ton/YiemAgent
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 6 Wiki Activity

Merge pull request 'v0.7.4-add_vector_search' (#33) from v0.7.4-add_vector_search into v0.7.4

Browse Source 
Reviewed-on: #33
This commit was merged in pull request #33.
This commit is contained in:
ton
2026-07-26 15:42:34 +00:00
parent 5bde0ca1f2 4d6cdbcf4a
commit c803238f86
6 changed files with 350 additions and 460 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Manifest.toml
+5 -5
View File
@@ -2,7 +2,7 @@
julia_version = "1.12.6"
manifest_format = "2.0"
project_hash = "dc7878808bbc4637a12e709dd495979a784824a5"
project_hash = "1c1379a2cec320abc347f3acb5ee815ba9855aa6"
[[deps.Accessors]]
deps = ["CompositionsBase", "ConstructionBase", "Dates", "InverseFunctions", "MacroTools"]
@@ -300,11 +300,11 @@ version = "1.1.0"
[[deps.GeneralUtils]]
deps = ["CSV", "DataFrames", "DataStructures", "Dates", "Distributions", "Graphs", "HTTP", "JSON", "LibPQ", "NATS", "PrettyPrinting", "Random", "Revise", "SHA", "StringDistances", "UUIDs"]
git-tree-sha1 = "a75a088ee8e5faf10f554ca00748e0e6ca58d1ca"
git-tree-sha1 = "93293126d24d3929ef6a5067f347bc28c6582c71"
repo-rev = "main"
repo-url = "https://git.yiem.cc/ton/GeneralUtils"
uuid = "c6c72f09-b708-4ac8-ac7c-2084d70108fe"
version = "0.5.1"
version = "0.5.10"
[[deps.Graphs]]
deps = ["ArnoldiMethod", "DataStructures", "Inflate", "LinearAlgebra", "Random", "SimpleTraits", "SparseArrays", "Statistics"]
@@ -1089,10 +1089,10 @@ uuid = "ddb6d928-2868-570f-bddf-ab3f9cf99eb6"
version = "0.4.16"
[[deps.YiemAgent]]
deps = ["Base64", "CSV", "DataFrames", "DataStructures", "Dates", "GeneralUtils", "HTTP", "JSON", "LLMMCTS", "LibPQ", "NATS", "PrettyPrinting", "Random", "Revise", "SQLLLM", "Serialization", "URIs", "UUIDs"]
deps = ["Base64", "CSV", "DataFrames", "DataStructures", "Dates", "HTTP", "JSON", "LLMMCTS", "LibPQ", "NATS", "PrettyPrinting", "Random", "Revise", "SQLLLM", "Serde", "Serialization", "URIs", "UUIDs"]
path = "."
uuid = "e012c34b-7f78-48e0-971c-7abb83b6f0a2"
version = "0.7.2"
version = "0.7.4"
[[deps.Zlib_jll]]
deps = ["Libdl"]
Project.toml
+1 -1
View File
@@ -28,7 +28,7 @@ UUIDs = "cf7118a7-6976-5b1a-9a39-7adc72f591a4"
Base64 = "1.11.0"
CSV = "0.10.15"
DataFrames = "1.7.0"
GeneralUtils = "0.5.1"
GeneralUtils = "0.5.10"
HTTP = "2.4.0"
JSON = "1.6.1"
LLMMCTS = "0.1.5"
etc.jl
+9 -199
View File
@@ -1,200 +1,10 @@
using HTTP, JSON, URIs, Random, PrettyPrinting, UUIDs, Dates, DataFrames, DataStructures
using GeneralUtils, SQLLLM, YiemAgent
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=$password"
function execute_sql_winedb(sql::T) where {T<:AbstractString}
host_url, _port = split(config["externalservice"]["sommpanion_db"]["url"], ':')
port = parse(Int, _port)
dbname = "winedb"
user = config["externalservice"]["sommpanion_db"]["user"]
password = config["externalservice"]["sommpanion_db"]["password"]
db_connection = LibPQ.Connection("host=$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)
# check if this column has vector embedding. if there is one, seach vector version instead
column_name_embedding = column_name * "_embedding"
if occursin(column_name_embedding, tables_schema[column_name_embedding])
vector_column = Dict(
"table_name"=> table_name,
"column_name"=> column_name_embedding,
"operator"=> "vector_similarity",
"value"=> column_obj["value"]
)
end
LibPQ.close(db_connection)
return result
end
sql =
"""
SELECT T1.winery, T1.wine_name, T1.wine_id, T1.vintage, T1.region, T1.country, T1.wine_type, T1.grape, T1.serving_temperature, T1.sweetness, T1.intensity, T1.tannin, T1.acidity, T1.tasting_notes, T2.price, T2.currency, T1.image_url, T3.retailer_name, T3.retailer_id FROM "wine" AS T1 JOIN "retailer_wine" AS T2 ON T1.wine_id = T2.wine_id JOIN "retailer" AS T3 ON T2.retailer_id = T3.retailer_id WHERE T1.wine_name = 'Montrachet Grand Cru' AND T1.winery = 'Domaine Jacques Prieur' AND T3.retailer_name = 'Yiem Wines Ltd' AND T3.retailer_id = 'f54eab6b-7650-4448-b009-c53f3efbcc3b';
"""
textresult, sql_result_raw, _, _ = YiemAgent.SQLexecution(execute_sql_winedb, sql)
result_vec = GeneralUtils.dfToVectorDict(sql_result_raw)
for d in result_vec
wine_name = d["wine_name"]
image_url_json_str = d["image_url"]
image_url_json_obj = JSON.parse(image_url_json)
base_url = "http://192.168.88.106:8080/"
image_base64 =
if haskey(image_url_json_obj, "bottle")
url = base_url * image_url_json_obj["bottle"]
image_data = HTTP.get(url) # vector{int} data
image_base64_string = base64encode(image_data)
else
nothing
end
d["image"] = image_base64
end
using LibPQ
using Tables
"""
update_car_regions_one_by_one(conn::LibPQ.Connection, target_word::String)
Iterates through all rows in the 'car' table where the region is "German",
and updates them one-by-one to the `target_word`.
"""
function update_car_regions_one_by_one(pg_conn_str::String, replace_word::String , target_word::String)
conn = LibPQ.Connection(pg_conn_str)
# 1. Fetch the target rows. Assumes 'id' is the primary key.
# We select the ID to target rows individually during the update step.
select_query = "SELECT id FROM car WHERE region = '$replace_word';"
result = execute(conn, select_query)
rows = Tables.rows(result)
# 2. Prepare the update statement for execution reuse
# Using explicit types for parameter placeholders ($1, $2)
update_query = "UPDATE car SET region = \$1 WHERE id = \$2;"
println("Starting one-by-one update...")
updated_count = 0
# 3. Iterate through rows one-by-one
for row in rows
# LibPQ row values are accessed via properties or column names
row_id = row.id
# Execute the parameterized statement safely
execute(conn, update_query, [target_word, row_id])
updated_count += 1
end
println("Successfully updated \$updated_count rows.")
return updated_count
end
function generate_wine_retail_sql(conditions::Dict{String, Any})::String
# 1. Base SQL structure
base_query = """
SELECT
w.winery,
w.wine_name,
w.wine_id,
w.vintage,
w.region,
w.country,
w.wine_type,
w.grape,
w.serving_temperature,
w.sweetness,
w.intensity,
w.tannin,
w.acidity,
w.tasting_notes,
rw.price,
rw.currency,
w.image_url,
NULL AS retailer_name,
rw.retailer_id
FROM wine AS w
JOIN retailer_wine AS rw
ON w.wine_id = rw.wine_id
"""
# 2. Dynamic WHERE Clause Builder
where_clauses = String[]
# Iterate over each table condition provided
for (table_name, table_conditions) in conditions
# Determine table alias
alias = if table_name == "wine"
"w"
elseif table_name == "retailer_wine"
"rw"
else
continue # Skip unsupported tables
end
# Process condition dictionaries
if isa(table_conditions, Dict) && !isempty(table_conditions)
for (column_name, filter_details) in table_conditions
if isa(filter_details, Dict) && haskey(filter_details, "operator")
op = filter_details["operator"]
raw_val = filter_details["value"]
# --- Value Type Handling ---
# Use tryparse instead of try/catch for cleaner, faster parsing
final_val = raw_val
if op in ("=", "<", ">", "<=", ">=")
str_val = string(raw_val)
num_val = tryparse(Float64, str_val)
if !isnothing(num_val)
final_val = isinteger(num_val) ? round(Int, num_val) : num_val
end
end
# --- SQL Formatting ---
if isa(final_val, Number)
clause = "$(alias).$(column_name) $(op) $(final_val)"
else
# Escape single quotes within string values
escaped_val = replace(string(final_val), "'" => "''")
clause = "$(alias).$(column_name) $(op) '$(escaped_val)'"
end
push!(where_clauses, clause)
end
end
end
end
# 3. Assemble Final Query
where_sql = isempty(where_clauses) ? "" : "WHERE " * join(where_clauses, " AND ")
return string(base_query, where_sql, ";")
end
src/interface.jl
+81 -19
View File
@@ -122,10 +122,70 @@ function decisionMaker(a::T; recentevents::Integer=20, maxattempt=3
errornote = "N/A"
response = nothing # placeholder for show when error msg show up
"""
{
"model": "your-model.gguf",
"messages": [ ... ],
"response_format": {
"type": "json_schema",
"json_schema": {
"name": "agent_action",
"strict": true,
"schema": {
"type": "object",
"properties": {
"think": {
"type": "string",
"description": "Your step-by-step reasoning process. Explain why you are choosing this action."
},
"action_name": {
"type": "string",
"enum": ["search_web", "get_weather", "calculate_math"],
"description": "The exact name of the tool to execute."
},
"action_input": {
"type": "object",
"properties": {
"query": { "type": ["string", "null"], "description": "For search_web" },
"location": { "type": ["string", "null"], "description": "For get_weather" },
"equation": { "type": ["string", "null"], "description": "For calculate_math" }
},
"required": ["query", "location", "equation"],
"additionalProperties": false
}
},
"required": ["think", "action_name", "action_input"],
"additionalProperties": false
}
}
}
}
"""
# strict output format
response_format = Dict(
"type"=> "json_schema",
"json_schema"=> Dict(
"name"=> "user_profile",
"strict"=> true,
"schema"=> Dict(
"type"=> "object",
"properties"=> Dict(
"plan"=> Dict("type"=> "string"),
"action_name"=> Dict("type"=> "string"),
"action_input"=> Dict("type"=> "string"),
),
"required"=> ["plan", "action_name", "action_input"],
"additionalProperties"=> false
)
)
)
msg = Dict(
"model"=> "gemma-4-E4B-it-UD-Q4_K_XL",
"messages"=> a.chathistory,
"temperature" => 0.7
"temperature"=> 0.7,
"response_format"=> response_format,
)
for attempt in 1:maxattempt
@@ -138,25 +198,27 @@ function decisionMaker(a::T; recentevents::Integer=20, maxattempt=3
response = replace(response, '$' => "USD")
end
responsedict = nothing
try
responsedict = Serde.parse_yaml(response)
catch e
println("\nERROR YiemAgent decisionMaker() Error: $e --(not qualify response)-> $response ", @__FILE__, ":", @__LINE__, " $(Dates.now())\n")
continue
end
# responsedict = nothing
# try
# responsedict = Serde.parse_yaml(response)
# catch e
# println("\nERROR YiemAgent decisionMaker() Error: $e --(not qualify response)-> $response ", @__FILE__, ":", @__LINE__, " $(Dates.now())\n")
# continue
# end
# check whether all answer's key points are in responsedict
println("\n---")
println(responsedict)
println("---\n")
ispass, errormsg = GeneralUtils.checkAgentResponse_JSON(responsedict, requiredKeys)
# # check whether all answer's key points are in responsedict
# println("\n---")
# println(responsedict)
# println("---\n")
# ispass, errormsg = GeneralUtils.checkAgentResponse_JSON(responsedict, requiredKeys)
if !ispass
errornote = errormsg
println("\nERROR YiemAgent decisionMaker() $errornote --(not qualify response)-> $responsedict ", @__FILE__, ":", @__LINE__, " $(Dates.now())\n")
continue
end
# if !ispass
# errornote = errormsg
# println("\nERROR YiemAgent decisionMaker() $errornote --(not qualify response)-> $responsedict ", @__FILE__, ":", @__LINE__, " $(Dates.now())\n")
# continue
# end
responsedict = JSON.parse(response)
if responsedict["action_input"] == "CHAT_BOX" &&
occursin("similar", responsedict["action_input"])
@@ -564,7 +626,7 @@ function think(a::T)::NamedTuple{(:thoughtdict, :result_raw), Tuple{OrderedDict,
end
@info "YiemAgent think() end " @__LINE__
@show thoughtdict
# @show thoughtdict
println("---\n")
return (thoughtdict=thoughtdict, result_raw=result_raw)
end
src/llmfunction.jl
+240 -216
View File
@@ -5,7 +5,7 @@ export virtualWineUserChatbox, jsoncorrection, search_wine_database!, # recomme
extractWineAttributes_2, paraphrase, SQLexecution
using HTTP, JSON, URIs, Random, PrettyPrinting, UUIDs, Dates, DataFrames, DataStructures,
Base64, Serde, LibPQ
Base64, Serde, LibPQ, NATS
using GeneralUtils, SQLLLM
using ..type, ..util
@@ -302,11 +302,47 @@ function search_wine_database!(a::T, thoughtdict::AbstractDict; useSQLLLM::Bool=
else
# direct query with possible sql instead of SQLLLM.
sql = predefined_wine_search_sql(a, thoughtdict["action_input"])
hard_conditions, vector_search = wine_search_term_classification(a, thoughtdict["action_input"])
# do hard filter
# sql = generatesql(a, inventoryquery)
println("\nSQL: $sql ", @__FILE__, ":", @__LINE__, " $(Dates.now()) \n")
sql = predefined_wine_search_sql(hard_conditions)
@info "\nsql: $sql, \nvector_search: $vector_search"
textresult, sql_result_df, success, _ = SQLexecution(a.context.executeSQL, sql)
# do vector search
vector_search_str = ""
for i in vector_search
vector_search_str = vector_search_str * " " * i["value"]
end
vector_search_str = String(strip(vector_search_str))
vector_search_str = GeneralUtils.removestring(vector_search_str, ["%"])
@show vector_search
@show vector_search_str
config = a.context.agentconfig
host_url, _port = split(config["externalservice"]["sommpanion_db"]["url"], ':')
port = parse(Int, _port)
dbname = "winedb"
user = config["externalservice"]["sommpanion_db"]["user"]
password = config["externalservice"]["sommpanion_db"]["password"]
pg_conn_str = "host=$host_url port=$port dbname=$dbname user=$user password=$password"
#WORKING
# df = GeneralUtils.find_text_vector_similarity(
# vector_search_str,
# "wine",
# "tasting_notes_embedding",
# GeneralUtils.execute_postgres_sql(pg_conn_str, sql), #BUG input pair (F, arg)
# a.context.getTextEmbedding([vector_search_str]) #BUG input pair (F, arg)
# )
# @show df
# error(888888)
items = nothing
if sql_result_df !== nothing
result_vec = GeneralUtils.dfToVectorDict(sql_result_df)
@@ -619,9 +655,9 @@ julia> thoughtdict =
```
julia> predefined_wine_search_sql(agent, thoughtdict["action_input"])
"""
function predefined_wine_search_sql(a::T, searchterm::String,
function wine_search_term_classification(a::T, searchterm::String,
; maxattempt=10
)::String where {T<:agent}
) where {T<:agent}
systemmsg =
"""
@@ -637,43 +673,47 @@ function predefined_wine_search_sql(a::T, searchterm::String,
# your responsibility includes
Fulfill the objective.
# you should only respond in YAML format as described below
table_name_1:
column_name_1:
operator: "="
value: "..."
column_name_2:
operator: "="
value: "..."
...
table_name_2:
column_name_1:
operator: "="
value: "..."
column_name_2:
operator: "="
value: "..."
...
# You must output your response as a JSON object containing a single key: "extracted_info".
The "extracted_info" key must contain an array of objects. Each object must contain:
1) "table_name": The name of the table.
2) "column_name": The specific column being filtered.
3) "operator": The comparison operator (e.g., "=", ">").
4) "value": The value to compare against.
If the user does not specify any filters, return an empty array for "extracted_info": {"extracted_info": []}.
# here are some example
<user>
4-wheel drive car with red color that will give me fast and furious emotion. No more than 7000 USD
</user>
<assistant>
car_info: # table_name
drive_type: # column_name
operator: "=" # operator is not "N/A" because drive_type column store quantitative value
value: "4-wheel" # column_value
color:
operator: "=" # operator is not "N/A" because color column store quantitative value
value: "red"
drive_feeling:
operator: "N/A" # operator is "N/A" because drive_feeling column store qualitative value
value: "fast and furious"
price_list:
price:
operator: "<" # operator is not "N/A" because drive_type column store quantitative value
value: "7000"
{
"extracted_info": [
{
"table_name": "car_info",
"column_name": "drive_type",
"operator": "=",
"value": "4-wheel"
},
{
"table_name": "car_info",
"column_name": "color",
"operator": "=",
"value": "red"
},
{
"table_name": "car_info",
"column_name": "drive_feeling",
"operator": "=",
"value": "fast and furious"
},
{
"table_name": "price_list",
"column_name": "price",
"operator": "<",
"value": "7000"
}
}
</assistant>
"""
@@ -700,6 +740,48 @@ function predefined_wine_search_sql(a::T, searchterm::String,
"""
input = context * searchterm
response_format = Dict(
"type" => "json_schema",
"json_schema" => Dict(
"name" => "extracted_conditions",
"strict" => true,
"schema" => Dict(
"type" => "object",
"properties" => Dict(
"extracted_info" => Dict(
"type" => "array",
"items" => Dict(
"type" => "object",
"properties" => Dict(
"table_name" => Dict(
"type" => "string",
"description" => "The name of the database table."
),
"column_name" => Dict(
"type" => "string",
"description" => "The name of the column to filter on."
),
"operator" => Dict(
"type" => "string",
"enum" => ["=", "!=", ">", "<", ">=", "<=", "LIKE", "IN", "IS NULL", "IS NOT NULL"],
"description" => "The SQL comparison operator."
),
"value" => Dict(
"type" => ["string", "null"],
"description" => "The value to compare against. Use null for IS NULL/IS NOT NULL."
)
),
"required" => ["table_name", "column_name", "operator", "value"],
"additionalProperties" => false
)
)
),
"required" => ["extracted_info"],
"additionalProperties" => false
)
)
)
msg = Dict(
"model" => "gemma-4-E4B-it-UD-Q4_K_XL",
"messages" => [
@@ -716,92 +798,142 @@ function predefined_wine_search_sql(a::T, searchterm::String,
]
),
],
"temperature" => 0.7
"temperature" => 0.7,
"response_format"=> response_format,
)
for attempt in 1:maxattempt
response = a.context.text2textInstructLLM("random_id", msg)
responsedict = nothing
try
responsedict = Serde.parse_yaml(response)
catch e
println("\nERROR YiemAgent predefined_wine_search_sql() Error: $e --(not qualify response)-> $response ", @__FILE__, ":", @__LINE__, " $(Dates.now())\n")
continue
end
responsedict = JSON.parse(response)
# responsedict = nothing
# try
# responsedict = Serde.parse_yaml(response)
# catch e
# println("\nERROR YiemAgent predefined_wine_search_sql() Error: $e --(not qualify response)-> $response ", @__FILE__, ":", @__LINE__, " $(Dates.now())\n")
# continue
# end
# println("\n ", table_schema)
println("\n ", responsedict)
@info "before BM25 " @__LINE__
"""
responsedict = Dict(
"wine" => Dict(
"tasting_notes" => Dict(
"operator" => "N/A",
"value" => "casual dinner"
),
"wine_type" => Dict(
"operator" => "=",
"value" => "red"
)
),
"retailer_wine" => Dict(
"currency" => Dict(
"operator" => "=", "value" => "USD"
),
"price" => Dict(
"operator" => "<", "value" => "1000"
)
)
)
"""
# to ensure user input is correct
for entry in responsedict["extracted_info"]
table_name = entry["table_name"]::String
column_name = entry["column_name"]::String
for (table_name, table_info_dict) in responsedict
for (column_name, v) in table_info_dict
bucket = classify_column(a.context.pg_conn_str, table_name, column_name)
if bucket == "fuzzy_correction"
words_catalog = GeneralUtils.harvest_entity_catalog(a.context.pg_conn_str, table_name, column_name)
resolved_word = GeneralUtils.resolve_entity(v["value"], words_catalog; threshold=0.9)
table_info_dict[column_name]["value"] = resolved_word
resolved_word = GeneralUtils.resolve_entity(entry["value"], words_catalog; threshold=0.9)
entry["value"] = resolved_word
end
end
end
# filter for column that will be used for hard condition (SQL where clause)
# column with "N/A" operator will be used in vector search
# column with non-standard operator will be used in vector search
vector_search_words = ""
for (table_name, table_dict) in responsedict
for (column_name, column_dict) in table_dict
if column_dict["operator"] ∉ ["=","<>","!=",">","<",">=","<=","!<","!>","<=>"]
vector_search_words = vector_search_words * column_dict["value"] * ", "
delete!(table_dict, column_name)
hard_operators = ["=","<>","!=",">","<",">=","<=","!<","!>","<=>"]
# remove table from responsedict if there is no column to used
if length(responsedict[table_name]) == 0
delete!(responsedict, table_name)
end
end
# Build new list of hard condition entries
hard_conditions = JSON.Object{String, Any}[]
vector_search = JSON.Object{String, Any}[]
for entry in responsedict["extracted_info"]
if entry["operator"] ∈ hard_operators
push!(hard_conditions, entry)
else
push!(vector_search, entry)
end
end
responsedict = hard_conditions
println("")
pprintln(responsedict)
@show responsedict
@info "predefined_wine_search_sql() " @__LINE__
#WORKING do vector searched
println("")
@show vector_search_words
sql = predefined_wine_search_sql(responsedict)
return sql
return (hard_conditions=hard_conditions, vector_search=vector_search)
end
error("SQLLLM DecisionMaker() failed to generate a thought \n", response)
end
function predefined_wine_search_sql(conditions::Vector{JSON.Object{String, Any}})::String
# 1. Base SQL structure
base_query =
"""
SELECT
w.winery,
w.wine_name,
w.wine_id,
w.vintage,
w.region,
w.country,
w.wine_type,
w.grape,
w.serving_temperature,
w.sweetness,
w.intensity,
w.tannin,
w.acidity,
w.tasting_notes,
rw.price,
rw.currency,
w.image_url,
r.retailer_name,
rw.retailer_id
FROM wine AS w
JOIN retailer_wine AS rw ON w.wine_id = rw.wine_id
JOIN retailer AS r ON rw.retailer_id = r.retailer_id
"""
# 2. Dynamic WHERE Clause Builder
where_clauses = String[]
# Iterate over each condition object in the array
for cond in conditions
table_name = String(cond["table_name"])
column_name = String(cond["column_name"])
op = String(cond["operator"])
raw_val = cond["value"]
# Determine table alias
alias = if table_name == "wine"
"w"
elseif table_name == "retailer_wine"
"rw"
else
continue
end
# --- Value Type Handling ---
final_val = raw_val
if op in ("=", "<", ">", "<=", ">=")
str_val = string(raw_val)
num_val = tryparse(Float64, str_val)
if !isnothing(num_val)
final_val = isinteger(num_val) ? round(Int, num_val) : num_val
end
end
# --- SQL Formatting ---
if isa(final_val, Number)
clause = "$(alias).$(column_name) $(op) $(final_val)"
else
escaped_val = replace(string(final_val), "'" => "''")
clause = "$(alias).$(column_name) $(op) '$(escaped_val)'"
end
push!(where_clauses, clause)
end
# 3. Assemble Final Query
where_sql = isempty(where_clauses) ? "" : "WHERE " * join(where_clauses, " AND ")
return string(base_query, where_sql, ";")
end
function SQLexecution(executeSQL::Function, sql::T
)::NamedTuple where {T<:AbstractString}
@@ -1286,92 +1418,7 @@ function extractWineAttributes_2(a::T1, input::T2)::String where {T1<:agent, T2<
error("extractWineAttributes_2() failed to get a response")
end
function predefined_wine_search_sql(conditions::Dict{String, Any})::String
# 1. Base SQL structure
base_query =
"""
SELECT
w.winery,
w.wine_name,
w.wine_id,
w.vintage,
w.region,
w.country,
w.wine_type,
w.grape,
w.serving_temperature,
w.sweetness,
w.intensity,
w.tannin,
w.acidity,
w.tasting_notes,
rw.price,
rw.currency,
w.image_url,
r.retailer_name,
rw.retailer_id
FROM wine AS w
JOIN retailer_wine AS rw ON w.wine_id = rw.wine_id
JOIN retailer AS r ON rw.retailer_id = r.retailer_id
"""
# 2. Dynamic WHERE Clause Builder
where_clauses = String[]
# Iterate over each table condition provided
for (table_name, table_conditions) in conditions
# Determine table alias
alias = if table_name == "wine"
"w"
elseif table_name == "retailer_wine"
"rw"
else
continue # Skip unsupported tables
end
# Process condition dictionaries
if isa(table_conditions, Dict) && !isempty(table_conditions)
for (column_name, filter_details) in table_conditions
if isa(filter_details, Dict) && haskey(filter_details, "operator")
op = filter_details["operator"]
raw_val = filter_details["value"]
# --- Value Type Handling ---
# Use tryparse instead of try/catch for cleaner, faster parsing
final_val = raw_val
if op in ("=", "<", ">", "<=", ">=")
str_val = string(raw_val)
num_val = tryparse(Float64, str_val)
if !isnothing(num_val)
final_val = isinteger(num_val) ? round(Int, num_val) : num_val
end
end
# --- SQL Formatting ---
if isa(final_val, Number)
clause = "$(alias).$(column_name) $(op) $(final_val)"
else
# Escape single quotes within string values
escaped_val = replace(string(final_val), "'" => "''")
clause = "$(alias).$(column_name) $(op) '$(escaped_val)'"
end
push!(where_clauses, clause)
end
end
end
end
# 3. Assemble Final Query
where_sql = isempty(where_clauses) ? "" : "WHERE " * join(where_clauses, " AND ")
return string(base_query, where_sql, ";")
end
@@ -1467,13 +1514,6 @@ end
function classify_column(pg_conn_str::String, table_name::String, column_name::String;
sample_size::Integer=1000)
conn = LibPQ.Connection(pg_conn_str)
@@ -1575,44 +1615,28 @@ end
function harvest_entity_catalog(pg_conn_str::String, table::String, column::String)
conn = LibPQ.Connection(pg_conn_str)
return harvest_entity_catalog(conn, table, column)
end
function harvest_entity_catalog_with_pg_type(conn::LibPQ.Connection, table::String, column::String)
try
# 1. Query the actual data
data_query = "SELECT DISTINCT $(column) FROM $(table) WHERE $(column) IS NOT NULL;"
df = DataFrame(LibPQ.execute(conn, data_query))
values = String.(strip.(string.(df[!, 1])))
# 2. Query the database schema for the column's data type
# Note: Postgres stores unquoted table/column names in lowercase
type_query = """
SELECT data_type
FROM information_schema.columns
WHERE table_name = lower('$(table)')
AND column_name = lower('$(column)');
"""
type_df = DataFrame(LibPQ.execute(conn, type_query))
pg_type = isempty(type_df) ? "unknown" : type_df[1, 1]
return (values = values, type = pg_type)
catch e
@error "Failed to harvest catalog" exception=e
return (values = String[], type = "unknown")
finally
close(conn)
end
end
# Usage:
# result = harvest_entity_catalog_with_pg_type(conn, "users", "created_at")
# println(result.values) # ["2023-01-01", "2023-02-15"]
# println(result.type) # "timestamp without time zone"
src/type.jl
+1 -7
View File
@@ -164,7 +164,6 @@ function sommelier(
- You can only recommend wines that are currently in our inventory
- Before searching the database for wine, ensure you have at least the following information: 1) budget, 2) wine type, and 3) occasion. Additional details are always helpful. If the user is unsure, provide relevant information and gather insights to make reasonable inferences.
- Ask the user one question at a time.
- Do not ask the user about wine's flavor e.g. floral, citrusy, nutty or some thing similar as these terms cannot be used to search the database.
- Once the user has selected their wine, if you haven't already, ask the user whether they need any further assistance. Do not offer any additional services.
- Only end the conversation when the user explicitly intends to do so. When ending, ensure a polite farewell and an invitation to return in the future.
- Spicy foods should be paired only with light red wines.
@@ -200,17 +199,12 @@ function sommelier(
- Processing sales orders or engaging in any other sales-related activities. These are the job of our sales team at the store.
- Answering questions or offering additional services beyond those related to your store's wine recommendations such as discounts, quantity, rewards programs, promotions, delivery options, shipping, boxes, gift wrapping, packaging, personalized messages or something similar. These are the job of our sales team at the store.
# you should then respond to the user with interleaving plan, action_name, action_input
# you should then respond to the user with interleaving plan, action_name, action_input in JSON format
1) "plan", Based on the current situation, state a complete action plan to complete the task and rationale. Be specific.
2) "action_name", (Typically corresponds to the execution of the first step in your plan) Can be one of the available_actions name
3) "action_input", The input to the action you are about to perform according to your plan.
After the action is executed you gets "action_result". It is the output from the action you selected.
# you should only respond in YAML format as described below
plan: "..."
action_name: "..."
action_input: "..."
# available actions
"CHAT_BOX", which you can use to talk with the user. The input is dialogue you want to chat with the user according to your plan.
"SEARCH_WINE_DATABASE", allows you to search information about wines you want in your inventory's database. The input is strictly supported search term including: retailer_name, wine price, winery, name, vintage, region, country, type of wine, grape varietal, tasting notes, occasion, food pairing, intensity, tannin, sweetness, and acidity.