update
This commit is contained in:
narawat lamaiin
207
test/runtest.jl
207
test/runtest.jl
@@ -1,12 +1,29 @@
|
||||
using Revise
|
||||
using LibPQ, JSON3, PrettyPrinting, UUIDs, DataFrames, DataStructures, Base64
|
||||
using LibPQ, Dates, JSON3, PrettyPrinting, UUIDs, DataFrames, DataStructures, Base64
|
||||
using GeneralUtils, SQLLLM
|
||||
|
||||
|
||||
config = copy(JSON3.read("config.json"))
|
||||
config = copy(JSON3.read("/appfolder/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=$password")
|
||||
result = LibPQ.execute(DBconnection, sql)
|
||||
close(DBconnection)
|
||||
return result
|
||||
end
|
||||
|
||||
function executeSQLVectorDB(sql)
|
||||
host = config[:externalservice][:SQLVectorDB][:host]
|
||||
port = config[:externalservice][:SQLVectorDB][:port]
|
||||
dbname = config[:externalservice][:SQLVectorDB][:dbname]
|
||||
user = config[:externalservice][:SQLVectorDB][:user]
|
||||
password = config[:externalservice][:SQLVectorDB][:password]
|
||||
DBconnection = LibPQ.Connection("host=$host port=$port dbname=$dbname user=$user password=$password")
|
||||
result = LibPQ.execute(DBconnection, sql)
|
||||
close(DBconnection)
|
||||
return result
|
||||
@@ -14,11 +31,11 @@ end
|
||||
|
||||
function text2textInstructLLM(prompt::String)
|
||||
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_medium",
|
||||
mqttBrokerAddress=config[:mqttServerInfo][:broker],
|
||||
mqttBrokerPort=config[:mqttServerInfo][:port],
|
||||
)
|
||||
@@ -28,7 +45,7 @@ function text2textInstructLLM(prompt::String)
|
||||
:payload => Dict(
|
||||
:text => prompt,
|
||||
:kwargs => Dict(
|
||||
:num_ctx => 20480,
|
||||
:num_ctx => 16384,
|
||||
:temperature => 0.2,
|
||||
)
|
||||
)
|
||||
@@ -40,126 +57,104 @@ function text2textInstructLLM(prompt::String)
|
||||
return response
|
||||
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 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],
|
||||
config[:externalservice][:loadbalancer][:mqtttopic];
|
||||
msgPurpose="embedding",
|
||||
senderName="yiemagent",
|
||||
senderId=sessionId,
|
||||
receiverName="text2textinstruct_medium",
|
||||
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]
|
||||
)
|
||||
response = GeneralUtils.sendReceiveMqttMsg(outgoingMsg; timeout=120)
|
||||
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]
|
||||
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__, " $(Dates.now())")
|
||||
return (dict=output_str, distance=distance)
|
||||
else
|
||||
println("\n~~~ similar sql not found, max distance $maxdistance ", @__FILE__, ":", @__LINE__, " $(Dates.now())")
|
||||
return (dict=nothing, distance=nothing)
|
||||
end
|
||||
end
|
||||
|
||||
|
||||
function insertSQLVectorDB(query::T1, SQL::T2; maxdistance::Integer=3) where {T1<:AbstractString, T2<:AbstractString}
|
||||
tablename = "sqlllm_decision_repository"
|
||||
# get embedding of the query
|
||||
# query = state[:thoughtHistory][:question]
|
||||
df = findSimilarTextFromVectorDB(query, tablename,
|
||||
"function_input_embedding", executeSQLVectorDB)
|
||||
row, col = size(df)
|
||||
distance = row == 0 ? Inf : df[1, :distance]
|
||||
if row == 0 || distance > 10 # no close enough SQL stored in the database
|
||||
latestKey, _ = GeneralUtils.findHighestIndexKey(state[:thoughtHistory], :action_input)
|
||||
_sqlStatement = state[:thoughtHistory][latestKey]
|
||||
if occursin("SELECT", _sqlStatement) # make sure it is an SQL statement before adding into DB
|
||||
sqlStatementBase64 = base64encode(_sqlStatement)
|
||||
sqlStatement = replace(_sqlStatement, "'"=>"")
|
||||
sql =
|
||||
"""
|
||||
INSERT INTO sql_statement_repository (question, sql_statement, sql_statement_base64, embedding) VALUES ('$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__, " $(Dates.now())")
|
||||
# println(sql)
|
||||
_ = executeSQLVectorDB(sql)
|
||||
end
|
||||
end
|
||||
|
||||
function querySQLVectorDB(state)
|
||||
|
||||
# provide similarSQL at the first time thinking only
|
||||
latestKey, _ = GeneralUtils.findHighestIndexKey(state[:thoughtHistory], :action_input)
|
||||
if latestKey === nothing
|
||||
# get embedding of the query
|
||||
query = [state[:thoughtHistory][:question]]
|
||||
msgMeta = GeneralUtils.generate_msgMeta(
|
||||
config[:externalservice][:text2textinstruct][:mqtttopic];
|
||||
msgPurpose= "embedding",
|
||||
senderName= "yiemagent",
|
||||
senderId= string(uuid4()),
|
||||
receiverName= "text2textinstruct",
|
||||
mqttBrokerAddress= config[:mqttServerInfo][:broker],
|
||||
mqttBrokerPort= config[:mqttServerInfo][:port],
|
||||
)
|
||||
|
||||
outgoingMsg = Dict(
|
||||
:msgMeta=> msgMeta,
|
||||
:payload=> Dict(
|
||||
:text=> query
|
||||
)
|
||||
)
|
||||
response = GeneralUtils.sendReceiveMqttMsg(outgoingMsg)
|
||||
embedding = response[:response][:embeddings][1]
|
||||
|
||||
# check whether there is close enough vector already store in vectorDB. if no, add, else skip
|
||||
sql =
|
||||
"""
|
||||
SELECT *, embedding <-> '$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))
|
||||
return sqlStatement
|
||||
else
|
||||
return nothing
|
||||
end
|
||||
end
|
||||
return nothing
|
||||
end
|
||||
|
||||
|
||||
sessionId = "555"
|
||||
|
||||
|
||||
# query = Dict(:text=> "How many wines from France do you have that can be paired with lamb?")
|
||||
# query = "How many wines are from United States?"
|
||||
query = "retailer: Yiem, wine_type: red, sweetness: 1-2, intensity: 4-5, wine price: 20-40"
|
||||
# query = "wine_type: white, country: United States, sweetness: 1-2, tannin: 3, food to be served with wine: pizza"
|
||||
# query = "retailer: Yiem, wine_type: red, sweetness: 1-2, intensity: 4-5, wine price: 20-40"
|
||||
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"
|
||||
# query = Dict(:text=> "wine_type: white, country: France, sweetness: 1")
|
||||
result = SQLLLM.query(query, executeSQL, text2textInstructLLM;
|
||||
addSQLVectorDB=addSQLVectorDB,
|
||||
querySQLVectorDB=querySQLVectorDB)
|
||||
insertSQLVectorDB=insertSQLVectorDB,
|
||||
similarSQLVectorDB=similarSQLVectorDB)
|
||||
|
||||
println(result)
|
||||
error(555)
|
||||
|
||||
Reference in New Issue
Block a user