempts to get a valid response from the LLM
+- Each state in highValueStateList should contain a thoughtHistory with action_input and observation
+- The LLM evaluates attempts based on accuracy and relevance to the original question
+"""
+function compareState(question::String, highValueStateList::Vector{T},
+  text2textInstructLLM::Function, llmFormatName::String
+  )::Integer where {T<:AbstractDict}
+
+  systemmsg = 
+  """
+    Your profile:
+    - You are a helpful assistant
+    Situation:
+    - The user has made multiple attempts to solve the question, resulting in various answers
+    Your mission:
+    - Identify and select the most accurate and relevant response from these multiple results for the user
+    At each round of conversation, you will be given the following:
+      Question: the question the user is trying to answer
+      Attempt: the user's attempted actions and their corresponding results
+    You should then respond to the user with the following:
+      Comparison: detailed comparison of all results from all attempts from various aspects.
+      Rationale: a brief explanation of why the selected response is the most accurate and relevant
+      Selected_response_number: the number the selected response in the list of results (e.g., 1, 2, 3, ...)
+    You should only respond in format as described below:
+      Comparison: ...
+      Rationale: ...
+      Selected_response_number: ...
+    Here are some examples:
+      User's question: "How many German wines do you have?"
+      Attempt 1)
+      Action: SELECT COUNT(*) FROM wines WHERE country = 'Germany'
+      Result: 100 wines
+      Attempt 2)
+      Action: SELECT COUNT(*) FROM wines WHERE country = 'Germany' AND type = 'Red'
+      Result: 50 red wines
+      Comparison: The second attempt counts only German red wines while the first attempt includes all German wines.
+      Rationale: The user is asking for the number of German wines without specifying a type, so the most accurate response is the first attempt because it includes all German wines.
+      Selected_response_number:1
+
+    Let's begin!
+  """
+
+  potentialSolution = []
+  keys = [:action_input, :observation]
+  # extract the last action_name, action_input, observation of each state in highValueStateList and store them in a dictionary then push into potentialSolution
+  for state in highValueStateList
+    thoughtHistory = state[:thoughtHistory]
+    _, currentstate_latestIndice = 
+      GeneralUtils.findHighestIndexKey(thoughtHistory, keys[1])
+    latestKeys = makekey.(keys, currentstate_latestIndice)
+    d = Dict()
+    # get the last action_name, action_input, observation of currentstate
+    for (i,v) in enumerate(keys)
+      d[v] = thoughtHistory[latestKeys[i]]
+    end
+    push!(potentialSolution, d)
+  end
+
+  """
+  # put potential solutions from potentialSolution into the following form
+  Attempt 1)
+    action_name: 
+    action_input:
+    observation:
+  Attempt 2)
+    action_name:` 
+    action_input:
+    observation:`
+  ...
+  """
+  potentialSolutionStr = ""
+  for (i, state) in enumerate(potentialSolution)
+    potentialSolutionStr *= "Attempt $i)\n"
+    for k in keys
+      potentialSolutionStr *= "$k: $(state[k])\n"
+      println("")
+    end
+  end
+
+  errornote = "N/A"
+
+  for attempt in 1:10
+    errorFlag = false
+
+    usermsg =
+    """
+    Question: $question
+    Attempts: $potentialSolutionStr
+    P.S. $errornote
+    """
+
+    _prompt = 
+    [
+      Dict(:name=> "system", :text=> systemmsg),
+      Dict(:name=> "user", :text=> usermsg)
+    ]
+
+    # put in model format
+    prompt = GeneralUtils.formatLLMtext(_prompt, llmFormatName)
+
+    header = ["Comparison:", "Rationale:", "Selected_response_number:"]
+    dictkey = ["comparison", "rationale", "selected_response_number"]
+
+    response = text2textInstructLLM(prompt, modelsize="medium")
+
+    # sometime LLM output something like **Comprehension**: which is not expected
+    response = replace(response, "**"=>"")
+    response = replace(response, "***"=>"")
+    response = GeneralUtils.deFormatLLMtext(response, llmFormatName)
+    think, response = GeneralUtils.extractthink(response)
+
+    # check whether response has all header
+    detected_kw = GeneralUtils.detectKeywordVariation(header, response)
+    missingkeys = [k for (k, v) in detected_kw if v === nothing]
+    if !isempty(missingkeys)
+      errornote = "$missingkeys are missing from your previous response"
+      println("\nERROR SQLLLM extractContent_dataframe() $errornote ", @__FILE__, ":", @__LINE__, " $(Dates.now())")
+      continue
+    elseif sum([length(i) for i in values(detected_kw)]) > length(header)
+      errornote = "\nYour previous attempt has duplicated points according to the required response format"
+      println("\nERROR SQLLLM extractContent_dataframe() $errornote ", @__FILE__, ":", @__LINE__, " $(Dates.now())")
+      continue
+    end
+
+    responsedict = GeneralUtils.textToDict(response, header; dictKey=dictkey, symbolkey=true)
+
+    responsedict[:selected_response_number] = responsedict[:selected_response_number][1]  # some time "6\nThe trajectories are incomplete" is generated but I only need the number.
+    try
+      responsedict[:selected_response_number] = parse(Int, responsedict[:selected_response_number]) # convert string "5" into integer 5
+    catch
+      errornote = "In your previous attempt, Selected_response_number was not a number. It must be a number."
+      println("\nERROR SQLLLM compareState() Attempt $attempt. $errornote ", @__FILE__, ":", @__LINE__, " $(Dates.now())")
+      continue
+    end
+
+    println("\n~~~ compareState() ", @__FILE__, ":", @__LINE__, " $(Dates.now())")
+    pprintln(Dict(responsedict))
+
+    return responsedict[:selected_response_number]
+  end
+  error("compareState() failed to generate an evaluation, Response: \n$response\n<|End of error|>", @__FILE__, ":", @__LINE__, " $(Dates.now())")
+end
+
+
 
 
 
@@ -824,8 +1000,6 @@ end
 
 
 
-
-
 
 
 

src/util.jl

@@ -1,6 +1,8 @@
 module util
 
+export makekey
 
+makekey(key, indice) = Symbol("$(key)_$indice")
 
 
 

system_prompt_template.jl

@@ -0,0 +1,160 @@
+"""
+# -------------------------------- Default system message template ------------------------------- #
+
+<Your role>
+  - You are a helpful assistant
+</Your role>
+<Situation>
+  - Describe the current situation
+  Ex. The world use enormous energy from non-sustainable sources. This leads to climate change.
+</Situation>
+<Your vision>
+  - state your vision of how the situation will evolve, what would you want the situation to evolve into
+  Ex. To be the leading innovator in sustainable technology by 2030, transforming global energy systems.
+</Your vision>
+<Your mission>
+  - state the goal
+  Ex. Empowering communities through clean energy solutions to create a sustainable future.
+</Your mission>
+<Your mission's objective includes>
+  - Specific, measurable, and time-bound goals that directly support the mission.
+  Ex. Launch 50 solar-powered water purification systems in 3 regions by 2025.
+</Your mission's objective includes>
+<Your responsibility includes>
+  - state the mini goals that fall under your responsibility
+</Your responsibility includes>
+<Your responsibility does NOT includes>
+  - 
+</Your responsibility does NOT includes>
+<At each round of conversation, you will be given the following information>
+  -
+</At each round of conversation, you will be given the following information>
+<You must follow the following policy>
+  -
+</You must follow the following policy>
+<You should follow the following guidelines>
+  -
+</You should follow the following guidelines>
+<You should then respond to the user with interleaving Comprehension, Plan, Action_name, Action_input>
+  Comprehension: State your comprehension about the current situation.
+  Plan: Given the current circumstances, outline a detailed, step-by-step plan to accomplish the task. Be specific.
+  Action_name: (Typically corresponds to the execution of the first step in your plan) Can be one of the following function names:
+    - CHATBOX which you can use to talk with the user. The input is your intentions for the dialogue. Be specific.
+    - CHECKRESOURCES which you can use to check resources
+    - IMPLEMENT which you can use to implement the solution
+  Action_input: Detail the input for the action.
+</You should then respond to the user with interleaving Comprehension, Plan, Action_name, Action_input>
+<You should only respond in format as described below>
+  Comprehension: ...
+  Plan: ...
+  Action_name: ...
+  Action_input: ...
+</You should only respond in format as described below>
+<Here are some examples>
+
+</Here are some examples>
+
+Let's begin!
+
+
+
+
+
+
+
+
+
+# ------------------------------------------- Example: ------------------------------------------- #
+
+<Your profile>
+- You are a founder of a tech startup
+</Your profile>
+<Situation>
+- The global rise in bedridden patients, driven by an aging population, presents significant challenges for caregivers. Family members often become primary caretakers, leading to physical and emotional strain. This situation frequently forces caregivers to make difficult choices, including leaving their careers to provide full-time care, which impacts both family finances and personal well-being.
+</Situation>
+<Your vision>
+  - We want to develop a system that can help people with bedridden patients and their families so that they could go on with their lives.
+</Your vision>
+<Your mission>
+  - To create an innovative caregiving support platform that reduces the physical and emotional burden on family caregivers while ensuring quality care for bedridden patients
+</Your mission>
+<Your mission's objectives include>
+  - Develop smart monitoring systems for patient safety
+  - Create automated alert mechanisms for critical situations
+  - Design user-friendly interfaces for remote patient monitoring
+  - Implement AI-driven predictive care recommendations
+  - Build a support network connecting caregivers with healthcare professionals
+  - Establish training modules for family caregivers
+</Your mission's objectives include>
+<Your responsibilities include>
+  - Lead product vision and strategy development
+  - Oversee technical implementation and system architecture
+  - Coordinate with healthcare experts for medical validation
+  - Ensure compliance with healthcare regulations
+  - Manage stakeholder relationships
+  - Drive fundraising and business development
+</Your responsibilities include>
+<At each round of conversation, you will be given the following>
+  Challenges: user's specific caregiving challenges
+  Context: context and severity of the situation
+  Feedback: comments from family caregivers
+  Solutions: potential solution based on immediate and long-term impact
+</At each round of conversation, you will be given the following>
+<You must follow the following guidelines>
+  - Always prioritize patient safety and well-being
+  - Maintain empathy and understanding in all interactions
+  - Focus on practical, implementable solutions
+  - Consider both immediate needs and long-term sustainability
+  - Respect privacy and confidentiality of all stakeholders
+  - Follow healthcare regulations and best practices
+</You must follow the following guidelines>
+<You should then respond to the user with interleaving Comprehension, Plan, Action_name, Action_input>
+  Comprehension: State your comprehension about the current situation.
+  Plan: Given the current circumstances, outline a detailed, step-by-step plan to accomplish the task. Be specific.
+  Action_name: (Typically corresponds to the execution of the first step in your plan)
+    Can be one of the following function names:
+    - CHATBOX which you can use to talk with the user. The input is your intentions for the dialogue. Be specific.
+    - CHECKRESOURCES which you can use to check resources
+    - IMPLEMENT which you can use to implement the solution
+  Action_input: Detail the input for the action.
+</You should then respond to the user with interleaving Comprehension, Plan, Action_name, Action_input>
+<You should only respond in format as described below>
+  Comprehension: ...
+  Plan: ...
+  Action_name: ...
+  Action_input: ...
+</You should only respond in format as described below>
+<Here are some examples>
+  Example 1:
+  Challenges: "My mother needs constant monitoring at night, but I'm exhausted from lack of sleep."
+  Context: Elderly patient with dementia, requires 24/7 supervision
+  Feedback: "Need urgent solution for night monitoring"
+  Solutions: Smart monitoring system with motion sensors and alerts
+
+  Comprehension: The caregiver is experiencing severe sleep deprivation due to nighttime monitoring requirements
+  Plan: 
+    1. Assess current monitoring needs
+    2. Propose smart monitoring system installation
+    3. Set up emergency alert system
+    4. Train family on system usage
+  Action_name: CHATBOX
+  Action_input: Discuss specific nighttime behaviors and incidents to determine optimal sensor placement and alert thresholds
+
+  Example 2:
+  Challenges: "Managing medication schedules is becoming overwhelming"
+  Context: Patient on multiple medications with complex timing requirements
+  Feedback: "Need help with medication management"
+  Solutions: Automated medication reminder and tracking system
+
+  Comprehension: Caregiver struggling with complex medication management tasks
+  Plan:
+    1. Review current medication schedule
+    2. Implement automated reminder system
+    3. Set up medication tracking log
+    4. Connect with pharmacy for refill automation
+  Action_name: IMPLEMENT
+  Action_input: Deploy medication management module with smart alerts and compliance tracking
+</Here are some examples>
+
+Let's begin!
+"""

test/Manifest.toml

@@ -0,0 +1,41 @@
+# 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"

test/Project.toml

@@ -0,0 +1,2 @@
+[deps]
+Test = "8dfed614-e22c-5e08-85e1-65c5234f0b40"

test/runtests.jl

@@ -3,7 +3,7 @@ using LibPQ, Dates, JSON3, PrettyPrinting, UUIDs, DataFrames, DataStructures, Ba
 using GeneralUtils, SQLLLM
 
 
-config = copy(JSON3.read("/appfolder/mountvolume/appdata/config.json"))
+config = JSON3.read("/appfolder/app/dev/YiemAgent/test/config.json")
 
 function executeSQL(sql::T) where {T<:AbstractString}
   host = config[:externalservice][:wineDB][:host]
@@ -29,13 +29,19 @@ function executeSQLVectorDB(sql)
   return result
 end
 
-function text2textInstructLLM(prompt::String; maxattempt=3)
+function text2textInstructLLM(prompt::String; maxattempt::Integer=3, modelsize::String="medium",
+    senderId=GeneralUtils.uuid4snakecase(), timeout=180,
+    llmkwargs=Dict(
+      :num_ctx => 32768,
+      :temperature => 0.5,
+    )
+  )
   msgMeta = GeneralUtils.generate_msgMeta(
     config[:externalservice][:loadbalancer][:mqtttopic];
     msgPurpose="inference",
     senderName="yiemagent",
-    senderId=sessionId,
+    senderId=senderId,
-    receiverName="text2textinstruct_small",
+    receiverName="text2textinstruct_$modelsize",
     mqttBrokerAddress=config[:mqttServerInfo][:broker],
     mqttBrokerPort=config[:mqttServerInfo][:port],
   )
@@ -44,18 +50,16 @@ function text2textInstructLLM(prompt::String; maxattempt=3)
     :msgMeta => msgMeta,
     :payload => Dict(
       :text => prompt,
-      :kwargs => Dict(
+      :kwargs => llmkwargs
-        :num_ctx => 16384,
-        :temperature => 0.2,
-      )
     )
   )
 
   response = nothing
   for attempts in 1:maxattempt
-    _response = GeneralUtils.sendReceiveMqttMsg(outgoingMsg; timeout=180, maxattempt=2)
+    _response = GeneralUtils.sendReceiveMqttMsg(outgoingMsg; timeout=timeout, maxattempt=maxattempt)
+    payload = _response[:response]
+    if _response[:success] && payload[:text] !== nothing
       response = _response[:response][:text]
-    if response !== nothing
       break
     else
       println("\n<text2textInstructLLM()> attempt $attempts/$maxattempt failed ", @__FILE__, ":", @__LINE__, " $(Dates.now())")
@@ -75,7 +79,7 @@ function getEmbedding(text::T) where {T<:AbstractString}
     msgPurpose="embedding",
     senderName="yiemagent",
     senderId=sessionId,
-    receiverName="text2textinstruct_small",
+    receiverName="textembedding",
     mqttBrokerAddress=config[:mqttServerInfo][:broker],
     mqttBrokerPort=config[:mqttServerInfo][:port],
   )
@@ -86,7 +90,8 @@ function getEmbedding(text::T) where {T<:AbstractString}
       :text => [text] # must be a vector of string
     )
   )
-  response = GeneralUtils.sendReceiveMqttMsg(outgoingMsg; timeout=120)
+
+  response = GeneralUtils.sendReceiveMqttMsg(outgoingMsg; timeout=120, maxattempt=3)
   embedding = response[:response][:embeddings]
   return embedding
 end
@@ -107,12 +112,12 @@ function findSimilarTextFromVectorDB(text::T1, tablename::T2, embeddingColumnNam
   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
@@ -129,7 +134,6 @@ function similarSQLVectorDB(query; maxdistance::Integer=100)
   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
@@ -153,12 +157,77 @@ function insertSQLVectorDB(query::T1, SQL::T2; maxdistance::Integer=3) where {T1
   end
 end
 
-sessionId = "555"
+
+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(JSON3.read(_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 = JSON3.write(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 = GeneralUtils.uuid4snakecase()
+d = Dict(:id => sessionId)
+filepath = "/appfolder/app/sessionid.json"
+open(filepath, "w") do io
+  JSON3.pretty(io, d)
+end
+
+
+
+
+# query = "How many German wines do you have?"
+# highValueStateList = copy(JSON3.read("/appfolder/app/highValueState_1.json"))
+# selectedState = SQLLLM.compareState(query, highValueStateList, text2textInstructLLM)
+
 
 
 # query = Dict(:text=> "How many wines from France do you have that can be paired with lamb?")
-query = "How many French wines do you have?"
+# query = "How many French wines from Yiem store under 100 dollars do you have?"
 # query = "retailer: Yiem, wine_type: red, sweetness: 1-2, intensity: 4-5, wine price: 20-40"
+query = "from Yiem retailer, red wine from France. price 100 to 1000 USD. sweetness: 1-2, intensity: 4-5"
 # query = "wine_type: white, country: United States, sweetness: 1-2, tannin: 3, food to be served with wine: pizza"
 # query = "wine_type: white, country: Austria, food to be served with wine: pork"
 # query = "wine price: less than 25, wine_type: rose, country: France, sweetness: 2, tannin: 3, food to be served with wine: pizza"

test/test_2.jl

@@ -1,16 +1,70 @@
-using Revise
+# using Revise
+# using SQLLLM, LLMMCTS, DataStructures, JSON3
+
+# query = "How many German wines do you have?"
+# highValueStateList = copy(JSON3.read("/appfolder/app/highValueState_1.json"))
+# selectedState = SQLLLM.compareState(query, highValueStateList)
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
 
-function testf(a)::NamedTuple{(:a, :b), Tuple{Union{Nothing, Int}, Int}}
-  if a == 1
-    return (a=nothing, b=5)
-  else
-    return (a=5, b=5)
-  end
-end
-
-
-q = testf(1)
-w = testf(2)
 
 
 

testfile.csv

@@ -1,8 +0,0 @@
-table_name,comment
-customer,"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."
-wine,"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."
-wine_food,"The wine_food table represents the association between wines and food items. It establishes a many-to-many relationship, allowing us to link specific wines with various food items."
-food,"The food table represents various food items. It stores information related to food names, country of origin, taste attributes (spiciness, sweetness, sourness, savoriness, and bitterness), serving temperature, additional_search_term, other attributes (in JSON format) and a description."
-retailer,"The retailer table stores information about different retailers. It includes details related to retailer names, usernames, passwords, addresses, contact persons, telephone numbers, email addresses, additional_search_term, other attributes (in JSON format) and a description."
-retailer_wine,"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."
-retailer_food,"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."