Add llama.cpp setup profile

2026-05-02 13:59:15 +10:00
parent 7dcdafcf67
commit 0481435ca6
6 changed files with 143 additions and 19 deletions
@@ -11,6 +11,7 @@ OPENAI_API_KEY=
 #
 #   npm run setup:local -- --profile openai
 #   npm run setup:local -- --profile qwen-local
+#   npm run setup:local -- --profile llama-cpp
 #
 # OpenAI profile:
 # LLM_PROFILE=openai
@@ -30,6 +31,15 @@ OPENAI_API_KEY=
 # EMBEDDING_MODEL=qwen3-embedding:0.6b
 # EMBEDDING_DIMENSIONS=1024
 #
+# Example llama.cpp:
+# LLM_PROFILE=openai-compatible
+# LLM_BASE_URL=http://127.0.0.1:8080/v1
+# LLM_MODEL=qwen3-4b
+# EMBEDDING_PROFILE=openai-compatible
+# EMBEDDING_BASE_URL=http://127.0.0.1:8081/v1
+# EMBEDDING_MODEL=qwen3-embedding-0.6b
+# EMBEDDING_DIMENSIONS=1024
+#
 # Example Qdrant sidecar, only needed when sqlite-vec is unavailable or unreliable:
 # VECTOR_BACKEND=qdrant
 # QDRANT_URL=http://localhost:6333