LlamaIndex: This and that. Naming things.

Author: amotl

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

@@ -0,0 +1,47 @@
+import os
+
+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
+
+
+def configure_llm():
+    """
+    Configure LLM. Use either vanilla Open AI, or Azure Open AI.
+    """
+
+    openai.api_type = os.getenv("OPENAI_API_TYPE")
+    openai.azure_endpoint = os.getenv("OPENAI_AZURE_ENDPOINT")
+    openai.api_version = os.getenv("OPENAI_AZURE_API_VERSION")
+    openai.api_key = os.getenv("OPENAI_API_KEY")
+
+    if openai.api_type == "openai":
+        llm = OpenAI(
+            api_key=os.getenv("OPENAI_API_KEY"),
+            temperature=0.0
+        )
+    elif openai.api_type == "azure":
+        llm = AzureOpenAI(
+            engine=os.getenv("LLM_INSTANCE"),
+            azure_endpoint=os.getenv("OPENAI_AZURE_ENDPOINT"),
+            api_key = os.getenv("OPENAI_API_KEY"),
+            api_version = os.getenv("OPENAI_AZURE_API_VERSION"),
+            temperature=0.0
+        )
+    else:
+        raise ValueError(f"Open AI API type not defined or invalid: {openai.api_type}")
+
+    Settings.llm = llm
+    if openai.api_type == "openai":
+        Settings.embed_model = LangchainEmbedding(OpenAIEmbeddings())
+    elif openai.api_type == "azure":
+        Settings.embed_model = LangchainEmbedding(
+            AzureOpenAIEmbeddings(
+                azure_endpoint=os.getenv("OPENAI_AZURE_ENDPOINT"),
+                model=os.getenv("EMBEDDING_MODEL_INSTANCE")
+            )
+        )

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

@@ -4,56 +4,14 @@
 """
 
 import os
-import openai
 import sqlalchemy as sa
 
 from dotenv import load_dotenv
-from langchain_openai import AzureOpenAIEmbeddings
-from langchain_openai import OpenAIEmbeddings
-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():
-    """
-    Configure LLM. Use either vanilla Open AI, or Azure Open AI.
-    """
-
-    openai.api_type = os.getenv("OPENAI_API_TYPE")
-    openai.azure_endpoint = os.getenv("OPENAI_AZURE_ENDPOINT")
-    openai.api_version = os.getenv("OPENAI_AZURE_API_VERSION")
-    openai.api_key = os.getenv("OPENAI_API_KEY")
-
-    if openai.api_type == "openai":
-        llm = OpenAI(
-            api_key=os.getenv("OPENAI_API_KEY"),
-            temperature=0.0
-        )
-    elif openai.api_type == "azure":
-        llm = AzureOpenAI(
-            engine=os.getenv("LLM_INSTANCE"),
-            azure_endpoint=os.getenv("OPENAI_AZURE_ENDPOINT"),
-            api_key = os.getenv("OPENAI_API_KEY"),
-            api_version = os.getenv("OPENAI_AZURE_API_VERSION"),
-            temperature=0.0
-        )
-    else:
-        raise ValueError(f"Open AI API type not defined or invalid: {openai.api_type}")
-
-    Settings.llm = llm
-    if openai.api_type == "openai":
-        Settings.embed_model = LangchainEmbedding(OpenAIEmbeddings())
-    elif openai.api_type == "azure":
-        Settings.embed_model = LangchainEmbedding(
-            AzureOpenAIEmbeddings(
-                azure_endpoint=os.getenv("OPENAI_AZURE_ENDPOINT"),
-                model=os.getenv("EMBEDDING_MODEL_INSTANCE")
-            )
-        )
+from boot import configure_llm
 
 
 def 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

@@ -22,7 +22,7 @@ def init_database(cratedb):
     cratedb.run_sql((HERE / "init.sql").read_text())
 
 
-def test_main(cratedb, capsys):
+def test_nlsql(cratedb, capsys):
     """
     Execute `demo_nlsql.py` and verify outcome.
     """