LlamaIndex: This and that. Naming things.

Author: amotl

topic/machine-learning/llama-index/README.md

@@ -92,7 +92,7 @@ Save your changes.
 Run the code like so:
 
 ```bash
-python main.py
+python demo_nlsql.py
 ```
 
 Here's the expected output:

topic/machine-learning/llama-index/main.py renamed to topic/machine-learning/llama-index/boot.py

@@ -1,21 +1,12 @@
-"""
-Use an LLM to query a database in human language.
-Example code using LlamaIndex with vanilla Open AI and Azure Open AI.
-"""
-
 import os
-import openai
-import sqlalchemy as sa
 
-from dotenv import load_dotenv
+import openai
 from langchain_openai import AzureOpenAIEmbeddings
 from langchain_openai import OpenAIEmbeddings
+from llama_index.core import Settings
 from llama_index.llms.azure_openai import AzureOpenAI
 from llama_index.llms.openai import OpenAI
 from llama_index.embeddings.langchain import LangchainEmbedding
-from llama_index.core.utilities.sql_wrapper import SQLDatabase
-from llama_index.core.query_engine import NLSQLTableQueryEngine
-from llama_index.core import Settings
 
 
 def configure_llm():
@@ -54,39 +45,3 @@ def configure_llm():
                 model=os.getenv("EMBEDDING_MODEL_INSTANCE")
             )
         )
-
-
-def main():
-    """
-    Use an LLM to query a database in human language.
-    """
-
-    # Configure application.
-    load_dotenv()
-    configure_llm()
-
-    # Configure database connection and query engine.
-    print("Connecting to CrateDB")
-    engine_crate = sa.create_engine(os.getenv("CRATEDB_SQLALCHEMY_URL"))
-    engine_crate.connect()
-
-    print("Creating LlamaIndex QueryEngine")
-    sql_database = SQLDatabase(engine_crate, include_tables=[os.getenv("CRATEDB_TABLE_NAME")])
-    query_engine = NLSQLTableQueryEngine(
-        sql_database=sql_database,
-        tables=[os.getenv("CRATEDB_TABLE_NAME")],
-        llm=Settings.llm
-    )
-
-    # Invoke an inquiry.
-    print("Running query")
-    QUERY_STR = "What is the average value for sensor 1?"
-    answer = query_engine.query(QUERY_STR)
-    print(answer.get_formatted_sources())
-    print("Query was:", QUERY_STR)
-    print("Answer was:", answer)
-    print(answer.metadata)
-
-
-if __name__ == "__main__":
-    main()

topic/machine-learning/llama-index/demo_nlsql.py

@@ -0,0 +1,50 @@
+"""
+Use an LLM to query a database in human language.
+Example code using LlamaIndex with vanilla Open AI and Azure Open AI.
+"""
+
+import os
+import sqlalchemy as sa
+
+from dotenv import load_dotenv
+from llama_index.core.utilities.sql_wrapper import SQLDatabase
+from llama_index.core.query_engine import NLSQLTableQueryEngine
+from llama_index.core import Settings
+
+from boot import configure_llm
+
+
+def main():
+    """
+    Use an LLM to query a database in human language.
+    """
+
+    # Configure application.
+    load_dotenv()
+    configure_llm()
+
+    # Configure database connection and query engine.
+    print("Connecting to CrateDB")
+    engine_crate = sa.create_engine(os.getenv("CRATEDB_SQLALCHEMY_URL"))
+    engine_crate.connect()
+
+    print("Creating LlamaIndex QueryEngine")
+    sql_database = SQLDatabase(engine_crate, include_tables=[os.getenv("CRATEDB_TABLE_NAME")])
+    query_engine = NLSQLTableQueryEngine(
+        sql_database=sql_database,
+        tables=[os.getenv("CRATEDB_TABLE_NAME")],
+        llm=Settings.llm
+    )
+
+    # Invoke an inquiry.
+    print("Running query")
+    QUERY_STR = "What is the average value for sensor 1?"
+    answer = query_engine.query(QUERY_STR)
+    print(answer.get_formatted_sources())
+    print("Query was:", QUERY_STR)
+    print("Answer was:", answer)
+    print(answer.metadata)
+
+
+if __name__ == "__main__":
+    main()

topic/machine-learning/llama-index/env.azure

@@ -1,8 +1,8 @@
-OPENAI_API_KEY=TODO
-OPENAI_API_TYPE=azure
-OPENAI_AZURE_ENDPOINT=https://TODO.openai.azure.com
-OPENAI_AZURE_API_VERSION=2024-08-01-preview
-LLM_INSTANCE=TODO
-EMBEDDING_MODEL_INSTANCE=TODO
-CRATEDB_SQLALCHEMY_URL="crate://USER:PASSWORD@HOST:4200/?ssl=true"
-CRATEDB_TABLE_NAME=time_series_data
+export OPENAI_API_KEY=TODO
+export OPENAI_API_TYPE=azure
+export OPENAI_AZURE_ENDPOINT=https://TODO.openai.azure.com
+export OPENAI_AZURE_API_VERSION=2024-08-01-preview
+export LLM_INSTANCE=TODO
+export EMBEDDING_MODEL_INSTANCE=TODO
+export CRATEDB_SQLALCHEMY_URL="crate://USER:PASSWORD@HOST:4200/?ssl=true"
+export CRATEDB_TABLE_NAME=time_series_data

topic/machine-learning/llama-index/env.standalone

@@ -1,4 +1,4 @@
 # OPENAI_API_KEY=sk-XJZ7pfog5Gp8Kus8D--invalid--0CJ5lyAKSefZLaV1Y9S1
-OPENAI_API_TYPE=openai
-CRATEDB_SQLALCHEMY_URL="crate://crate@localhost:4200/"
-CRATEDB_TABLE_NAME=time_series_data
+export OPENAI_API_TYPE=openai
+export CRATEDB_SQLALCHEMY_URL="crate://crate@localhost:4200/"
+export CRATEDB_TABLE_NAME=time_series_data

topic/machine-learning/llama-index/test.py

@@ -22,17 +22,17 @@ def init_database(cratedb):
     cratedb.run_sql((HERE / "init.sql").read_text())
 
 
-def test_main(cratedb, capsys):
+def test_nlsql(cratedb, capsys):
     """
-    Execute `main.py` and verify outcome.
+    Execute `demo_nlsql.py` and verify outcome.
     """
 
     # Load the standalone configuration also for software testing.
     # On CI, `OPENAI_API_KEY` will need to be supplied externally.
     load_dotenv("env.standalone")
 
     # Invoke the workload, in-process.
-    from main import main
+    from demo_nlsql import main
     main()
 
     # Verify the outcome.