Add support to llama as llm

poetry.lock

@@ -1,4 +1,4 @@
-# This file is automatically @generated by Poetry 1.4.0 and should not be changed by hand.
+# This file is automatically @generated by Poetry 1.4.2 and should not be changed by hand.
 
 [[package]]
 name = "aiohttp"
@@ -1274,6 +1274,20 @@ llms = ["anthropic (>=0.2.4,<0.3.0)", "cohere (>=3,<4)", "huggingface_hub (>=0,<
 openai = ["openai (>=0,<1)"]
 qdrant = ["qdrant-client (>=1.1.1,<2.0.0)"]
 
+[[package]]
+name = "llama-cpp-python"
+version = "0.1.23"
+description = "A Python wrapper for llama.cpp"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "llama_cpp_python-0.1.23.tar.gz", hash = "sha256:323a937e68e04251b5ad1804922e05d15c8b6bfbcf7c3e683a7b39a20e165ebf"},
+]
+
+[package.dependencies]
+typing-extensions = ">=4.5.0,<5.0.0"
+
 [[package]]
 name = "markdown-it-py"
 version = "2.2.0"
@@ -2763,4 +2777,4 @@ testing = ["big-O", "flake8 (<5)", "jaraco.functools", "jaraco.itertools", "more
 [metadata]
 lock-version = "2.0"
 python-versions = "^3.9"
-content-hash = "70e86f7d3b5caed792e37ccf9e11ed95008e5078dd8830e4f8b96cc1d35c7b60"
+content-hash = "a5f1a33bedd704cea56a6c8d3d97c8d8daad4b78f47765cca068f88face28647"