docs: fix LlamaIndex and llama.h documentation links

Point the LlamaIndex example at the current llama_cpp page, and point llama.h at include/llama.h in ggml-org/llama.cpp.

Author: cloudgpuapp

CHANGELOG.md

@@ -7,6 +7,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+- docs: fix LlamaIndex and llama.h documentation links by @mrhy7176
 - fix(ci): use supported Python versions on Ubuntu by @abetlen in #2407
 - feat: update llama.cpp to ggml-org/llama.cpp@7d7f02875
 

README.md

@@ -19,7 +19,7 @@ This package provides:
 - High-level Python API for text completion
     - OpenAI-like API
     - [LangChain compatibility](https://python.langchain.com/docs/integrations/llms/llamacpp)
-    - [LlamaIndex compatibility](https://docs.llamaindex.ai/en/stable/examples/llm/llama_2_llama_cpp.html)
+    - [LlamaIndex compatibility](https://docs.llamaindex.ai/en/stable/examples/llm/llama_cpp/)
 - OpenAI compatible web server
     - [Local Copilot replacement](https://llama-cpp-python.readthedocs.io/en/latest/server/#code-completion)
     - [Function Calling support](https://llama-cpp-python.readthedocs.io/en/latest/server/#function-calling)
@@ -745,7 +745,7 @@ docker run --rm -it -p 8000:8000 -v /path/to/models:/models -e MODEL=/models/lla
 [API Reference](https://llama-cpp-python.readthedocs.io/en/latest/api-reference/#low-level-api)
 
 The low-level API is a direct [`ctypes`](https://docs.python.org/3/library/ctypes.html) binding to the C API provided by `llama.cpp`.
-The entire low-level API can be found in [llama_cpp/llama_cpp.py](https://github.com/abetlen/llama-cpp-python/blob/master/llama_cpp/llama_cpp.py) and directly mirrors the C API in [llama.h](https://github.com/ggerganov/llama.cpp/blob/master/llama.h).
+The entire low-level API can be found in [llama_cpp/llama_cpp.py](https://github.com/abetlen/llama-cpp-python/blob/master/llama_cpp/llama_cpp.py) and directly mirrors the C API in [llama.h](https://github.com/ggml-org/llama.cpp/blob/master/include/llama.h).
 
 Below is a short example demonstrating how to use the low-level API to tokenize a prompt: