Feature add Add LlamaCppChatCompletionClient and llama-cpp

.github/workflows/checks.yml

@@ -197,7 +197,7 @@ jobs:
 
       - name: Install Python deps
         run: |
-          uv sync --locked --all-extras
+          uv sync --locked --all-extras --no-extra llama-cpp
         shell: pwsh
         working-directory: ./python
 

python/packages/autogen-core/docs/src/reference/index.md

@@ -54,6 +54,7 @@ python/autogen_ext.models.azure
 python/autogen_ext.models.anthropic
 python/autogen_ext.models.semantic_kernel
 python/autogen_ext.models.ollama
+python/autogen_ext.models.llama_cpp
 python/autogen_ext.tools.code_execution
 python/autogen_ext.tools.graphrag
 python/autogen_ext.tools.http

python/packages/autogen-core/docs/src/reference/python/autogen_ext.models.llama_cpp.rst

@@ -0,0 +1,9 @@
+autogen\_ext.models.llama\_cpp
+==============================
+
+
+.. automodule:: autogen_ext.models.llama_cpp
+   :members:
+   :undoc-members:
+   :show-inheritance:
+   :member-order: bysource

python/packages/autogen-ext/pyproject.toml

@@ -32,6 +32,11 @@ file-surfer = [
     "autogen-agentchat==0.4.8",
     "markitdown~=0.0.1",
 ]
+
+llama-cpp = [
+    "llama-cpp-python>=0.1.9",
+]
+
 graphrag = ["graphrag>=1.0.1"]
 chromadb = ["chromadb"]
 web-surfer = [

python/packages/autogen-ext/src/autogen_ext/models/llama_cpp/__init__.py

@@ -0,0 +1,10 @@
+try:
+    from ._llama_cpp_completion_client import LlamaCppChatCompletionClient
+except ImportError as e:
+    raise ImportError(
+        "Dependencies for Llama Cpp not found. "
+        "Please install llama-cpp-python: "
+        "pip install autogen-ext[llama-cpp]"
+    ) from e
+
+__all__ = ["LlamaCppChatCompletionClient"]