Add support for GitHub models

.devcontainer/devcontainer.json

@@ -1,7 +1,7 @@
 // For format details, see https://aka.ms/devcontainer.json. For config options, see the README at:
 // https://github.com/microsoft/vscode-dev-containers/tree/v0.245.0/containers/python-3
 {
-    "name": "Python 3",
+    "name": "python-openai-demos (Azure OpenAI)",
     "image": "mcr.microsoft.com/devcontainers/python:3.11-bullseye",
 
     "features": {
@@ -14,10 +14,7 @@
         "vscode": {
             // Set *default* container specific settings.json values on container create.
             "settings": {
-                "python.defaultInterpreterPath": "/usr/local/bin/python",
-                "files.exclude": {
-                    "__pycache__": true
-                }
+                "python.defaultInterpreterPath": "/usr/local/bin/python"
             },
 
             // Add the IDs of extensions you want installed when the container is created.
@@ -29,9 +26,6 @@
         }
     },
 
-    // Use 'forwardPorts' to make a list of ports inside the container available locally.
-    // "forwardPorts": [],
-
     // Use 'postCreateCommand' to run commands after the container is created.
     "postCreateCommand": "pip3 install --user -r requirements-dev.txt",
 

.devcontainer/github/devcontainer.json

@@ -0,0 +1,31 @@
+// For format details, see https://aka.ms/devcontainer.json. For config options, see the README at:
+// https://github.com/microsoft/vscode-dev-containers/tree/v0.245.0/containers/python-3
+{
+    "name": "python-openai-demos (GitHub models)",
+    "image": "mcr.microsoft.com/devcontainers/python:3.11-bullseye",
+    "features": {
+    },
+    // Configure tool-specific properties.
+    "customizations": {
+        // Configure properties specific to VS Code.
+        "vscode": {
+            // Set *default* container specific settings.json values on container create.
+            "settings": {
+                "python.defaultInterpreterPath": "/usr/local/bin/python"
+            },
+
+            // Add the IDs of extensions you want installed when the container is created.
+            "extensions": [
+                "ms-python.python",
+                "charliermarsh.ruff",
+                "ms-python.black-formatter"
+            ]
+        }
+    },
+
+    // Use 'postCreateCommand' to run commands after the container is created.
+    "postCreateCommand": "pip3 install --user -r requirements-dev.txt && cp .env.sample.github .env",
+
+    // Comment out to connect as root instead. More info: https://aka.ms/vscode-remote/containers/non-root.
+    "remoteUser": "vscode"
+}

.devcontainer/ollama/devcontainer.json

@@ -0,0 +1,32 @@
+// For format details, see https://aka.ms/devcontainer.json. For config options, see the README at:
+// https://github.com/microsoft/vscode-dev-containers/tree/v0.245.0/containers/python-3
+{
+    "name": "python-openai-demos (Ollama)",
+    "image": "mcr.microsoft.com/devcontainers/python:3.11-bullseye",
+    "features": {
+        "ghcr.io/prulloac/devcontainer-features/ollama:1": {}
+    },
+    // Configure tool-specific properties.
+    "customizations": {
+        // Configure properties specific to VS Code.
+        "vscode": {
+            // Set *default* container specific settings.json values on container create.
+            "settings": {
+                "python.defaultInterpreterPath": "/usr/local/bin/python"
+            },
+
+            // Add the IDs of extensions you want installed when the container is created.
+            "extensions": [
+                "ms-python.python",
+                "charliermarsh.ruff",
+                "ms-python.black-formatter"
+            ]
+        }
+    },
+
+    // Use 'postCreateCommand' to run commands after the container is created.
+    "postCreateCommand": "pip3 install --user -r requirements-dev.txt && cp .env.sample.ollama .env",
+
+    // Comment out to connect as root instead. More info: https://aka.ms/vscode-remote/containers/non-root.
+    "remoteUser": "vscode"
+}

.devcontainer/openai/devcontainer.json

@@ -0,0 +1,29 @@
+// For format details, see https://aka.ms/devcontainer.json. For config options, see the README at:
+// https://github.com/microsoft/vscode-dev-containers/tree/v0.245.0/containers/python-3
+{
+    "name": "python-openai-demos (Ollama)",
+    "image": "mcr.microsoft.com/devcontainers/python:3.11-bullseye",
+    // Configure tool-specific properties.
+    "customizations": {
+        // Configure properties specific to VS Code.
+        "vscode": {
+            // Set *default* container specific settings.json values on container create.
+            "settings": {
+                "python.defaultInterpreterPath": "/usr/local/bin/python"
+            },
+
+            // Add the IDs of extensions you want installed when the container is created.
+            "extensions": [
+                "ms-python.python",
+                "charliermarsh.ruff",
+                "ms-python.black-formatter"
+            ]
+        }
+    },
+
+    // Use 'postCreateCommand' to run commands after the container is created.
+    "postCreateCommand": "pip3 install --user -r requirements-dev.txt && cp .env.sample.openai .env",
+
+    // Comment out to connect as root instead. More info: https://aka.ms/vscode-remote/containers/non-root.
+    "remoteUser": "vscode"
+}

.env.sample

@@ -1,12 +1,14 @@
-# API_HOST can be either azure, ollama, or openai:
+# API_HOST can be either azure, ollama, openai, or github:
 API_HOST=azure
 # Needed for Azure:
 AZURE_OPENAI_ENDPOINT=https://YOUR-AZURE-OPENAI-SERVICE-NAME.openai.azure.com
 AZURE_OPENAI_DEPLOYMENT=YOUR-AZURE-DEPLOYMENT-NAME
 AZURE_OPENAI_VERSION=2024-03-01-preview
 # Needed for Ollama:
 OLLAMA_ENDPOINT=http://localhost:11434/v1
-OLLAMA_MODEL=llama2
+OLLAMA_MODEL=llama3.1
 # Needed for OpenAI.com:
 OPENAI_KEY=YOUR-OPENAI-KEY
 OPENAI_MODEL=gpt-3.5-turbo
+# Needed for GitHub models:
+GITHUB_MODEL=gpt-4o

.env.sample.azure

@@ -0,0 +1,5 @@
+# See .env.sample for all options
+API_HOST=azure
+AZURE_OPENAI_ENDPOINT=https://YOUR-AZURE-OPENAI-SERVICE-NAME.openai.azure.com
+AZURE_OPENAI_DEPLOYMENT=YOUR-AZURE-DEPLOYMENT-NAME
+AZURE_OPENAI_VERSION=2024-03-01-preview

.env.sample.github

@@ -0,0 +1,3 @@
+# See .env.sample for all options
+API_HOST=github
+GITHUB_MODEL=gpt-4o

.env.sample.ollama

@@ -0,0 +1,4 @@
+# See .env.sample for all options
+API_HOST=ollama
+OLLAMA_ENDPOINT=http://localhost:11434/v1
+OLLAMA_MODEL=llama3.1

.env.sample.openai

@@ -0,0 +1,4 @@
+# See .env.sample for all options
+API_HOST=openai
+OPENAI_KEY=YOUR-OPENAI-KEY
+OPENAI_MODEL=gpt-3.5-turbo

.vscode/settings.json

@@ -0,0 +1,5 @@
+{
+    "files.exclude": {
+        "__pycache__": true
+    }
+}

chat.py

@@ -9,6 +9,7 @@
 API_HOST = os.getenv("API_HOST")
 
 if API_HOST == "azure":
+
     token_provider = azure.identity.get_bearer_token_provider(
         azure.identity.DefaultAzureCredential(), "https://cognitiveservices.azure.com/.default"
     )
@@ -18,13 +19,22 @@
         azure_ad_token_provider=token_provider,
     )
     MODEL_NAME = os.getenv("AZURE_OPENAI_DEPLOYMENT")
+
 elif API_HOST == "ollama":
+
     client = openai.OpenAI(
         base_url=os.getenv("OLLAMA_ENDPOINT"),
         api_key="nokeyneeded",
     )
     MODEL_NAME = os.getenv("OLLAMA_MODEL")
+
+elif API_HOST == "github":
+
+    client = openai.OpenAI(base_url="https://models.inference.ai.azure.com", api_key=os.getenv("GITHUB_TOKEN"))
+    MODEL_NAME = os.getenv("GITHUB_MODEL")
+
 else:
+
     client = openai.OpenAI(api_key=os.getenv("OPENAI_KEY"))
     MODEL_NAME = os.getenv("OPENAI_MODEL")
 

chat_async.py

@@ -21,10 +21,13 @@
     MODEL_NAME = os.getenv("AZURE_OPENAI_DEPLOYMENT")
 elif API_HOST == "ollama":
     client = openai.AsyncOpenAI(
-        base_url="http://localhost:11434/v1",
+        base_url=os.getenv("OLLAMA_ENDPOINT"),
         api_key="nokeyneeded",
     )
     MODEL_NAME = os.getenv("OLLAMA_MODEL")
+elif API_HOST == "github":
+    client = openai.AsyncOpenAI(base_url="https://models.inference.ai.azure.com", api_key=os.getenv("GITHUB_TOKEN"))
+    MODEL_NAME = os.getenv("GITHUB_MODEL")
 else:
     client = openai.AsyncOpenAI(api_key=os.getenv("OPENAI_KEY"))
     MODEL_NAME = os.getenv("OPENAI_MODEL")

chat_history.py

@@ -20,10 +20,13 @@
     MODEL_NAME = os.getenv("AZURE_OPENAI_DEPLOYMENT")
 elif API_HOST == "ollama":
     client = openai.OpenAI(
-        base_url="http://localhost:11434/v1",
+        base_url=os.getenv("OLLAMA_ENDPOINT"),
         api_key="nokeyneeded",
     )
     MODEL_NAME = os.getenv("OLLAMA_MODEL")
+elif API_HOST == "github":
+    client = openai.OpenAI(base_url="https://models.inference.ai.azure.com", api_key=os.getenv("GITHUB_TOKEN"))
+    MODEL_NAME = os.getenv("GITHUB_MODEL")
 else:
     client = openai.OpenAI(api_key=os.getenv("OPENAI_KEY"))
     MODEL_NAME = os.getenv("OPENAI_MODEL")

chat_history_stream.py

@@ -20,10 +20,13 @@
     MODEL_NAME = os.getenv("AZURE_OPENAI_DEPLOYMENT")
 elif API_HOST == "ollama":
     client = openai.OpenAI(
-        base_url="http://localhost:11434/v1",
+        base_url=os.getenv("OLLAMA_ENDPOINT"),
         api_key="nokeyneeded",
     )
     MODEL_NAME = os.getenv("OLLAMA_MODEL")
+elif API_HOST == "github":
+    client = openai.OpenAI(base_url="https://models.inference.ai.azure.com", api_key=os.getenv("GITHUB_TOKEN"))
+    MODEL_NAME = os.getenv("GITHUB_MODEL")
 else:
     client = openai.OpenAI(api_key=os.getenv("OPENAI_KEY"))
     MODEL_NAME = os.getenv("OPENAI_MODEL")

chat_langchain.py

@@ -25,6 +25,12 @@
         openai_api_base=os.getenv("OLLAMA_ENDPOINT"),
         openai_api_key=os.getenv("OPENAI_KEY"),
     )
+elif API_HOST == "github":
+    llm = ChatOpenAI(
+        model_name=os.getenv("GITHUB_MODEL"),
+        openai_api_base="https://models.inference.ai.azure.com",
+        openai_api_key=os.getenv("GITHUB_TOKEN"),
+    )
 else:
     llm = ChatOpenAI(model_name=os.getenv("OPENAI_MODEL"), openai_api_key=os.getenv("OPENAI_KEY"))
 

chat_llamaindex.py

@@ -27,6 +27,13 @@
     llm = OpenAILike(
         model=os.getenv("OLLAMA_MODEL"), api_base=os.getenv("OLLAMA_ENDPOINT"), api_key="fake", is_chat_model=True
     )
+elif API_HOST == "github":
+    llm = OpenAILike(
+        model=os.getenv("GITHUB_MODEL"),
+        api_base="https://models.inference.ai.azure.com",
+        api_key=os.getenv("GITHUB_TOKEN"),
+        is_chat_model=True,
+    )
 else:
     llm = OpenAI(model=os.getenv("OPENAI_MODEL"), api_key=os.getenv("OPENAI_KEY"))
 

chat_safety.py

@@ -20,10 +20,13 @@
     MODEL_NAME = os.getenv("AZURE_OPENAI_DEPLOYMENT")
 elif API_HOST == "ollama":
     client = openai.OpenAI(
-        base_url="http://localhost:11434/v1",
+        base_url=os.getenv("OLLAMA_ENDPOINT"),
         api_key="nokeyneeded",
     )
     MODEL_NAME = os.getenv("OLLAMA_MODEL")
+elif API_HOST == "github":
+    client = openai.OpenAI(base_url="https://models.inference.ai.azure.com", api_key=os.getenv("GITHUB_TOKEN"))
+    MODEL_NAME = os.getenv("GITHUB_MODEL")
 else:
     client = openai.OpenAI(api_key=os.getenv("OPENAI_KEY"))
     MODEL_NAME = os.getenv("OPENAI_MODEL")

chat_stream.py

@@ -24,6 +24,9 @@
         api_key="nokeyneeded",
     )
     MODEL_NAME = os.getenv("OLLAMA_MODEL")
+elif API_HOST == "github":
+    client = openai.OpenAI(base_url="https://models.inference.ai.azure.com", api_key=os.getenv("GITHUB_TOKEN"))
+    MODEL_NAME = os.getenv("GITHUB_MODEL")
 else:
     client = openai.OpenAI(api_key=os.getenv("OPENAI_KEY"))
     MODEL_NAME = os.getenv("OPENAI_MODEL")
@@ -45,4 +48,5 @@
 for event in completion:
     if event.choices:
         content = event.choices[0].delta.content
-        print(content, end="", flush=True)
+        if content:
+            print(content, end="", flush=True)