From 6386c2f8aa0a8ae28f0ac422b514a7ea9565773d Mon Sep 17 00:00:00 2001
From: localai-org-maint-bot
 <306269227+localai-org-maint-bot@users.noreply.github.com>
Date: Sun, 25 Oct 2026 09:52:09 +0000
Subject: [PATCH] feat(gallery): add BGE base English variants

Add F16, Q8_0 and Q4_K_M builds with CLS pooling and retrieval usage documentation. Pin the GGUF revision and verify SHA256 values against Hugging Face metadata and download headers.

Assisted-by: Codex:gpt-6

(cherry picked from commit e61c44f31760482ac4b7c275e24d022eec0c8545, mudler/LocalAI#12717)
Assisted-by: Claude:claude-sonnet-5-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---
 gallery/index.yaml        |  87 ++++++++++++++++++++++++++++++
 gallery/models/index.yaml | 111 ++++++++++++++++++++++++++++++++++++++
 2 files changed, 198 insertions(+)

diff --git a/gallery/index.yaml b/gallery/index.yaml
index 917613886..861aa0c0e 100644
--- a/gallery/index.yaml
+++ b/gallery/index.yaml
@@ -3,6 +3,93 @@
 # written by scripts/models/cmd/modelcatalog and stays only so releases before
 # the cutover keep working. CI fails when it differs from the generated copy:
 #   go run ./scripts/models/cmd/modelcatalog --library gallery/models/index.yaml --out gallery/index.yaml
+- url: github:mudler/LocalAI/gallery/virtual.yaml@master
+  name: bge-base-en-v1.5-f16
+  description: |
+    BGE-base-en-v1.5 is a 109M English embedding model for semantic search
+    and retrieval. This F16 GGUF build produces 768-dimensional embeddings
+    with a 512-token context. For retrieval, prefix queries with
+    "Represent this sentence for searching relevant passages: "; leave passages unprefixed.
+  license: mit
+  urls:
+    - https://huggingface.co/BAAI/bge-base-en-v1.5
+    - https://huggingface.co/CompendiumLabs/bge-base-en-v1.5-gguf
+  tags:
+    - embeddings
+    - gguf
+    - cpu
+    - gpu
+  files:
+    - filename: bge-base-en-v1.5-f16.gguf
+      sha256: 88360fdf8521af0ac08d43818bd272da679ab97c685d9b273c48efd01a4187c2
+      uri: https://huggingface.co/CompendiumLabs/bge-base-en-v1.5-gguf/resolve/24914efdfa9ee54e815c3fcaa78a617031251c5c/bge-base-en-v1.5-f16.gguf
+  overrides:
+    backend: llama-cpp
+    context_size: 512
+    embeddings: true
+    options:
+      - pooling:cls
+    parameters:
+      model: bge-base-en-v1.5-f16.gguf
+  variants:
+    - model: bge-base-en-v1.5-q8-0
+    - model: bge-base-en-v1.5-q4-k-m
+- url: github:mudler/LocalAI/gallery/virtual.yaml@master
+  name: bge-base-en-v1.5-q8-0
+  description: |
+    BGE-base-en-v1.5 is a 109M English embedding model for semantic search
+    and retrieval. This Q8_0 GGUF build produces 768-dimensional embeddings
+    with a 512-token context. For retrieval, prefix queries with
+    "Represent this sentence for searching relevant passages: "; leave passages unprefixed.
+  license: mit
+  urls:
+    - https://huggingface.co/BAAI/bge-base-en-v1.5
+    - https://huggingface.co/CompendiumLabs/bge-base-en-v1.5-gguf
+  tags:
+    - embeddings
+    - gguf
+    - cpu
+    - gpu
+  files:
+    - filename: bge-base-en-v1.5-q8_0.gguf
+      sha256: ad1afe72cd6654a558667a3db10878b049a75bfd72912e1dabb91310d671173c
+      uri: https://huggingface.co/CompendiumLabs/bge-base-en-v1.5-gguf/resolve/24914efdfa9ee54e815c3fcaa78a617031251c5c/bge-base-en-v1.5-q8_0.gguf
+  overrides:
+    backend: llama-cpp
+    context_size: 512
+    embeddings: true
+    options:
+      - pooling:cls
+    parameters:
+      model: bge-base-en-v1.5-q8_0.gguf
+- url: github:mudler/LocalAI/gallery/virtual.yaml@master
+  name: bge-base-en-v1.5-q4-k-m
+  description: |
+    BGE-base-en-v1.5 is a 109M English embedding model for semantic search
+    and retrieval. This Q4_K_M GGUF build produces 768-dimensional embeddings
+    with a 512-token context. For retrieval, prefix queries with
+    "Represent this sentence for searching relevant passages: "; leave passages unprefixed.
+  license: mit
+  urls:
+    - https://huggingface.co/BAAI/bge-base-en-v1.5
+    - https://huggingface.co/CompendiumLabs/bge-base-en-v1.5-gguf
+  tags:
+    - embeddings
+    - gguf
+    - cpu
+    - gpu
+  files:
+    - filename: bge-base-en-v1.5-q4_k_m.gguf
+      sha256: 74aebb552ea73b271d3b9c709923b4b7633b304fbc897a0498e52a180c3a9da9
+      uri: https://huggingface.co/CompendiumLabs/bge-base-en-v1.5-gguf/resolve/24914efdfa9ee54e815c3fcaa78a617031251c5c/bge-base-en-v1.5-q4_k_m.gguf
+  overrides:
+    backend: llama-cpp
+    context_size: 512
+    embeddings: true
+    options:
+      - pooling:cls
+    parameters:
+      model: bge-base-en-v1.5-q4_k_m.gguf
 - url: github:mudler/LocalAI/gallery/virtual.yaml@master
   name: bge-small-en-v1.5-f16
   description: |
diff --git a/gallery/models/index.yaml b/gallery/models/index.yaml
index 724c624cb..015b99c75 100644
--- a/gallery/models/index.yaml
+++ b/gallery/models/index.yaml
@@ -4,6 +4,117 @@
 # changes and never edit it by hand. CI fails when it is stale. A build from
 # master reads it as the default model source; a tagged build reads the gallery
 # until the release cutover.
+- kind: model
+  id: bge-base-en-v1.5-f16
+  name: bge-base-en-v1.5-f16
+  version: 0.0.0-gallery.e45654707d11
+  description: |
+    BGE-base-en-v1.5 is a 109M English embedding model for semantic search
+    and retrieval. This F16 GGUF build produces 768-dimensional embeddings
+    with a 512-token context. For retrieval, prefix queries with
+    "Represent this sentence for searching relevant passages: "; leave passages unprefixed.
+  license: mit
+  urls:
+    - https://huggingface.co/BAAI/bge-base-en-v1.5
+    - https://huggingface.co/CompendiumLabs/bge-base-en-v1.5-gguf
+  tags:
+    - embeddings
+    - gguf
+    - cpu
+    - gpu
+  channel: gallery
+  policy:
+    requireSignature: false
+  schemaVersion: 1
+  model:
+    url: github:mudler/LocalAI/gallery/virtual.yaml@master
+    files:
+      - filename: bge-base-en-v1.5-f16.gguf
+        sha256: 88360fdf8521af0ac08d43818bd272da679ab97c685d9b273c48efd01a4187c2
+        uri: https://huggingface.co/CompendiumLabs/bge-base-en-v1.5-gguf/resolve/24914efdfa9ee54e815c3fcaa78a617031251c5c/bge-base-en-v1.5-f16.gguf
+    overrides:
+      backend: llama-cpp
+      context_size: 512
+      embeddings: true
+      options:
+        - pooling:cls
+      parameters:
+        model: bge-base-en-v1.5-f16.gguf
+    variants:
+      - model: bge-base-en-v1.5-q8-0
+      - model: bge-base-en-v1.5-q4-k-m
+- kind: model
+  id: bge-base-en-v1.5-q8-0
+  name: bge-base-en-v1.5-q8-0
+  version: 0.0.0-gallery.c8e222453322
+  description: |
+    BGE-base-en-v1.5 is a 109M English embedding model for semantic search
+    and retrieval. This Q8_0 GGUF build produces 768-dimensional embeddings
+    with a 512-token context. For retrieval, prefix queries with
+    "Represent this sentence for searching relevant passages: "; leave passages unprefixed.
+  license: mit
+  urls:
+    - https://huggingface.co/BAAI/bge-base-en-v1.5
+    - https://huggingface.co/CompendiumLabs/bge-base-en-v1.5-gguf
+  tags:
+    - embeddings
+    - gguf
+    - cpu
+    - gpu
+  channel: gallery
+  policy:
+    requireSignature: false
+  schemaVersion: 1
+  model:
+    url: github:mudler/LocalAI/gallery/virtual.yaml@master
+    files:
+      - filename: bge-base-en-v1.5-q8_0.gguf
+        sha256: ad1afe72cd6654a558667a3db10878b049a75bfd72912e1dabb91310d671173c
+        uri: https://huggingface.co/CompendiumLabs/bge-base-en-v1.5-gguf/resolve/24914efdfa9ee54e815c3fcaa78a617031251c5c/bge-base-en-v1.5-q8_0.gguf
+    overrides:
+      backend: llama-cpp
+      context_size: 512
+      embeddings: true
+      options:
+        - pooling:cls
+      parameters:
+        model: bge-base-en-v1.5-q8_0.gguf
+- kind: model
+  id: bge-base-en-v1.5-q4-k-m
+  name: bge-base-en-v1.5-q4-k-m
+  version: 0.0.0-gallery.1dfbb38a60d2
+  description: |
+    BGE-base-en-v1.5 is a 109M English embedding model for semantic search
+    and retrieval. This Q4_K_M GGUF build produces 768-dimensional embeddings
+    with a 512-token context. For retrieval, prefix queries with
+    "Represent this sentence for searching relevant passages: "; leave passages unprefixed.
+  license: mit
+  urls:
+    - https://huggingface.co/BAAI/bge-base-en-v1.5
+    - https://huggingface.co/CompendiumLabs/bge-base-en-v1.5-gguf
+  tags:
+    - embeddings
+    - gguf
+    - cpu
+    - gpu
+  channel: gallery
+  policy:
+    requireSignature: false
+  schemaVersion: 1
+  model:
+    url: github:mudler/LocalAI/gallery/virtual.yaml@master
+    files:
+      - filename: bge-base-en-v1.5-q4_k_m.gguf
+        sha256: 74aebb552ea73b271d3b9c709923b4b7633b304fbc897a0498e52a180c3a9da9
+        uri: https://huggingface.co/CompendiumLabs/bge-base-en-v1.5-gguf/resolve/24914efdfa9ee54e815c3fcaa78a617031251c5c/bge-base-en-v1.5-q4_k_m.gguf
+    overrides:
+      backend: llama-cpp
+      context_size: 512
+      embeddings: true
+      options:
+        - pooling:cls
+      parameters:
+        model: bge-base-en-v1.5-q4_k_m.gguf
 - kind: model
   id: bge-small-en-v1.5-f16
   name: bge-small-en-v1.5-f16