dearwolf/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-05-31 07:54:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 34

feat(llama.cpp): support embeddings endpoints (#2871)

Browse source 
* feat(llama.cpp): add embeddings

Also enable embeddings by default for llama.cpp models

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix(Makefile): prepare llama.cpp sources only once

Otherwise we keep cloning llama.cpp for each of the variants

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* do not set embeddings to false

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* docs: add embeddings to the YAML config reference

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2024-07-15 22:54:16 +02:00 • committed by GitHub
parent 6564e7ea01
commit 35561edb6e
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 44 additions and 12 deletions
Download patch file Download diff file Expand all files Collapse all files

20
Makefile
View file

@ -310,7 +310,7 @@ sources/whisper.cpp:
sources/whisper.cpp/libwhisper.a: sources/whisper.cpp
cd sources/whisper.cpp && $(MAKE) libwhisper.a libggml.a
get-sources: sources/go-llama.cpp sources/gpt4all sources/go-piper sources/go-rwkv.cpp sources/whisper.cpp sources/go-bert.cpp sources/go-stable-diffusion sources/go-tiny-dream
get-sources: sources/go-llama.cpp sources/gpt4all sources/go-piper sources/go-rwkv.cpp sources/whisper.cpp sources/go-bert.cpp sources/go-stable-diffusion sources/go-tiny-dream backend/cpp/llama/llama.cpp
replace:
$(GOCMD) mod edit -replace github.com/donomii/go-rwkv.cpp=$(CURDIR)/sources/go-rwkv.cpp
@ -767,28 +767,28 @@ else
endif
# This target is for manually building a variant with-auto detected flags
backend-assets/grpc/llama-cpp: backend-assets/grpc
backend-assets/grpc/llama-cpp: backend-assets/grpc backend/cpp/llama/llama.cpp
cp -rf backend/cpp/llama backend/cpp/llama-cpp
$(MAKE) -C backend/cpp/llama-cpp purge
$(info ${GREEN}I llama-cpp build info:avx2${RESET})
$(MAKE) VARIANT="llama-cpp" build-llama-cpp-grpc-server
cp -rfv backend/cpp/llama-cpp/grpc-server backend-assets/grpc/llama-cpp
backend-assets/grpc/llama-cpp-avx2: backend-assets/grpc
backend-assets/grpc/llama-cpp-avx2: backend-assets/grpc backend/cpp/llama/llama.cpp
cp -rf backend/cpp/llama backend/cpp/llama-avx2
$(MAKE) -C backend/cpp/llama-avx2 purge
$(info ${GREEN}I llama-cpp build info:avx2${RESET})
CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=on -DGGML_AVX2=on -DGGML_AVX512=off -DGGML_FMA=on -DGGML_F16C=on" $(MAKE) VARIANT="llama-avx2" build-llama-cpp-grpc-server
cp -rfv backend/cpp/llama-avx2/grpc-server backend-assets/grpc/llama-cpp-avx2
backend-assets/grpc/llama-cpp-avx: backend-assets/grpc
backend-assets/grpc/llama-cpp-avx: backend-assets/grpc backend/cpp/llama/llama.cpp
cp -rf backend/cpp/llama backend/cpp/llama-avx
$(MAKE) -C backend/cpp/llama-avx purge
$(info ${GREEN}I llama-cpp build info:avx${RESET})
CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=on -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off" $(MAKE) VARIANT="llama-avx" build-llama-cpp-grpc-server
cp -rfv backend/cpp/llama-avx/grpc-server backend-assets/grpc/llama-cpp-avx
backend-assets/grpc/llama-cpp-fallback: backend-assets/grpc
backend-assets/grpc/llama-cpp-fallback: backend-assets/grpc backend/cpp/llama/llama.cpp
cp -rf backend/cpp/llama backend/cpp/llama-fallback
$(MAKE) -C backend/cpp/llama-fallback purge
$(info ${GREEN}I llama-cpp build info:fallback${RESET})
@ -799,35 +799,35 @@ ifeq ($(BUILD_TYPE),metal)
cp backend/cpp/llama-fallback/llama.cpp/build/bin/default.metallib backend-assets/grpc/
endif
backend-assets/grpc/llama-cpp-cuda: backend-assets/grpc
backend-assets/grpc/llama-cpp-cuda: backend-assets/grpc backend/cpp/llama/llama.cpp
cp -rf backend/cpp/llama backend/cpp/llama-cuda
$(MAKE) -C backend/cpp/llama-cuda purge
$(info ${GREEN}I llama-cpp build info:cuda${RESET})
CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=on -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_CUDA=ON" $(MAKE) VARIANT="llama-cuda" build-llama-cpp-grpc-server
cp -rfv backend/cpp/llama-cuda/grpc-server backend-assets/grpc/llama-cpp-cuda
backend-assets/grpc/llama-cpp-hipblas: backend-assets/grpc
backend-assets/grpc/llama-cpp-hipblas: backend-assets/grpc backend/cpp/llama/llama.cpp
cp -rf backend/cpp/llama backend/cpp/llama-hipblas
$(MAKE) -C backend/cpp/llama-hipblas purge
$(info ${GREEN}I llama-cpp build info:hipblas${RESET})
BUILD_TYPE="hipblas" $(MAKE) VARIANT="llama-hipblas" build-llama-cpp-grpc-server
cp -rfv backend/cpp/llama-hipblas/grpc-server backend-assets/grpc/llama-cpp-hipblas
backend-assets/grpc/llama-cpp-sycl_f16: backend-assets/grpc
backend-assets/grpc/llama-cpp-sycl_f16: backend-assets/grpc backend/cpp/llama/llama.cpp
cp -rf backend/cpp/llama backend/cpp/llama-sycl_f16
$(MAKE) -C backend/cpp/llama-sycl_f16 purge
$(info ${GREEN}I llama-cpp build info:sycl_f16${RESET})
BUILD_TYPE="sycl_f16" $(MAKE) VARIANT="llama-sycl_f16" build-llama-cpp-grpc-server
cp -rfv backend/cpp/llama-sycl_f16/grpc-server backend-assets/grpc/llama-cpp-sycl_f16
backend-assets/grpc/llama-cpp-sycl_f32: backend-assets/grpc
backend-assets/grpc/llama-cpp-sycl_f32: backend-assets/grpc backend/cpp/llama/llama.cpp
cp -rf backend/cpp/llama backend/cpp/llama-sycl_f32
$(MAKE) -C backend/cpp/llama-sycl_f32 purge
$(info ${GREEN}I llama-cpp build info:sycl_f32${RESET})
BUILD_TYPE="sycl_f32" $(MAKE) VARIANT="llama-sycl_f32" build-llama-cpp-grpc-server
cp -rfv backend/cpp/llama-sycl_f32/grpc-server backend-assets/grpc/llama-cpp-sycl_f32
backend-assets/grpc/llama-cpp-grpc: backend-assets/grpc
backend-assets/grpc/llama-cpp-grpc: backend-assets/grpc backend/cpp/llama/llama.cpp
cp -rf backend/cpp/llama backend/cpp/llama-grpc
$(MAKE) -C backend/cpp/llama-grpc purge
$(info ${GREEN}I llama-cpp build info:grpc${RESET})