328 lines
12 KiB
Julia
328 lines
12 KiB
Julia
using JSON, Dates, UUIDs, PrettyPrinting, LibPQ, Base64, DataFrames, DataStructures, HTTP, Base64,
|
|
NATS, Base.Threads
|
|
using YiemAgent, GeneralUtils
|
|
|
|
struct text2textInstructLLM
|
|
natsConn::NATS.Connection
|
|
topic::String
|
|
senderID::String
|
|
fileserver_url::String
|
|
end
|
|
|
|
function (t::text2textInstructLLM)(openai_msg::Dict{String, Any})
|
|
payloads = [("msg", openai_msg, "dictionary")] # List of tuples
|
|
_, msg_envelope_json_str = msghandler.smartpack(
|
|
t.topic,
|
|
payloads;
|
|
sender_id=t.senderID,
|
|
msg_purpose="text2text",
|
|
fileserver_url=t.fileserver_url)
|
|
|
|
reply = NATS.request(t.natsConn, t.topic, msg_envelope_json_str, timeout=180)
|
|
|
|
incoming_env_json_str = String(reply.payload)
|
|
incoming_env = msghandler.smartunpack(incoming_env_json_str)
|
|
_llm_response = incoming_env["payloads"][1][2]
|
|
llm_response = _llm_response["choices"][1]["message"]["content"]
|
|
return llm_response
|
|
end
|
|
|
|
|
|
# function get_embedding(text::AbstractArray{String})
|
|
# documents_dict = Dict("documents" => text)
|
|
# payloads = [("documents", documents_dict, "dictionary")]
|
|
# _, msg_envelope_json_str = msghandler.smartpack(
|
|
# config["externalservice"]["servicesloadbalancer"]["nats"],
|
|
# payloads;
|
|
# msg_purpose="embedding",
|
|
# broker_url=config["nats_server_info"]["url"],
|
|
# fileserver_url=config["externalservice"]["fileserver"]["url"])
|
|
|
|
# reply = NATS.request(agent_conn,
|
|
# config["externalservice"]["servicesloadbalancer"]["nats"],
|
|
# msg_envelope_json_str, timeout=120)
|
|
# incoming_env_json_str = String(reply.payload)
|
|
# incoming_env = msghandler.smartunpack(incoming_env_json_str)
|
|
# embedding_response = incoming_env["payloads"][1][2]
|
|
|
|
# return embedding_response
|
|
# end
|
|
|
|
|
|
# """ sql = "SELECT * FROM wine;"
|
|
# result = execute_sql_winedb(sql)
|
|
# """
|
|
# function execute_sql_winedb(sql::T) where {T<:AbstractString}
|
|
# host_url, _port = split(config["externalservice"]["sommpanion_db"]["url"], ':')
|
|
# port = parse(Int, _port)
|
|
# dbname = "winedb"
|
|
# user = config["externalservice"]["sommpanion_db"]["user"]
|
|
# password = config["externalservice"]["sommpanion_db"]["password"]
|
|
# db_connection = LibPQ.Connection("host=$host_url port=$port dbname=$dbname user=$user password=$password")
|
|
# result = nothing
|
|
# try
|
|
# result = LibPQ.execute(db_connection, sql)
|
|
# catch e
|
|
# LibPQ.close(db_connection)
|
|
# end
|
|
|
|
# LibPQ.close(db_connection)
|
|
# return result
|
|
# end
|
|
|
|
# """ find similar sql from vector database
|
|
# sql = "SELECT * FROM wine;"
|
|
# result, distance = similar_sql_vectordb(sql)
|
|
# """
|
|
# function similar_sql_vectordb(sql::T; maxdistance::Number=1) where {T<:AbstractString}
|
|
# tablename = "sqlllm_decision_repository"
|
|
# # get embedding of the query
|
|
# df = find_similar_text_from_vectordb(sql, tablename,
|
|
# "function_input_embedding", execute_sql_vectordb)
|
|
# # println(df[1, [:id, :function_output]])
|
|
# row, col = size(df)
|
|
# distance = row == 0 ? Inf : df[1, :distance]
|
|
# if row != 0 && distance < maxdistance
|
|
# # if there is usable SQL, return it.
|
|
# output_b64 = df[1, :function_output_base64] # pick the closest match
|
|
# output_str = String(base64decode(output_b64))
|
|
# rowid = df[1, :id]
|
|
# println("\n--| similar sql found. row id $rowid, distance $distance ", @__FILE__, ":", @__LINE__, " $(Dates.now())")
|
|
# pprintln(output_str)
|
|
# return (result=output_str, distance=distance)
|
|
# else
|
|
# println("\n--| similar sql not found, max distance $maxdistance ", @__FILE__, ":", @__LINE__, " $(Dates.now())")
|
|
# return (result=nothing, distance=nothing)
|
|
# end
|
|
# end
|
|
|
|
# """ insert query and sql into vector database
|
|
# query = "get all wines from wine table"
|
|
# sql = "SELECT * FROM wine;"
|
|
# insert_sql_vectordb(query, sql)
|
|
# """
|
|
# function insert_sql_vectordb(query::T1, SQL::T2; maxdistance::Number=3
|
|
# ) where {T1<:AbstractString, T2<:AbstractString}
|
|
|
|
# tablename = "sqlllm_decision_repository"
|
|
# # get embedding of the query
|
|
# # query = state[:thoughtHistory][:question]
|
|
# df = find_similar_text_from_vectordb(query, tablename,
|
|
# "function_input_embedding", execute_sql_vectordb)
|
|
# row, col = size(df)
|
|
# distance = row == 0 ? Inf : df[1, :distance]
|
|
# if row == 0 || distance > maxdistance # no close enough SQL stored in the database
|
|
# _query_embedding = get_embedding([query])
|
|
# _query_embedding = GeneralUtils.dictify(_query_embedding)
|
|
# # println("\n--- _query_embedding() ", @__FILE__, ":", @__LINE__, " $(Dates.now())")
|
|
# # println(_query_embedding)
|
|
# # println("---\n")
|
|
# query_embedding = _query_embedding["data"][1]["embedding"]
|
|
# query = replace(query, "'" => "")
|
|
# sql_base64 = base64encode(SQL)
|
|
# sql_ = replace(SQL, "'" => "")
|
|
|
|
# sql =
|
|
# """
|
|
# INSERT INTO $tablename (function_input, function_output, function_output_base64, function_input_embedding) VALUES ('$query', '$sql_', '$sql_base64', '$query_embedding');
|
|
# """
|
|
# # println("\n--| added new decision to vectorDB ", @__FILE__, ":", @__LINE__, " $(Dates.now())")
|
|
# # println(sql)
|
|
# _ = execute_sql_vectordb(sql)
|
|
# end
|
|
# end
|
|
|
|
# """ execute sql against vectordb
|
|
# sql = "SELECT * FROM wine;"
|
|
# result = execute_sql_vectordb(sql)
|
|
# """
|
|
# function execute_sql_vectordb(sql::T) where {T<:AbstractString}
|
|
# host_url, _port = split(config["externalservice"]["sommpanion_vectordb"]["url"], ':')
|
|
# port = parse(Int, _port)
|
|
# dbname = config["externalservice"]["sommpanion_vectordb"]["dbname"]
|
|
# user = config["externalservice"]["sommpanion_vectordb"]["user"]
|
|
# password = config["externalservice"]["sommpanion_vectordb"]["password"]
|
|
# DBconnection = LibPQ.Connection("host=$host_url port=$port dbname=$dbname user=$user password=$password")
|
|
# result = LibPQ.execute(DBconnection, sql)
|
|
# close(DBconnection)
|
|
# return result
|
|
# end
|
|
|
|
# """ search similar decision llm made from vectordb
|
|
# """
|
|
# function similar_sommelier_decision(recentevents::T1; maxdistance::Integer=3
|
|
# )::Union{AbstractDict, Nothing} where {T1<:AbstractString}
|
|
|
|
# tablename = "sommelier_decision_repository"
|
|
# # find similar
|
|
# df = find_similar_text_from_vectordb(recentevents, tablename,
|
|
# "function_input_embedding", execute_sql_vectordb)
|
|
# row, col = size(df)
|
|
# distance = row == 0 ? Inf : df[1, :distance]
|
|
# if row != 0 && distance < maxdistance
|
|
# # if there is usable decision, return it.
|
|
# rowid = df[1, :id]
|
|
# println("\n--| found similar decision. row id $rowid, distance $distance ", @__FILE__, " ", @__LINE__)
|
|
# output_b64 = df[1, :function_output_base64] # pick the closest match
|
|
# _output_str = String(base64decode(output_b64))
|
|
# output = copy(JSON.read(_output_str))
|
|
# return output
|
|
# else
|
|
# println("\n--| similar decision not found, max distance $maxdistance ", @__FILE__, " ", @__LINE__)
|
|
# return nothing
|
|
# end
|
|
# end
|
|
|
|
# """ search similar text from vectordb
|
|
# """
|
|
# function find_similar_text_from_vectordb(text::T1, tablename::T2, embeddingColumnName::T3,
|
|
# vectorDB::Function; limit::Integer=1
|
|
# )::DataFrame where {T1<:AbstractString, T2<:AbstractString, T3<:AbstractString}
|
|
# # get embedding from LLM service
|
|
# _embedding = get_embedding([text])
|
|
# _embedding = _embedding["data"][1]["embedding"]
|
|
# _embedding = "$_embedding"
|
|
|
|
# embedding = _embedding[4:end] # remove 'Any' from Any[...]
|
|
|
|
# # check whether there is close enough vector already store in vectorDB. if no, add, else skip
|
|
# sql = """
|
|
# SELECT *, $embeddingColumnName <-> '$embedding' as distance
|
|
# FROM $tablename
|
|
# ORDER BY distance LIMIT $limit;
|
|
# """
|
|
# response = vectorDB(sql)
|
|
# df = DataFrame(response)
|
|
|
|
# return df
|
|
# end
|
|
|
|
# """ insert decision llm made to vectordb
|
|
# """
|
|
# function insert_sommelier_decision(recentevents::T1, decision::T2; maxdistance::Integer=5
|
|
# ) where {T1<:AbstractString, T2<:AbstractDict}
|
|
# tablename = "sommelier_decision_repository"
|
|
# # find similar
|
|
# df = find_similar_text_from_vectordb(recentevents, tablename,
|
|
# "function_input_embedding", execute_sql_vectordb)
|
|
# row, col = size(df)
|
|
# distance = row == 0 ? Inf : df[1, :distance]
|
|
# if row == 0 || distance > maxdistance # no close enough SQL stored in the database
|
|
# _embedding = get_embedding([recentevents])[1]
|
|
# recentevents_embedding = _embedding["data"][1]["embedding"]
|
|
# recentevents = replace(recentevents, "'" => "")
|
|
# decision_json = JSON.json(decision)
|
|
# decision_base64 = base64encode(decision_json)
|
|
# decision = replace(decision_json, "'" => "")
|
|
|
|
# sql =
|
|
# """
|
|
# INSERT INTO $tablename (function_input, function_output, function_output_base64, function_input_embedding) VALUES ('$recentevents', '$decision', '$decision_base64', '$recentevents_embedding');
|
|
# """
|
|
# println("\n--| added new decision to vectorDB ", @__FILE__, " ", @__LINE__)
|
|
# println(sql)
|
|
# _ = execute_sql_vectordb(sql)
|
|
# else
|
|
# println("--| similar decision previously cached, distance $distance ", @__FILE__, " ", @__LINE__)
|
|
# end
|
|
# end
|
|
|
|
# function find_related_tables_for_user_question(question::String; top_row_num::Integer=20)
|
|
|
|
# metadata_df = GeneralUtils.extract_column_metadata(pg_conn_str)
|
|
# embedding_ready = GeneralUtils.generate_embedding_payloads(metadata_df)
|
|
|
|
# # use only text content
|
|
# embedding_ready_2 = [i["text_content"] for i in embedding_ready]
|
|
|
|
# table_embedding = get_embedding(embedding_ready_2)
|
|
|
|
# _user_question_embedding = get_embedding([question])
|
|
# user_question_embedding = Float64.(_user_question_embedding["data"][1]["embedding"])
|
|
# user_question_similarity = []
|
|
|
|
# for i in table_embedding["data"]
|
|
# i_data = i["embedding"]
|
|
# i_float = Float64.(i_data)
|
|
# r = 1 - Distances.cosine_dist(i_float, user_question_embedding)
|
|
# push!(user_question_similarity, r)
|
|
# end
|
|
|
|
# new_df = hcat(metadata_df, DataFrame(user_question_similarity = user_question_similarity))
|
|
# sorted_df = sort(new_df, :user_question_similarity, rev=true) # sort max to min
|
|
# _top_20_tables = unique(sorted_df[1:top_row_num, :table_name])
|
|
# top_20_tables = [i for i in _top_20_tables] # convert to Vector{String}
|
|
# g, id_to_table, table_to_id = GeneralUtils.harvest_db_undirected_schema_graph(pg_conn_str)
|
|
# table_relationship = GeneralUtils.resolve_semantic_cluster(top_20_tables, g, table_to_id, id_to_table)
|
|
|
|
# # tables that I should put schema in LLM context
|
|
# return table_relationship
|
|
# end
|
|
|
|
|
|
# function prepareContext(state::agentState)::agentContext
|
|
|
|
# #TODO filter tools from state.tools based on user intend in user message and tool description
|
|
# filteredTools = state.tools
|
|
|
|
# #TODO add filtered tools to the current system prompt / modify systemPrompt here
|
|
# preparedSystemPrompt = state.systemPrompt
|
|
|
|
# #TODO add system prompt, adjust/modify and inject additional context into messages
|
|
# preparedMessages = deepcopy(state.messages) # messages that will be send to LLM
|
|
|
|
# agentCtx = agentContext(preparedSystemPrompt, preparedMessages, filteredTools)
|
|
|
|
# return agentCtx
|
|
# end
|
|
|
|
# function formatMsgForLLM(ctx::agentContext)::Dict{String, Any}
|
|
|
|
# end
|
|
|
|
|
|
config = JSON.parsefile("./appconfig.json")
|
|
host_url, _port = split(config["externalservice"]["sommpanion_db"]["url"], ':')
|
|
port = parse(Int, _port)
|
|
dbname = "winedb"
|
|
user = config["externalservice"]["sommpanion_db"]["user"]
|
|
password = config["externalservice"]["sommpanion_db"]["password"]
|
|
pg_conn_str = "host=$host_url port=$port dbname=$dbname user=$user password=$password"
|
|
sessionId = "0"
|
|
backend_session_topic = "sommpanion.testsubject"
|
|
agent_ch = Channel(8)
|
|
agent_conn = NATS.connect(config["nats_server_info"]["url"])
|
|
|
|
sub2 = NATS.subscribe(agent_conn, backend_session_topic) do msg
|
|
put!(agent_ch, msg)
|
|
end
|
|
|
|
|
|
|
|
# model=YiemAgent.llmModel("model_1", "unknown", "unknown", "", false, String[],
|
|
# YiemAgent.modelCost(0.0, 0.0, 0.0, 0.0), 0, 0)
|
|
|
|
|
|
|
|
#WORKING load tools
|
|
text2text_llm = text2textInstructLLM(agent_conn,
|
|
config["externalservice"]["servicesloadbalancer"]["nats"],
|
|
"sender",
|
|
config["externalservice"]["fileserver"]["url"])
|
|
|
|
agent = YiemAgent.yiemAgent(
|
|
"/home/ton/docker-apps/sommpanion/agent-backend/tools",
|
|
text2text_llm
|
|
)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|