update

Reviewed-on: #4

Manifest.toml

@@ -1,8 +1,8 @@
 # This file is machine-generated - editing it directly is not advised
 
-julia_version = "1.11.2"
+julia_version = "1.11.4"
 manifest_format = "2.0"
-project_hash = "b483014657ef9f0fde60d7258585b291d6f0eeca"
+project_hash = "cb7f3c57318e927e8ac4dc2dea9acdcace566ed1"
 
 [[deps.AliasTables]]
 deps = ["PtrArrays", "Random"]
@@ -120,9 +120,9 @@ version = "1.11.0"
 
 [[deps.Distributions]]
 deps = ["AliasTables", "FillArrays", "LinearAlgebra", "PDMats", "Printf", "QuadGK", "Random", "SpecialFunctions", "Statistics", "StatsAPI", "StatsBase", "StatsFuns"]
-git-tree-sha1 = "3101c32aab536e7a27b1763c0797dba151b899ad"
+git-tree-sha1 = "0b4190661e8a4e51a842070e7dd4fae440ddb7f4"
 uuid = "31c24e10-a181-5473-b8eb-7969acd0382f"
-version = "0.25.113"
+version = "0.25.118"
 
     [deps.Distributions.extensions]
     DistributionsChainRulesCoreExt = "ChainRulesCore"
@@ -158,9 +158,9 @@ version = "0.1.10"
 
 [[deps.FileIO]]
 deps = ["Pkg", "Requires", "UUIDs"]
-git-tree-sha1 = "2dd20384bf8c6d411b5c7370865b1e9b26cb2ea3"
+git-tree-sha1 = "b66970a70db13f45b7e57fbda1736e1cf72174ea"
 uuid = "5789e2e9-d7fb-5bc7-8068-2c6fae9b9549"
-version = "1.16.6"
+version = "1.17.0"
 weakdeps = ["HTTP"]
 
     [deps.FileIO.extensions]
@@ -168,9 +168,9 @@ weakdeps = ["HTTP"]
 
 [[deps.FilePathsBase]]
 deps = ["Compat", "Dates"]
-git-tree-sha1 = "7878ff7172a8e6beedd1dea14bd27c3c6340d361"
+git-tree-sha1 = "3bab2c5aa25e7840a4b065805c0cdfc01f3068d2"
 uuid = "48062228-2e41-5def-b9a4-89aafe57970f"
-version = "0.9.22"
+version = "0.9.24"
 weakdeps = ["Mmap", "Test"]
 
     [deps.FilePathsBase.extensions]
@@ -200,11 +200,9 @@ version = "1.11.0"
 
 [[deps.GeneralUtils]]
 deps = ["CSV", "DataFrames", "DataStructures", "Dates", "Distributions", "JSON3", "MQTTClient", "PrettyPrinting", "Random", "SHA", "UUIDs"]
-git-tree-sha1 = "978d9a5c3fc30205dd72d4a2a2ed4fa85ebee5cf"
-repo-rev = "main"
-repo-url = "https://git.yiem.cc/ton/GeneralUtils"
+path = "/appfolder/app/dev/GeneralUtils"
 uuid = "c6c72f09-b708-4ac8-ac7c-2084d70108fe"
-version = "0.1.0"
+version = "0.2.3"
 
 [[deps.HTTP]]
 deps = ["Base64", "CodecZlib", "ConcurrentUtilities", "Dates", "ExceptionUnwrapping", "Logging", "LoggingExtras", "MbedTLS", "NetworkOptions", "OpenSSL", "PrecompileTools", "Random", "SimpleBufferStream", "Sockets", "URIs", "UUIDs"]
@@ -214,9 +212,9 @@ version = "1.10.13"
 
 [[deps.HypergeometricFunctions]]
 deps = ["LinearAlgebra", "OpenLibm_jll", "SpecialFunctions"]
-git-tree-sha1 = "b1c2585431c382e3fe5805874bda6aea90a95de9"
+git-tree-sha1 = "68c173f4f449de5b438ee67ed0c9c748dc31a2ec"
 uuid = "34004b35-14d8-5ef3-9330-4cdb6864b03a"
-version = "0.3.25"
+version = "0.3.28"
 
 [[deps.ICU_jll]]
 deps = ["Artifacts", "JLLWrappers", "Libdl", "Pkg"]
@@ -260,9 +258,9 @@ uuid = "41ab1584-1d38-5bbf-9106-f11c6c58b48f"
 version = "1.3.0"
 
 [[deps.IrrationalConstants]]
-git-tree-sha1 = "630b497eafcc20001bba38a4651b327dcfc491d2"
+git-tree-sha1 = "e2222959fbc6c19554dc15174c81bf7bf3aa691c"
 uuid = "92d709cd-6900-40b7-9082-c6be49f344b6"
-version = "0.2.2"
+version = "0.2.4"
 
 [[deps.IterTools]]
 git-tree-sha1 = "42d5f897009e7ff2cf88db414a389e5ed1bdd023"
@@ -305,12 +303,10 @@ uuid = "b39eb1a6-c29a-53d7-8c32-632cd16f18da"
 version = "1.19.3+0"
 
 [[deps.LLMMCTS]]
-deps = ["GeneralUtils", "JSON3"]
-git-tree-sha1 = "d8c653b8fafbd3757b7332985efaf1fdb8b6fe97"
-repo-rev = "main"
-repo-url = "https://git.yiem.cc/ton/LLMMCTS"
+deps = ["GeneralUtils", "JSON3", "PrettyPrinting"]
+path = "/appfolder/app/dev/LLMMCTS"
 uuid = "d76c5a4d-449e-4835-8cc4-dd86ec44f241"
-version = "0.1.2"
+version = "0.1.4"
 
 [[deps.LaTeXStrings]]
 git-tree-sha1 = "dda21b8cbd6a6c40d9d02a73230f9d70fed6918c"
@@ -370,9 +366,9 @@ version = "1.11.0"
 
 [[deps.LogExpFunctions]]
 deps = ["DocStringExtensions", "IrrationalConstants", "LinearAlgebra"]
-git-tree-sha1 = "a2d09619db4e765091ee5c6ffe8872849de0feea"
+git-tree-sha1 = "13ca9e2586b89836fd20cccf56e57e2b9ae7f38f"
 uuid = "2ab3a3ac-af41-5b50-aa03-7779005ae688"
-version = "0.3.28"
+version = "0.3.29"
 
     [deps.LogExpFunctions.extensions]
     LogExpFunctionsChainRulesCoreExt = "ChainRulesCore"
@@ -475,7 +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"]
@@ -493,7 +489,7 @@ version = "3.0.15+1"
 deps = ["Artifacts", "CompilerSupportLibraries_jll", "JLLWrappers", "Libdl", "Pkg"]
 git-tree-sha1 = "13652491f6856acfd2db29360e1bbcd4565d04f1"
 uuid = "efe28fd5-8261-553b-a9e1-b2916fc3738e"
-version = "0.5.5+0"
+version = "0.5.5+2"
 
 [[deps.OrderedCollections]]
 git-tree-sha1 = "12f1439c4f986bb868acda6ea33ebc78e19b95ad"
@@ -502,9 +498,9 @@ version = "1.7.0"
 
 [[deps.PDMats]]
 deps = ["LinearAlgebra", "SparseArrays", "SuiteSparse"]
-git-tree-sha1 = "949347156c25054de2db3b166c52ac4728cbad65"
+git-tree-sha1 = "48566789a6d5f6492688279e22445002d171cf76"
 uuid = "90014a1f-27ba-587c-ab20-58faa44d9150"
-version = "0.11.31"
+version = "0.11.33"
 
 [[deps.Parsers]]
 deps = ["Dates", "PrecompileTools", "UUIDs"]
@@ -556,15 +552,15 @@ uuid = "de0858da-6303-5e67-8744-51eddeeeb8d7"
 version = "1.11.0"
 
 [[deps.PtrArrays]]
-git-tree-sha1 = "77a42d78b6a92df47ab37e177b2deac405e1c88f"
+git-tree-sha1 = "1d36ef11a9aaf1e8b74dacc6a731dd1de8fd493d"
 uuid = "43287f4e-b6f4-7ad1-bb20-aadabca52c3d"
-version = "1.2.1"
+version = "1.3.0"
 
 [[deps.QuadGK]]
 deps = ["DataStructures", "LinearAlgebra"]
-git-tree-sha1 = "cda3b045cf9ef07a08ad46731f5a3165e56cf3da"
+git-tree-sha1 = "9da16da70037ba9d701192e27befedefb91ec284"
 uuid = "1fd47b50-473d-5c70-9696-f719f8f3bcdc"
-version = "2.11.1"
+version = "2.11.2"
 
     [deps.QuadGK.extensions]
     QuadGKEnzymeExt = "Enzyme"
@@ -623,11 +619,9 @@ version = "0.7.0"
 
 [[deps.SQLLLM]]
 deps = ["CSV", "DataFrames", "DataStructures", "Dates", "FileIO", "GeneralUtils", "HTTP", "JSON3", "LLMMCTS", "LibPQ", "PrettyPrinting", "Random", "Revise", "StatsBase", "Tables", "URIs", "UUIDs"]
-git-tree-sha1 = "45e660e44de0950a5e5f92d467298d8b768b6023"
-repo-rev = "main"
-repo-url = "https://git.yiem.cc/ton/SQLLLM"
+path = "/appfolder/app/dev/SQLLLM"
 uuid = "2ebc79c7-cc10-4a3a-9665-d2e1d61e63d3"
-version = "0.2.0"
+version = "0.2.4"
 
 [[deps.SQLStrings]]
 git-tree-sha1 = "55de0530689832b1d3d43491ee6b67bd54d3323c"
@@ -672,9 +666,9 @@ version = "1.11.0"
 
 [[deps.SpecialFunctions]]
 deps = ["IrrationalConstants", "LogExpFunctions", "OpenLibm_jll", "OpenSpecFun_jll"]
-git-tree-sha1 = "2f5d4697f21388cbe1ff299430dd169ef97d7e14"
+git-tree-sha1 = "64cca0c26b4f31ba18f13f6c12af7c85f478cfde"
 uuid = "276daf66-3868-5448-9aa4-cd146d93841b"
-version = "2.4.0"
+version = "2.5.0"
 
     [deps.SpecialFunctions.extensions]
     SpecialFunctionsChainRulesCoreExt = "ChainRulesCore"
@@ -699,16 +693,16 @@ uuid = "82ae8749-77ed-4fe6-ae5f-f523153014b0"
 version = "1.7.0"
 
 [[deps.StatsBase]]
-deps = ["DataAPI", "DataStructures", "LinearAlgebra", "LogExpFunctions", "Missings", "Printf", "Random", "SortingAlgorithms", "SparseArrays", "Statistics", "StatsAPI"]
-git-tree-sha1 = "5cf7606d6cef84b543b483848d4ae08ad9832b21"
+deps = ["AliasTables", "DataAPI", "DataStructures", "LinearAlgebra", "LogExpFunctions", "Missings", "Printf", "Random", "SortingAlgorithms", "SparseArrays", "Statistics", "StatsAPI"]
+git-tree-sha1 = "29321314c920c26684834965ec2ce0dacc9cf8e5"
 uuid = "2913bbd2-ae8a-5f71-8c99-4fb6c76f3a91"
-version = "0.34.3"
+version = "0.34.4"
 
 [[deps.StatsFuns]]
 deps = ["HypergeometricFunctions", "IrrationalConstants", "LogExpFunctions", "Reexport", "Rmath", "SpecialFunctions"]
-git-tree-sha1 = "b423576adc27097764a90e163157bcfc9acf0f46"
+git-tree-sha1 = "35b09e80be285516e52c9054792c884b9216ae3c"
 uuid = "4c63d2b9-4356-54db-8cca-17b64c39e42c"
-version = "1.3.2"
+version = "1.4.0"
 
     [deps.StatsFuns.extensions]
     StatsFunsChainRulesCoreExt = "ChainRulesCore"

Project.toml

@@ -1,9 +1,10 @@
 name = "YiemAgent"
 uuid = "e012c34b-7f78-48e0-971c-7abb83b6f0a2"
 authors = ["narawat lamaiin <narawat@outlook.com>"]
-version = "0.1.1"
+version = "0.3.0"
 
 [deps]
+CSV = "336ed68f-0bac-5ca0-87d4-7b16caf5d00b"
 DataFrames = "a93c6f00-e57d-5684-b7b6-d8193f3e46c0"
 DataStructures = "864edb3b-99cc-5e75-8d2d-829cb0a9cfe8"
 Dates = "ade2ca70-3891-5945-98fb-dc099432e06a"
@@ -21,7 +22,5 @@ URIs = "5c2747f8-b7ea-4ff2-ba2e-563bfd36b1d4"
 UUIDs = "cf7118a7-6976-5b1a-9a39-7adc72f591a4"
 
 [compat]
+CSV = "0.10.15"
 DataFrames = "1.7.0"
-GeneralUtils = "0.1.0"
-LLMMCTS = "0.1.2"
-SQLLLM = "0.2.0"

fast_inference_guideline.txt

@@ -0,0 +1,72 @@
+To make **LLM-driven inference** fast while maintaining its dynamic capabilities, there are a few practices or approaches to avoid, as they could lead to performance bottlenecks or inefficiencies. Here's what *not* to do:
+
+---
+
+### **1. Avoid Using Overly Large Models for Every Query**
+While larger LLMs like GPT-4 provide high accuracy and nuanced responses, they may slow down real-time processing due to their computational complexity. Instead:
+- Use distilled or smaller models (e.g., GPT-3.5 Turbo or fine-tuned versions) for faster inference without compromising much on quality.
+
+---
+
+### **2. Avoid Excessive Entity Preprocessing**
+Don’t rely on overly complicated preprocessing steps (like advanced NER models or regex-heavy pipelines) to extract entities from the query before invoking the LLM. This could add latency. Instead:
+- Design efficient prompts that allow the LLM to extract entities and generate responses simultaneously.
+
+---
+
+### **3. Avoid Asking the LLM Multiple Separate Questions**
+Running the LLM for multiple subtasks—for example, entity extraction first and response generation second—can significantly slow down the pipeline. Instead:
+- Create prompts that combine tasks into one pass, e.g., *"Identify the city name and generate a weather response for this query: 'What's the weather in London?'"*.
+
+---
+
+### **4. Don’t Overload the LLM with Context History**
+Excessively lengthy conversation history or irrelevant context in your prompts can slow down inference times. Instead:
+- Provide only the relevant context for each query, trimming unnecessary parts of the conversation.
+
+---
+
+### **5. Avoid Real-Time Dependence on External APIs**
+Using external APIs to fetch supplementary data (e.g., weather details or location info) during every query can introduce latency. Instead:
+- Pre-fetch API data asynchronously and use the LLM to integrate it dynamically into responses.
+
+---
+
+### **6. Avoid Running LLM on Underpowered Hardware**
+Running inference on CPUs or low-spec GPUs will result in slower response times. Instead:
+- Deploy the LLM on optimized infrastructure (e.g., high-performance GPUs like NVIDIA A100 or cloud platforms like Azure AI) to reduce latency.
+
+---
+
+### **7. Skip Lengthy Generative Prompts**
+Avoid prompts that encourage the LLM to produce overly detailed or verbose responses, as these take longer to process. Instead:
+- Use concise prompts that focus on generating actionable or succinct answers.
+
+---
+
+### **8. Don’t Ignore Optimization Techniques**
+Failing to optimize your LLM setup can drastically impact performance. For example:
+- Avoid skipping techniques like model quantization (reducing numerical precision to speed up inference) or distillation (training smaller models).
+
+---
+
+### **9. Don’t Neglect Response Caching**
+While you may not want a full caching system to avoid sunk costs, dismissing lightweight caching entirely can impact speed. Instead:
+- Use temporary session-based caching for very frequent queries, without committing to a full-fledged cache infrastructure.
+
+---
+
+### **10. Avoid One-Size-Fits-All Solutions**
+Applying the same LLM inference method to all queries—whether simple or complex—will waste processing resources. Instead:
+- Route basic queries to faster, specialized models and use the LLM for nuanced or multi-step queries only.
+
+---
+
+### Summary: Focus on Efficient Design
+By avoiding these pitfalls, you can ensure that LLM-driven inference remains fast and responsive:
+- Optimize prompts.
+- Use smaller models for simpler queries.
+- Run the LLM on high-performance hardware.
+- Trim unnecessary preprocessing or contextual steps.
+
+Would you like me to help refine a prompt or suggest specific tools to complement your implementation? Let me know!

src/type.jl

@@ -1,6 +1,6 @@
 module type
   
-export agent, sommelier, companion
+export agent, sommelier, companion, virtualcustomer
 
 using Dates, UUIDs, DataStructures, JSON3
 using GeneralUtils
@@ -9,11 +9,44 @@ using GeneralUtils
 
 abstract type agent end
 
-
 mutable struct companion <: agent
   name::String  # agent name
   id::String    # agent id
+  systemmsg::String # system message
+  tools::Dict  # tools
   maxHistoryMsg::Integer  # e.g. 21th and earlier messages will get summarized
+  chathistory::Vector{Dict{Symbol, Any}}
+  memory::Dict{Symbol, Any}
+  func::NamedTuple  # NamedTuple of functions 
+  llmFormatName::String
+end
+
+function companion(
+  func::NamedTuple  # NamedTuple of functions
+  ;
+  name::String= "Assistant",
+  id::String= GeneralUtils.uuid4snakecase(), 
+  maxHistoryMsg::Integer= 20,
+  chathistory::Vector{Dict{Symbol, String}} = Vector{Dict{Symbol, String}}(),
+  llmFormatName::String= "granite3",
+  systemmsg::String=
+    """
+      Your name: $name
+      Your sex: Female
+      Your role: You are a helpful assistant.
+      You should follow the following guidelines:
+      - Focus on the latest conversation.
+      - Your like to be short and concise.
+
+      Let's begin!
+      """,
+  )
+
+  tools = Dict( # update input format
+      "CHATBOX"=> Dict(
+        :description => "- CHATBOX which you can use to talk with the user. The input is your intentions for the dialogue. Be specific.",
+      ),
+    )
 
   """ Memory
     Ref: Chat prompt format https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGML/discussions/3
@@ -22,38 +55,23 @@ mutable struct companion <: agent
       Dict(:name=>"user", :text=> "Wassup!", :timestamp=> Dates.now()),
       Dict(:name=>"assistant", :text=> "Hi I'm your assistant.", :timestamp=> Dates.now()),
     ]
-
   """
-  chathistory::Vector{Dict{Symbol, Any}}
-  memory::Dict{Symbol, Any}
-
-  # communication function
-  text2textInstructLLM::Function
-end
-
-function companion(
-  text2textInstructLLM::Function
-  ;
-  name::String= "Assistant",
-  id::String= string(uuid4()),
-  maxHistoryMsg::Integer= 20,
-  chathistory::Vector{Dict{Symbol, String}} = Vector{Dict{Symbol, String}}(),
-  )
-
   memory = Dict{Symbol, Any}(
-              :chatbox=> "",
-              :shortmem=> OrderedDict{Symbol, Any}(),
             :events=> Vector{Dict{Symbol, Any}}(),
-              :state=> Dict{Symbol, Any}(),
+            :state=> Dict{Symbol, Any}(), # state of the agent
+            :recap=> OrderedDict{Symbol, Any}(),  # recap summary of the conversation
           )
 
   newAgent = companion(
     name,
     id,
+    systemmsg,
+    tools,
     maxHistoryMsg,
     chathistory,
     memory,
-    text2textInstructLLM
+    func,
+    llmFormatName
     )
   
   return newAgent
@@ -61,6 +79,7 @@ end
 
 
 
+
 """ A sommelier agent.
 
 # Arguments
@@ -134,20 +153,10 @@ mutable struct sommelier <: agent
   retailername::String
   tools::Dict   
   maxHistoryMsg::Integer  # e.g. 21th and earlier messages will get summarized
-
-  """ Memory
-    Ref: Chat prompt format https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGML/discussions/3
-    NO "system" message in chathistory because I want to add it at the inference time
-    chathistory= [
-      Dict(:name=>"user", :text=> "Wassup!", :timestamp=> Dates.now()),
-      Dict(:name=>"assistant", :text=> "Hi I'm your assistant.", :timestamp=> Dates.now()),
-    ]
-
-  """
   chathistory::Vector{Dict{Symbol, Any}}
   memory::Dict{Symbol, Any}
-
   func  # NamedTuple of functions 
+  llmFormatName::String
 end
 
 function sommelier(
@@ -158,6 +167,7 @@ function sommelier(
   retailername::String= "retailer_name",
   maxHistoryMsg::Integer= 20,
   chathistory::Vector{Dict{Symbol, String}} = Vector{Dict{Symbol, String}}(),
+  llmFormatName::String= "granite3"
   )
 
   tools = Dict( # update input format
@@ -171,21 +181,26 @@ function sommelier(
         :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.""",
       ),
-      # "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,
-      # ),
     )
 
+  """ Memory
+    Ref: Chat prompt format https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGML/discussions/3
+    NO "system" message in chathistory because I want to add it at the inference time
+    chathistory= [
+      Dict(:name=>"user", :text=> "Wassup!", :timestamp=> Dates.now()),
+      Dict(:name=>"assistant", :text=> "Hi I'm your assistant.", :timestamp=> Dates.now()),
+    ]
+  """
   memory = Dict{Symbol, Any}(
-              :chatbox=> "",
-              :shortmem=> OrderedDict{Symbol, Any}(),
+            :shortmem=> OrderedDict{Symbol, Any}(
+              :db_search_result=> Any[],
+              :scratchpad=> "", #[PENDING] should be a dict e.g. Dict(:database_search_result=>Dict(:wines=> "", :search_query=> ""))
+            ),
             :events=> Vector{Dict{Symbol, Any}}(),
             :state=> Dict{Symbol, Any}(
-                :wine_presented_to_user=> "None",
             ),
+            :recap=> OrderedDict{Symbol, Any}(),
+            
           )
 
   newAgent = sommelier(
@@ -196,7 +211,82 @@ function sommelier(
     maxHistoryMsg,
     chathistory,
     memory,
-    func
+    func,
+    llmFormatName
+    )
+  
+  return newAgent
+end
+
+
+mutable struct virtualcustomer <: agent
+  name::String  # agent name
+  id::String    # agent id
+  systemmsg::String # system message
+  tools::Dict   
+  maxHistoryMsg::Integer  # e.g. 21th and earlier messages will get summarized
+  chathistory::Vector{Dict{Symbol, Any}}
+  memory::Dict{Symbol, Any}
+  func  # NamedTuple of functions 
+  llmFormatName::String
+end
+
+function virtualcustomer(
+  func,  # NamedTuple of functions
+  ;
+  name::String= "Assistant",
+  id::String= string(uuid4()),
+  maxHistoryMsg::Integer= 20,
+  chathistory::Vector{Dict{Symbol, String}} = Vector{Dict{Symbol, String}}(),
+  llmFormatName::String= "granite3",
+  systemmsg::String=
+    """
+      Your name: $name
+      Your sex: Female
+      Your role: You are a helpful assistant.
+      You should follow the following guidelines:
+      - Focus on the latest conversation.
+      - Your like to be short and concise.
+
+      Let's begin!
+      """,
+  )
+
+  tools = Dict( # update input format
+      "chatbox"=> 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 => "" ,
+      ),
+    )
+
+  """ Memory
+    Ref: Chat prompt format https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGML/discussions/3
+    NO "system" message in chathistory because I want to add it at the inference time
+    chathistory= [
+      Dict(:name=>"user", :text=> "Wassup!", :timestamp=> Dates.now()),
+      Dict(:name=>"assistant", :text=> "Hi I'm your assistant.", :timestamp=> Dates.now()),
+    ]
+  """
+  memory = Dict{Symbol, Any}(
+            :shortmem=> OrderedDict{Symbol, Any}(
+            ),
+            :events=> Vector{Dict{Symbol, Any}}(),
+            :state=> Dict{Symbol, Any}(
+            ),
+            :recap=> OrderedDict{Symbol, Any}(),
+          )
+
+  newAgent = virtualcustomer(
+    name,
+    id,
+    systemmsg,
+    tools,
+    maxHistoryMsg,
+    chathistory,
+    memory,
+    func,
+    llmFormatName
     )
   
   return newAgent

src/util.jl

@@ -1,6 +1,7 @@
 module util
 
-export clearhistory, addNewMessage, vectorOfDictToText, eventdict, noises
+export clearhistory, addNewMessage, chatHistoryToText, eventdict, noises, createTimeline,
+        availableWineToText, createEventsLog, createChatLog
 
 using UUIDs, Dates, DataStructures, HTTP, JSON3
 using GeneralUtils
@@ -106,7 +107,7 @@ function addNewMessage(a::T1, name::String, text::T2;
     error("name is not in agent.availableRole $(@__LINE__)")
   end
 
-  #[] summarize the oldest 10 message
+  #[PENDING] summarize the oldest 10 message
   if length(a.chathistory) > maximumMsg
     summarize(a.chathistory)
   else
@@ -121,33 +122,39 @@ This function takes in a vector of dictionaries and outputs a single string wher
 
 # Arguments
   - `vecd::Vector`
-    a vector of dictionaries
+    A vector of dictionaries containing chat messages
   - `withkey::Bool` 
-    whether to include the key in the output text. Default is true
+    Whether to include the name as a prefix in the output text. Default is true
+  - `range::Union{Nothing,UnitRange,Int}` 
+    Optional range of messages to include. If nothing, includes all messages
 
-# Return
-  a string with the formatted dictionaries
+# Returns
+  A formatted string where each line contains either:
+  - If withkey=true: "name> message\n"
+  - If withkey=false: "message\n"
 
 # Example
-```jldoctest
+
 julia> using Revise
 julia> using GeneralUtils
 julia> vecd = [Dict(:name => "John", :text => "Hello"), Dict(:name => "Jane", :text => "Goodbye")]
 julia> GeneralUtils.vectorOfDictToText(vecd, withkey=true)
 "John> Hello\nJane> Goodbye\n"
 ```
-# Signature
 """
-function vectorOfDictToText(vecd::Vector; withkey=true)::String
+function chatHistoryToText(vecd::Vector; withkey=true, range=nothing)::String
   # Initialize an empty string to hold the final text
   text = ""
   
+  # Get the elements within the specified range, or all elements if no range provided
+  elements = isnothing(range) ? vecd : vecd[range]
+  
   # Determine whether to include the key in the output text or not
   if withkey
     # Loop through each dictionary in the input vector
-      for d in vecd
+    for d in elements
         # Extract the 'name' and 'text' keys from the dictionary
-          name = d[:name]
+        name = titlecase(d[:name])
         _text = d[:text]
         
         # Append the formatted string to the text variable
@@ -155,7 +162,7 @@ function vectorOfDictToText(vecd::Vector; withkey=true)::String
       end
   else
     # Loop through each dictionary in the input vector
-      for d in vecd
+    for d in elements
         # Iterate over all key-value pairs in the dictionary
         for (k, v) in d
             # Append the formatted string to the text variable
@@ -169,249 +176,238 @@ function vectorOfDictToText(vecd::Vector; withkey=true)::String
 end
 
 
+function availableWineToText(vecd::Vector)::String
+  # Initialize an empty string to hold the final text
+  rowtext = ""
+  # Loop through each dictionary in the input vector
+  for (i, d) in enumerate(vecd)
+    # Iterate over all key-value pairs in the dictionary
+    temp = []
+    for (k, v) in d
+      # Append the formatted string to the text variable
+      t = "$k:$v"
+      push!(temp, t)
+    end
+    _rowtext = join(temp, ',')
+    rowtext *= "$i) $_rowtext "
+  end
+  
+  return rowtext
+end
+
+
+
+""" Create a dictionary representing an event with optional details.
+
+# Arguments
+  - `event_description::Union{String, Nothing}`
+    A description of the event
+  - `timestamp::Union{DateTime, Nothing}`
+    The time when the event occurred
+  - `subject::Union{String, Nothing}`
+    The subject or entity associated with the event
+  - `thought::Union{AbstractDict, Nothing}`
+    Any associated thoughts or metadata
+  - `actionname::Union{String, Nothing}`
+    The name of the action performed (e.g., "CHAT", "CHECKINVENTORY")
+  - `actioninput::Union{String, Nothing}`
+    Input or parameters for the action
+  - `location::Union{String, Nothing}`
+    Where the event took place
+  - `equipment_used::Union{String, Nothing}`
+    Equipment involved in the event
+  - `material_used::Union{String, Nothing}`
+    Materials used during the event
+  - `outcome::Union{String, Nothing}`
+    The result or consequence of the event after action execution
+  - `note::Union{String, Nothing}`
+    Additional notes or comments
+
+# Returns
+  A dictionary with event details as symbol-keyed key-value pairs
+"""
 function eventdict(;
   event_description::Union{String, Nothing}=nothing,
   timestamp::Union{DateTime, Nothing}=nothing,
   subject::Union{String, Nothing}=nothing,
-  action_or_dialogue::Union{String, Nothing}=nothing,
+  thought::Union{AbstractDict, Nothing}=nothing,
+  actionname::Union{String, Nothing}=nothing, # "CHAT", "CHECKINVENTORY", "PRESENTBOX", etc
+  actioninput::Union{String, Nothing}=nothing,
   location::Union{String, Nothing}=nothing,
   equipment_used::Union{String, Nothing}=nothing,
   material_used::Union{String, Nothing}=nothing,
   outcome::Union{String, Nothing}=nothing,
   note::Union{String, Nothing}=nothing,
   )
-  return Dict{Symbol, Any}(
+
+  d = Dict{Symbol, Any}(
     :event_description=> event_description,
     :timestamp=> timestamp,
     :subject=> subject,
-      :action_or_dialogue=> action_or_dialogue,
+    :thought=> thought,
+    :actionname=> actionname,
+    :actioninput=> actioninput,
     :location=> location,
     :equipment_used=> equipment_used,
     :material_used=> material_used,
     :outcome=> outcome,
     :note=> note,
   )
+
+  return d
 end
 
 
+""" Create a formatted timeline string from a sequence of events.
 
-# """ Convert a single chat dictionary into LLM model instruct format.
+# Arguments
+  - `events::T1`
+    Vector of event dictionaries containing subject, actioninput and optional outcome fields
+    Each event dictionary should have the following keys:
+    - :subject - The subject or entity performing the action
+    - :actioninput - The action or input performed by the subject
+    - :outcome - (Optional) The result or outcome of the action
 
-# # Llama 3 instruct format example
-#   <|system|>
-#   You are a helpful AI assistant.<|end|>
-#   <|user|>
-#   I am going to Paris, what should I see?<|end|>
-#   <|assistant|>
-#   Paris, the capital of France, is known for its stunning architecture, art museums."<|end|>
-#   <|user|>
-#   What is so great about #1?<|end|>
-#   <|assistant|>
+# Returns
+  - `timeline::String`
+    A formatted string representing the events with their subjects, actions, and optional outcomes
+    Format: "{index}) {subject}> {actioninput} {outcome}\n" for each event
 
+# Example
 
-# # Arguments
-#   - `name::T`
-#     message owner name e.f. "system", "user" or "assistant"
-#   - `text::T`
+events = [
+  Dict(:subject => "User", :actioninput => "Hello", :outcome => nothing),
+  Dict(:subject => "Assistant", :actioninput => "Hi there!", :outcome => "with a smile")
+]
+timeline = createTimeline(events)
+# 1) User> Hello
+# 2) Assistant> Hi there! with a smile
 
-# # Return
-#   - `formattedtext::String`
-#     text formatted to model format
+"""
+function createTimeline(events::T1; eventindex::Union{UnitRange, Nothing}=nothing
+  ) where {T1<:AbstractVector}
+  # Initialize empty timeline string
+  timeline = ""
   
-# # Example
-# ```jldoctest
-# julia> using Revise
-# julia> using YiemAgent
-# julia> d = Dict(:name=> "system",:text=> "You are a helpful, respectful and honest assistant.",)
-# julia> formattedtext = YiemAgent.formatLLMtext_phi3instruct(d[:name], d[:text])
+  # Determine which indices to use - either provided range or full length
+  ind = 
+    if eventindex !== nothing
+      [eventindex...]
+    else
+      1:length(events)
+    end
 
-# ```
+  #[WORKING] Iterate through events and format each one
+  for i in ind
+    event = events[i]
+    # If no outcome exists, format without outcome
+    # if event[:actionname] == "CHATBOX"
+    #   timeline *= "Event_$i $(event[:subject])> action_name: $(event[:actionname]), action_input: $(event[:actioninput])\n"
+    # elseif event[:actionname] == "CHECKINVENTORY" && event[:outcome] === nothing
+    #   timeline *= "Event_$i $(event[:subject])> action_name: $(event[:actionname]), action_input: $(event[:actioninput]), observation: Not done yet.\n"
+    # If outcome exists, include it in formatting  
+    if event[:actionname] == "CHECKWINE"
+      timeline *= "Event_$i $(event[:subject])> action_name: $(event[:actionname]), action_input: $(event[:actioninput]), observation: $(event[:outcome])\n"
+    else
+      timeline *= "Event_$i $(event[:subject])> action_name: $(event[:actionname]), action_input: $(event[:actioninput])\n"
+    end
+  end
 
-# Signature
-# """
-# function formatLLMtext_phi3instruct(name::T, text::T) where {T<:AbstractString}
-#   formattedtext = 
-#   """
-#   <|$name|>
-#   $text<|end|>\n
-#   """
+  # Return formatted timeline string
+  return timeline
+end
+# function createTimeline(events::T1; eventindex::Union{UnitRange, Nothing}=nothing
+#   ) where {T1<:AbstractVector}
+#   # Initialize empty timeline string
+#   timeline = ""
   
-#   return formattedtext
-# end
-
-
-# """ Convert a single chat dictionary into LLM model instruct format.
-
-# # Llama 3 instruct format example
-#   <|begin_of_text|>
-#   <|start_header_id|>system<|end_header_id|>
-#   You are a helpful assistant.
-#   <|eot_id|>
-#   <|start_header_id|>user<|end_header_id|>
-#   Get me an icecream.
-#   <|eot_id|>
-#   <|start_header_id|>assistant<|end_header_id|>
-#   Go buy it yourself at 7-11.
-#   <|eot_id|>
-
-# # Arguments
-#   - `name::T`
-#     message owner name e.f. "system", "user" or "assistant"
-#   - `text::T`
-
-# # Return
-#   - `formattedtext::String`
-#     text formatted to model format
-
-# # Example
-# ```jldoctest
-# julia> using Revise
-# julia> using YiemAgent
-# julia> d = Dict(:name=> "system",:text=> "You are a helpful, respectful and honest assistant.",)
-# julia> formattedtext = YiemAgent.formatLLMtext_llama3instruct(d[:name], d[:text])
-# "<|begin_of_text|>\n  <|start_header_id|>system<|end_header_id|>\n  You are a helpful, respectful and honest assistant.\n  <|eot_id|>\n"
-# ```
-
-# Signature
-# """
-# function formatLLMtext_llama3instruct(name::T, text::T) where {T<:AbstractString}
-#   formattedtext = 
-#   if name == "system"
-#     """
-#     <|begin_of_text|>
-#     <|start_header_id|>$name<|end_header_id|>
-#     $text
-#     <|eot_id|>
-#     """
+#   # Determine which indices to use - either provided range or full length
+#   ind = 
+#     if eventindex !== nothing
+#       [eventindex...]
 #     else
-#     """
-#     <|start_header_id|>$name<|end_header_id|>
-#     $text
-#     <|eot_id|>
-#     """
+#       1:length(events)
 #     end
 
-#   return formattedtext
-# end
-
-
-
-# """ Convert a chat messages in vector of dictionary into LLM model instruct format.
-
-# # Arguments
-#   - `messages::Vector{Dict{Symbol, T}}`
-#     message owner name e.f. "system", "user" or "assistant"
-#   - `formatname::T`
-#     format name to be used
-
-# # Return
-#   - `formattedtext::String`
-#     text formatted to model format
-
-# # Example
-# ```jldoctest
-# julia> using Revise
-# julia> using YiemAgent
-# julia> chatmessage = [
-#           Dict(:name=> "system",:text=> "You are a helpful, respectful and honest assistant.",),
-#           Dict(:name=> "user",:text=> "list me all planets in our solar system.",),
-#           Dict(:name=> "assistant",:text=> "I'm sorry. I don't know. You tell me.",),
-#         ]
-# julia> formattedtext = YiemAgent.formatLLMtext(chatmessage, "llama3instruct")
-# "<|begin_of_text|>\n  <|start_header_id|>system<|end_header_id|>\n  You are a helpful, respectful and honest assistant.\n  <|eot_id|>\n  <|start_header_id|>user<|end_header_id|>\n  list me all planets in our solar system.\n  <|eot_id|>\n  <|start_header_id|>assistant<|end_header_id|>\n  I'm sorry. I don't know. You tell me.\n  <|eot_id|>\n"
-# ```
-
-# # Signature
-# """
-# function formatLLMtext(messages::Vector{Dict{Symbol, T}}, 
-#                       formatname::String="llama3instruct") where {T<:Any}
-#   f = if formatname == "llama3instruct"
-#     formatLLMtext_llama3instruct
-#   elseif formatname == "mistral"
-#     # not define yet
-#   elseif formatname == "phi3instruct"
-#     formatLLMtext_phi3instruct
+#   # Iterate through events and format each one
+#   for i in ind
+#     event = events[i]
+#     # If no outcome exists, format without outcome
+#     if event[:outcome] === nothing
+#       timeline *= "Event_$i $(event[:subject])> action_name: $(event[:actionname]), action_input: $(event[:actioninput]), observation: Not done yet.\n"
+#     # If outcome exists, include it in formatting  
 #     else
-#     error("$formatname template not define yet")
-#   end
-
-#   str = ""
-#   for t in messages
-#     str *= f(t[:name], t[:text])
-#   end
-
-#   # add <|assistant|> so that the model don't generate it and I don't need to clean it up later
-#   if formatname == "phi3instruct"
-#     str *= "<|assistant|>\n"
-#   end
-
-#   return str
-# end
-
-
-# """
-
-#   Arguments\n
-#   -----
-    
-#   Return\n
-#   -----
-
-#   Example\n
-#   -----
-#   ```jldoctest
-#   julia> 
-#   ```
-
-#   TODO\n
-#   -----
-#     [] update docstring
-#     [PENDING] implement the function
-
-#   Signature\n
-#   -----
-# """
-# function iterativeprompting(a::T, prompt::String, verification::Function) where {T<:agent}
-#   msgMeta = GeneralUtils.generate_msgMeta(
-#     a.config[:externalService][:text2textinstruct],
-#     senderName= "iterativeprompting",
-#     senderId= a.id,
-#     receiverName= "text2textinstruct",
-#   )
-
-#   outgoingMsg = Dict(
-#     :msgMeta=> msgMeta,
-#     :payload=> Dict(
-#       :text=> prompt,
-#     )
-#   )
-
-#   success = nothing
-#   result = nothing
-#   critique = ""
-
-#   # iteration loop
-#   while true
-#     # send prompt to LLM
-#     response = GeneralUtils.sendReceiveMqttMsg(outgoingMsg)
-#     error("--> iterativeprompting")
-#     # check for correctness and get feedback
-#     success, _critique = verification(response)
-
-#     if success
-#       result = response
-#       break
-#     else  
-#       # add critique to prompt
-#       critique *= _critique * "\n"
-#       replace!(prompt, "Critique: ..." => "Critique: $critique")
+#       timeline *= "Event_$i $(event[:subject])> action_name: $(event[:actionname]), action_input: $(event[:actioninput]), observation: $(event[:outcome])\n"
 #     end
 #   end
 
-#   return (success=success, result=result)
+#   # Return formatted timeline string
+#   return timeline
 # end
 
 
+function createEventsLog(events::T1; index::Union{UnitRange, Nothing}=nothing
+  ) where {T1<:AbstractVector}
+  # Initialize empty log array
+  log = Dict{Symbol, String}[]
+
+  # Determine which indices to use - either provided range or full length
+  ind = 
+    if index !== nothing
+      [index...]
+    else
+      1:length(events)
+    end
+
+  # Iterate through events and format each one
+  for i in ind
+    event = events[i]
+    # If no outcome exists, format without outcome
+    if event[:outcome] === nothing
+      subject = event[:subject]
+      actioninput = event[:actioninput]
+      d = Dict{Symbol, String}(:name=>subject, :text=>actioninput)
+      push!(log, d)
+    else
+      subject = event[:subject]
+      actioninput = event[:actioninput]
+      outcome = event[:outcome]
+      str = "Action: $actioninput Outcome: $outcome"
+      d = Dict{Symbol, String}(:name=>subject, :text=>str)
+      push!(log, d)
+    end
+  end
+
+  return log
+end
+
+
+function createChatLog(chatdict::T1; index::Union{UnitRange, Nothing}=nothing
+  ) where {T1<:AbstractVector}
+  # Initialize empty log array
+  log = Dict{Symbol, String}[]
+
+  # Determine which indices to use - either provided range or full length
+  ind = 
+    if index !== nothing
+      [index...]
+    else
+      1:length(chatdict)
+    end
+
+  # Iterate through events and format each one
+  for i in ind
+    event = chatdict[i]
+    subject = event[:name]
+    text = event[:text]
+    d = Dict{Symbol, String}(:name=>subject, :text=>text)
+    push!(log, d)
+  end
+
+  return log
+end
+
+
 
 
 

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/config.json

@@ -27,10 +27,14 @@
       "description": "agent role"
   },
   "organization": {
-      "value": "yiem_hq",
+      "value": "yiem_branch_1",
       "description": "organization name"
   },
   "externalservice": {
+    "loadbalancer": {
+      "mqtttopic": "/loadbalancer/requestingservice",
+      "description": "text to text service with instruct LLM"
+    },
     "text2textinstruct": {
         "mqtttopic": "/loadbalancer/requestingservice",
         "description": "text to text service with instruct LLM",
@@ -51,6 +55,22 @@
         "llminfo": {
             "name": "llama3instruct"
         }
+    },
+    "wineDB" : {
+      "description": "A wine database connection info for LibPQ client",
+      "host": "192.168.88.12",
+      "port": 10201,
+      "dbname": "wineDB",
+      "user": "yiemtechnologies",
+      "password": "yiemtechnologies@Postgres_0.0"
+    },
+    "SQLVectorDB" : {
+      "description": "A wine database connection info for LibPQ client",
+      "host": "192.168.88.12",
+      "port": 10203,
+      "dbname": "SQLVectorDB",
+      "user": "yiemtechnologies",
+      "password": "yiemtechnologies@Postgres_0.0"
     }
   }
 }

test/etc.jl

@@ -1,9 +0,0 @@
-using GeneralUtils
-
-response = "trajectory_evaluation:\nThe trajectory is correct so far. The thought accurately reflects the user's question, and the action taken is a valid attempt to retrieve data from the database that matches the specified criteria.\n\nanswer_evaluation:\nThe observation provides information about two red wines from Bordeaux rive droite in France, which partially answers the question. However, it does not provide a complete answer as it only lists the wine names and characteristics, but does not explicitly state whether there are any other wines that match the criteria.\n\naccepted_as_answer: No\n\nscore: 6\nThe trajectory is mostly correct, but the observation does not fully address the question.\n\nsuggestion: Consider adding more filters or parameters to the database query to retrieve a complete list of wines that match the specified criteria."
-
-responsedict = GeneralUtils.textToDict(response,
-            ["trajectory_evaluation", "answer_evaluation", "accepted_as_answer", "score", "suggestion"], 
-            rightmarker=":", symbolkey=true)
-
-

test/test_1.jl

@@ -8,31 +8,46 @@ using Base.Threads
 
 
 # load config
-config = JSON3.read("./test/config.json")
+config = JSON3.read("/appfolder/app/dev/YiemAgent/test/config.json")
 # config = copy(JSON3.read("../mountvolume/config.json"))
 
 
 function executeSQL(sql::T) where {T<:AbstractString}
-  DBconnection = LibPQ.Connection("host=192.168.88.12 port=10201 dbname=wineDB user=yiemtechnologies password=yiemtechnologies@Postgres_0.0")
+  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)
-  DBconnection = LibPQ.Connection("host=192.168.88.12 port=10203 dbname=SQLVectorDB user=yiemtechnologies password=yiemtechnologies@Postgres_0.0")
+  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)
+function text2textInstructLLM(prompt::String; maxattempt::Integer=3, modelsize::String="medium",
+    llmkwargs=Dict(
+      :num_ctx => 32768,
+      :temperature => 0.1,
+    )
+  )
   msgMeta = GeneralUtils.generate_msgMeta(
-    config[:externalservice][:text2textinstruct][:mqtttopic];
+    config[:externalservice][:loadbalancer][:mqtttopic];
     msgPurpose="inference",
     senderName="yiemagent",
-    senderId=string(uuid4()),
-    receiverName="text2textinstruct",
+    senderId=sessionId,
+    receiverName="text2textinstruct_$modelsize",
     mqttBrokerAddress=config[:mqttServerInfo][:broker],
     mqttBrokerPort=config[:mqttServerInfo][:port],
   )
@@ -41,15 +56,24 @@ function text2textInstructLLM(prompt::String)
     :msgMeta => msgMeta,
     :payload => Dict(
       :text => prompt,
-      :kwargs => Dict(
-        :num_ctx => 16384,
-        :temperature => 0.2,
-      )
+      :kwargs => llmkwargs
     )
   )
 
-  _response = GeneralUtils.sendReceiveMqttMsg(outgoingMsg; timeout=6000)
+  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
@@ -57,11 +81,11 @@ end
 # get text embedding from a LLM service
 function getEmbedding(text::T) where {T<:AbstractString}
   msgMeta = GeneralUtils.generate_msgMeta(
-    config[:externalservice][:text2textinstruct][:mqtttopic];
+    config[:externalservice][:loadbalancer][:mqtttopic];
     msgPurpose="embedding",
     senderName="yiemagent",
-    senderId=string(uuid4()),
-    receiverName="text2textinstruct",
+    senderId=sessionId,
+    receiverName="textembedding",
     mqttBrokerAddress=config[:mqttServerInfo][:broker],
     mqttBrokerPort=config[:mqttServerInfo][:port],
   )
@@ -72,7 +96,8 @@ function getEmbedding(text::T) where {T<:AbstractString}
       :text => [text] # must be a vector of string
     )
   )
-  response = GeneralUtils.sendReceiveMqttMsg(outgoingMsg; timeout=6000)
+
+  response = GeneralUtils.sendReceiveMqttMsg(outgoingMsg; timeout=120, maxattempt=3)
   embedding = response[:response][:embeddings]
   return embedding
 end
@@ -80,10 +105,8 @@ 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
@@ -95,29 +118,29 @@ 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
   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__)
+    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__)
+    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=1) where {T1<:AbstractString, T2<:AbstractString}
+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]
@@ -134,14 +157,14 @@ function insertSQLVectorDB(query::T1, SQL::T2; maxdistance::Integer=1) where {T1
     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)
+    # println("\n~~~ added new decision to vectorDB ", @__FILE__, ":", @__LINE__, " $(Dates.now())")
+    # println(sql)
     _ = executeSQLVectorDB(sql)
   end
 end
 
 
-function similarSommelierDecision(recentevents::T1; maxdistance::Integer=5
+function similarSommelierDecision(recentevents::T1; maxdistance::Integer=3
   )::Union{AbstractDict, Nothing} where {T1<:AbstractString}
   tablename = "sommelier_decision_repository"
   # find similar
@@ -174,7 +197,7 @@ function insertSommelierDecision(recentevents::T1, decision::T2; maxdistance::In
   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_embedding = getEmbedding(recentevents)[1]
     recentevents = replace(recentevents, "'" => "")
     decision_json = JSON3.write(decision)
     decision_base64 = base64encode(decision_json)
@@ -214,7 +237,7 @@ a = YiemAgent.sommelier(
 )
 
 while true
-  println("your respond: ")
+  print("\nyour respond: ")
   user_answer = readline()
   response = YiemAgent.conversation(a, Dict(:text=> user_answer))
   println("\n$response")
@@ -224,14 +247,13 @@ 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.
+
+
+"""