File size: 10,271 Bytes
c101c53 0614630 c101c53 c76addc c101c53 0614630 c76addc c101c53 0614630 c101c53 0614630 c76addc |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 |
from typing import List
from typing import AnyStr
from haystack import component
import pandas as pd
from pandasql import sqldf
pd.set_option('display.max_rows', None)
pd.set_option('display.max_columns', None)
pd.set_option('display.width', None)
pd.set_option('display.max_colwidth', None)
import sqlite3
import psycopg2
from pymongo import MongoClient
import pymongoarrow.monkey
import json
import pluck
from utils import TEMP_DIR
import ast
@component
class SQLiteQuery:
def __init__(self, sql_database: str):
self.connection = sqlite3.connect(sql_database, check_same_thread=False)
@component.output_types(results=List[str], queries=List[str])
def run(self, queries: List[str], session_hash):
print("ATTEMPTING TO RUN SQLITE QUERY")
dir_path = TEMP_DIR / str(session_hash)
results = []
for query in queries:
result = pd.read_sql(query, self.connection)
result.to_csv(f'{dir_path}/file_upload/query.csv', index=False)
results.append(f"{result}")
self.connection.close()
return {"results": results, "queries": queries}
def sqlite_query_func(queries: List[str], session_hash, **kwargs):
dir_path = TEMP_DIR / str(session_hash)
sql_query = SQLiteQuery(f'{dir_path}/file_upload/data_source.db')
try:
result = sql_query.run(queries, session_hash)
if len(result["results"][0]) > 1000:
print("QUERY TOO LARGE")
return {"reply": "query result too large to be processed by llm, the query results are in our query.csv file. If you need to display the results directly, perhaps use the table_generation_func function."}
else:
return {"reply": result["results"][0]}
except Exception as e:
reply = f"""There was an error running the SQL Query = {queries}
The error is {e},
You should probably try again.
"""
return {"reply": reply}
@component
class PostgreSQLQuery:
def __init__(self, url: str, sql_port: int, sql_user: str, sql_pass: str, sql_db_name: str):
self.connection = psycopg2.connect(
database=sql_db_name,
user=sql_user,
password=sql_pass,
host=url, # e.g., "localhost" or an IP address
port=sql_port # default is 5432
)
@component.output_types(results=List[str], queries=List[str])
def run(self, queries: List[str], session_hash):
print("ATTEMPTING TO RUN POSTGRESQL QUERY")
dir_path = TEMP_DIR / str(session_hash)
results = []
for query in queries:
print(query)
result = pd.read_sql_query(query, self.connection)
result.to_csv(f'{dir_path}/sql/query.csv', index=False)
results.append(f"{result}")
self.connection.close()
return {"results": results, "queries": queries}
def sql_query_func(queries: List[str], session_hash, db_url, db_port, db_user, db_pass, db_name, **kwargs):
sql_query = PostgreSQLQuery(db_url, db_port, db_user, db_pass, db_name)
try:
result = sql_query.run(queries, session_hash)
print("RESULT")
print(result)
if len(result["results"][0]) > 1000:
print("QUERY TOO LARGE")
return {"reply": "query result too large to be processed by llm, the query results are in our query.csv file. If you need to display the results directly, perhaps use the table_generation_func function."}
else:
return {"reply": result["results"][0]}
except Exception as e:
reply = f"""There was an error running the SQL Query = {queries}
The error is {e},
You should probably try again.
"""
print(reply)
return {"reply": reply}
@component
class DocDBQuery:
def __init__(self, connection_string: str, doc_db_name: str):
client = MongoClient(connection_string)
self.client = client
self.connection = client[doc_db_name]
@component.output_types(results=List[str], queries=List[str])
def run(self, aggregation_pipeline: List[str], db_collection, session_hash):
pymongoarrow.monkey.patch_all()
print("ATTEMPTING TO RUN MONGODB QUERY")
dir_path = TEMP_DIR / str(session_hash)
results = []
print(aggregation_pipeline)
aggregation_pipeline = aggregation_pipeline.replace(" ", "")
false_replace = [':false', ': false']
false_value = ':False'
true_replace = [':true', ': true']
true_value = ':True'
for replace in false_replace:
aggregation_pipeline = aggregation_pipeline.replace(replace, false_value)
for replace in true_replace:
aggregation_pipeline = aggregation_pipeline.replace(replace, true_value)
query_list = ast.literal_eval(aggregation_pipeline)
print("QUERY List")
print(query_list)
print(db_collection)
db = self.connection
collection = db[db_collection]
print(collection)
docs = collection.aggregate_pandas_all(query_list)
print("DATA FRAME COMPLETE")
docs.to_csv(f'{dir_path}/doc_db/query.csv', index=False)
print("CSV COMPLETE")
results.append(f"{docs}")
self.client.close()
return {"results": results, "queries": aggregation_pipeline}
def doc_db_query_func(aggregation_pipeline: List[str], db_collection: AnyStr, session_hash, connection_string, doc_db_name, **kwargs):
doc_db_query = DocDBQuery(connection_string, doc_db_name)
try:
result = doc_db_query.run(aggregation_pipeline, db_collection, session_hash)
print("RESULT")
if len(result["results"][0]) > 1000:
print("QUERY TOO LARGE")
return {"reply": "query result too large to be processed by llm, the query results are in our query.csv file. If you need to display the results directly, perhaps use the table_generation_func function."}
else:
return {"reply": result["results"][0]}
except Exception as e:
reply = f"""There was an error running the NoSQL (Mongo) Query = {aggregation_pipeline}
The error is {e},
You should probably try again.
"""
print(reply)
return {"reply": reply}
@component
class GraphQLQuery:
def __init__(self):
self.connection = pluck
@component.output_types(results=List[str], queries=List[str])
def run(self, graphql_query, graphql_api_string, graphql_api_token, graphql_token_header, session_hash):
print("ATTEMPTING TO RUN GRAPHQL QUERY")
dir_path = TEMP_DIR / str(session_hash)
results = []
headers = {"Content-Type": "application/json"}
if graphql_token_header and graphql_api_token:
headers[graphql_token_header] = graphql_api_token
print(graphql_query)
response = self.connection.execute(url=graphql_api_string, headers=headers, query=graphql_query, column_names="short")
if response.errors:
raise ValueError(response.errors)
elif response.data:
print("DATA FRAME COMPLETE")
print(response)
response_frame = response.frames['default']
print("RESPONSE FRAME")
#print(response_frame)
response_frame.to_csv(f'{dir_path}/graphql/query.csv', index=False)
print("CSV COMPLETE")
results.append(f"{response_frame}")
return {"results": results, "queries": graphql_query}
def graphql_query_func(graphql_query: AnyStr, session_hash, graphql_api_string, graphql_api_token, graphql_token_header, **kwargs):
graphql_object = GraphQLQuery()
try:
result = graphql_object.run(graphql_query, graphql_api_string, graphql_api_token, graphql_token_header, session_hash)
print("RESULT")
if len(result["results"][0]) > 1000:
print("QUERY TOO LARGE")
return {"reply": "query result too large to be processed by llm, the query results are in our query.csv file. If you need to display the results directly, perhaps use the table_generation_func function."}
else:
return {"reply": result["results"][0]}
except Exception as e:
reply = f"""There was an error running the GraphQL Query = {graphql_query}
The error is {e},
You should probably try again.
"""
print(reply)
return {"reply": reply}
def graphql_schema_query(graphql_type: AnyStr, session_hash, **kwargs):
dir_path = TEMP_DIR / str(session_hash)
try:
with open(f'{dir_path}/graphql/schema.json', 'r') as file:
data = json.load(file)
types_list = data["types"]
result = list(filter(lambda item: item["name"] == graphql_type, types_list))
print("SCHEMA RESULT")
print(graphql_type)
print(str(result))
return {"reply": str(result)}
except Exception as e:
reply = f"""There was an error querying our schema.json file with the type:{graphql_type}
The error is {e},
You should probably try again.
"""
print(reply)
return {"reply": reply}
def graphql_csv_query(csv_query: AnyStr, session_hash, **kwargs):
dir_path = TEMP_DIR / str(session_hash)
try:
query = pd.read_csv(f'{dir_path}/graphql/query.csv')
query.Name = 'query'
print("GRAPHQL CSV QUERY")
queried_df = sqldf(csv_query, locals())
print(queried_df)
queried_df.to_csv(f'{dir_path}/graphql/query.csv', index=False)
return {"reply": "The new query results are in our query.csv file. If you need to display the results directly, perhaps use the table_generation_func function."}
except Exception as e:
reply = f"""There was an error querying our query.csv file with the query:{csv_query}
The error is {e},
You should probably try again.
"""
print(reply)
return {"reply": reply} |