update

2024-12-09 20:48:45 +07:00
parent 4f1280daa3
commit 9aef993813
47 changed files with 16623 additions and 12554 deletions
--- a/test/runtest.jl
+++ b/test/runtest.jl
@@ -1,227 +1,255 @@
-using Revise      # remove when this package is completed
-using YiemAgent, GeneralUtils, JSON3, MQTTClient, Dates, UUIDs, LibPQ, Base64, DataFrames
+using Revise
+using JSON, JSON3, MQTTClient, Dates, UUIDs, PrettyPrinting, LibPQ, Base64, DataFrames
+using YiemAgent, GeneralUtils
 using Base.Threads

 # ---------------------------------------------- 100 --------------------------------------------- #

-config = copy(JSON3.read("config.json"))

-# instanceInternalTopic = config[:serviceInternalTopic][:mqtttopic] * "/1" 

-# client, connection = MakeConnection(config[:mqttServerInfo][:broker], 
-#                                     config[:mqttServerInfo][:port])
-
-receiveUserMsgChannel = Channel{Dict}(4)
-# receiveInternalMsgChannel = Channel{Dict}(4)
-# println(typeof(connection))
-# msgMeta = GeneralUtils.generate_msgMeta(
-#   "N/A", 
-#   replyTopic = config[:servicetopic][:mqtttopic]  # ask frontend reply to this instance_chat_topic
-#   )  
+# load config
+config = copy(JSON3.read("../mountvolume/config.json"))

 function executeSQL(sql::T) where {T<:AbstractString}
-  DBconnection = LibPQ.Connection("host=192.168.88.12 port=5432 dbname=yiem_wine_assistant user=yiem password=yiem@Postgres_0.0")
+  DBconnection = LibPQ.Connection("host=192.168.88.12 port=10201 dbname=wineDB user=yiemtechnologies password=yiemtechnologies@Postgres_0.0")
  result = LibPQ.execute(DBconnection, sql)
  close(DBconnection)
  return result
 end

+function executeSQLVectorDB(sql)
+  DBconnection = LibPQ.Connection("host=192.168.88.12 port=10203 dbname=SQLVectorDB user=yiemtechnologies password=yiemtechnologies@Postgres_0.0")
+  result = LibPQ.execute(DBconnection, sql)
+  close(DBconnection)
+  return result
+end
+
+
 function text2textInstructLLM(prompt::String)
  msgMeta = GeneralUtils.generate_msgMeta(
    config[:externalservice][:text2textinstruct][:mqtttopic];
-    msgPurpose= "inference",
-    senderName= "yiemagent",
-    senderId= string(uuid4()),
-    receiverName= "text2textinstruct",
-    mqttBrokerAddress= config[:mqttServerInfo][:broker],
-    mqttBrokerPort= config[:mqttServerInfo][:port],
+    msgPurpose="inference",
+    senderName="yiemagent",
+    senderId=string(uuid4()),
+    receiverName="text2textinstruct",
+    mqttBrokerAddress=config[:mqttServerInfo][:broker],
+    mqttBrokerPort=config[:mqttServerInfo][:port],
  )

  outgoingMsg = Dict(
-    :msgMeta=> msgMeta,
-    :payload=> Dict(
-      :text=> prompt,
-      :kwargs=> Dict(
-        :max_tokens=> 2048,
-        :stop=> ["<|eot_id|>"],
-        :temperature=> 0.2,
-        )
+    :msgMeta => msgMeta,
+    :payload => Dict(
+      :text => prompt,
+      :kwargs => Dict(
+        :num_ctx => 16384,
+        :temperature => 0.2,
      )
    )
+  )

-  _response = GeneralUtils.sendReceiveMqttMsg(outgoingMsg; timeout=120)
+  _response = GeneralUtils.sendReceiveMqttMsg(outgoingMsg; timeout=6000)
  response = _response[:response][:text]

  return response
 end

-function executeSQLVectorDB(sql)
-  DBconnection = LibPQ.Connection("host=192.168.88.12 port=5433 dbname=SQLVectorDB user=yiemtechnologies@gmail.com password=yiem@Postgres_0.0")
-  result = LibPQ.execute(DBconnection, sql)
-  close(DBconnection)
-  return result
-end

-function addSQLVectorDB(state)
-  # get embedding of the query
-  query = [state[:thoughtHistory][:question]]
+# get text embedding from a LLM service
+function getEmbedding(text::T) where {T<:AbstractString}
  msgMeta = GeneralUtils.generate_msgMeta(
    config[:externalservice][:text2textinstruct][:mqtttopic];
-    msgPurpose= "embedding",
-    senderName= "yiemagent",
-    senderId= string(uuid4()),
-    receiverName= "text2textinstruct",
-    mqttBrokerAddress= config[:mqttServerInfo][:broker],
-    mqttBrokerPort= config[:mqttServerInfo][:port],
+    msgPurpose="embedding",
+    senderName="yiemagent",
+    senderId=string(uuid4()),
+    receiverName="text2textinstruct",
+    mqttBrokerAddress=config[:mqttServerInfo][:broker],
+    mqttBrokerPort=config[:mqttServerInfo][:port],
  )

  outgoingMsg = Dict(
-    :msgMeta=> msgMeta,
-    :payload=> Dict(
-      :text=> query
-      )
+    :msgMeta => msgMeta,
+    :payload => Dict(
+      :text => [text] # must be a vector of string
    )
+  )
  response = GeneralUtils.sendReceiveMqttMsg(outgoingMsg)
-  embedding = response[:response][:embeddings][1]
+  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 *, embedding <-> '$embedding' as distance
-    FROM sql_statement_repository
-    ORDER BY distance LIMIT 1;
-    """
-  response = executeSQLVectorDB(sql)
+  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)
+  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~~~ found similar sql. row id $rowid, distance $distance ", @__FILE__, " ", @__LINE__)
+    return (dict=output_str, distance=distance)
+  else
+    println("\n~~~ similar sql not found, max distance $maxdistance ", @__FILE__, " ", @__LINE__)
+    return (dict=nothing, distance=nothing)
+  end
+end
+
+
+function insertSQLVectorDB(query::T1, SQL::T2; maxdistance::Integer=1) where {T1<:AbstractString, T2<:AbstractString}
+  tablename = "sqlllm_decision_repository"
+  # get embedding of the query
+  # query = state[:thoughtHistory][:question]
+  df = findSimilarTextFromVectorDB(query, tablename, 
+                                  "function_input_embedding", executeSQLVectorDB)
  row, col = size(df)
  distance = row == 0 ? Inf : df[1, :distance]
-  if row == 0 || distance > 10 # no close enough SQL stored in the database
-    latestKey, _ = GeneralUtils.findHighestIndexKey(state[:thoughtHistory], :action_input)
-    _sqlStatement = state[:thoughtHistory][latestKey]
-    if occursin("SELECT", _sqlStatement)  # make sure it is an SQL statement before adding into DB
-      sqlStatementBase64 = base64encode(_sqlStatement)
-      sqlStatement = replace(_sqlStatement, "'"=>"")
-      sql =
-      """
-      INSERT INTO sql_statement_repository (question, sql_statement, sql_statement_base64, embedding) VALUES ('$query', '$sqlStatement', '$sqlStatementBase64', '$embedding');
-      """
-      _ = executeSQLVectorDB(sql)
-      println("--> added new SQL statement to vectorDB ", @__FILE__, " ", @__LINE__)
-      println(sqlStatement)
-    end
+  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__)
+    println(sql)
+    _ = executeSQLVectorDB(sql)
  end
 end

-function querySQLVectorDB(state)

-  # provide similarSQL at the first time thinking only
-  latestKey, _ = GeneralUtils.findHighestIndexKey(state[:thoughtHistory], :action_input)
-  if latestKey === nothing
-    # get embedding of the query
-    query = [state[:thoughtHistory][:question]]
-    msgMeta = GeneralUtils.generate_msgMeta(
-      config[:externalservice][:text2textinstruct][:mqtttopic];
-      msgPurpose= "embedding",
-      senderName= "yiemagent",
-      senderId= string(uuid4()),
-      receiverName= "text2textinstruct",
-      mqttBrokerAddress= config[:mqttServerInfo][:broker],
-      mqttBrokerPort= config[:mqttServerInfo][:port],
-    )
-
-    outgoingMsg = Dict(
-      :msgMeta=> msgMeta,
-      :payload=> Dict(
-        :text=> query
-        )
-      )
-    response = GeneralUtils.sendReceiveMqttMsg(outgoingMsg)
-    embedding = response[:response][:embeddings][1]
-
-    # check whether there is close enough vector already store in vectorDB. if no, add, else skip 
-    sql =
-    """
-    SELECT *, embedding <-> '$embedding' as distance
-    FROM sql_statement_repository
-    ORDER BY distance LIMIT 1;
-    """
-    response = executeSQLVectorDB(sql)
-    df = DataFrame(response)
-    row, col = size(df)
-    distance = row == 0 ? Inf : df[1, :distance]
-    if row != 0 && distance < 100
-      # if there is usable SQL, return it.
-      sqlStatementBase64 = df[1, :sql_statement_base64]
-      sqlStatement = String(base64decode(sqlStatementBase64))
-      println("--> getting SQL statement from vectorDB ", @__FILE__, " ", @__LINE__)
-      println(sqlStatement)
-      return sqlStatement
-    else
-      return nothing
-    end
+function similarSommelierDecision(recentevents::T1; maxdistance::Integer=5
+  )::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
-  return nothing
 end


-# Instantiate an agent
+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 = a.func[: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 = "12345"
+
+externalFunction = (
+    getEmbedding=getEmbedding,
+    text2textInstructLLM=text2textInstructLLM,
+    executeSQL=executeSQL,
+    similarSQLVectorDB=similarSQLVectorDB,
+    insertSQLVectorDB=insertSQLVectorDB,
+    similarSommelierDecision=similarSommelierDecision,
+    insertSommelierDecision=insertSommelierDecision,
+  )
+
+
+
 a = YiemAgent.sommelier(
-  text2textInstructLLM,
-  executeSQL,
-  querySQLVectorDB,
-  addSQLVectorDB;
-  name= "Jene",
-  id= "tempId",  # agent instance id
+  externalFunction;
+  name="Ton",
+  id=sessionId,  # agent instance id
+  retailername="Yiem",
 )

-function main()
-  for i in 1:10
-    userinput = ""
-    for i in 1:3
-      if userinput == ""
-        println("")
-        println("--> user input:")
-        userinput = readline()
-      else
-        break
-      end
-    end
-    response = YiemAgent.conversation(a, Dict(:text=> userinput))
-    println("")
-    println("--> assistant response: \n", response)
-  end
+while true
+  println("your respond: ")
+  user_answer = readline()
+  response = YiemAgent.conversation(a, Dict(:text=> user_answer))
+  println("\n$response")
 end

-main()

-"""
-  I'm joining a graduation party this evening. I want to get a bottle of white wine from the US to celebrate. I'm ok with any price range.
-  Well, the party is small casual with close friends and no food serving.
-  I'm open to suggestion since I have no specific idea.
-  I'm ok with any region.
-
-
-
-
-  The input is instructions on how you want the presentation to be conducted.
-"""
-
-
-wines = 
-"""
-Summary: This table contains two wine records, both from the United States, with white wine types, moderate sweetness (2), and high intensity (5). 
-More details: 1) wine_id: add9824f-81b0-47da-a08a-ee20498bc6c8, wine_name: Belle Cote Chardonnay, brand: Peter Michael, manufacturer: Peter Michael, region: Californian, country: United States, wine_type: white, grape_variety: Chardonnay, serving_temperature: 11 to 13 Celsius, intensity: 5, sweetness: 2, tannin: missing, acidity: 3, fizziness: missing, tasting_notes: oak, butter, vanilla, cream, oil, lemon curd, pear, peach, apple
-2) wine_id: ff9a494c-e916-44c4-9385-1c18b23aa825, wine_name: Ma Belle-Fille Chardonnay, brand: Peter Michael, manufacturer: Peter Michael, region: Californian, country: United States, wine_type: white, grape_variety: Chardonnay, serving_temperature: 11 to 13 Celsius, intensity: 5, sweetness: 2, tannin: missing, acidity: 3, fizziness: missing, tasting_notes: oak, butter, vanilla, cream, banana, cheese, apricot, peach, apple
-"""
-
-
-
-# response = YiemAgent.conversation(a, Dict(:text=> "newtopic",) )
-
-# response = YiemAgent.conversation(a, Dict(:text=> "Hello, I would like a get a bottle of wine."))
-# println("---> YiemAgent: ", response)
-
-# response = YiemAgent.conversation(a, Dict(:text=> "I'm having a graduation party this evening. I'll pay at most 30 bucks."))
+# response = YiemAgent.conversation(a, Dict(:text=> "I want to get a French red wine under 100."))
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+



@@ -229,60 +257,16 @@ More details: 1) wine_id: add9824f-81b0-47da-a08a-ee20498bc6c8, wine_name: Belle



-# # input = "query=\"off dry, medium tannin, French Rosé\""
-# input = "Search the database for wine type: white, country: France, sweetness level: 1"
-# YiemAgent.winestock(a, input)
-
-
-
-
-# input = "French dry white wines with medium body"
-# input = "query=\"medium-bodied dry white wine\""
-# # input = "the customer is looking for a medium-bodied, dry white wine."
-# result = YiemAgent.checkinventory(a, input)





-error("test done")




-function run_with_timeout(f, args...; timeout=5)
-  result = Ref{Any}()
-  task = Threads.@spawn try
-      result[] = f(args...)
-  catch e
-      println("Task interrupted: ", e)
-  end
-
-  Timer(timeout) do _
-      if !istaskdone(task)
-          schedule(task, InterruptException())
-          println("Task did not complete in time. Aborting.")
-      else
-          println("Task completed within the timeout.")
-      end
-  end
-
-  return result[]
-end
-
-# Example function that takes arguments and returns a value
-function example_function(x, y)
-  sleep(10)  # Simulate a long-running task
-  return x + y
-end
-
-# Example usage
-result = run_with_timeout(example_function, 3, 4; timeout=5)
-println("Result: ", result)


-a = `$"hello\nworld"`
-a = $"hello\nworld"

-a = """$("hello\nworld")"""