From 95fbf05ace6f8087052f42359afa11d5fcfd8215 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 09:52:06 +0000
Subject: [PATCH] feat(gallery): add BGE small English variants

Add F16, Q8_0 and Q4_K_M builds for English retrieval. Pin the source
revision and verify each SHA256 against HF metadata and download headers.
Document query prefixes and the 512-token context.

Assisted-by: Codex:gpt-6

(cherry picked from commit b99b669cefa927fdeb8cbf2efdc694cfcbcf4cad, mudler/LocalAI#12713)
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 948c6b39d..917613886 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-small-en-v1.5-f16
+  description: |
+    BGE-small-en-v1.5 is a 33M English embedding model for semantic search
+    and retrieval. This F16 GGUF build produces 384-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-small-en-v1.5
+    - https://huggingface.co/CompendiumLabs/bge-small-en-v1.5-gguf
+  tags:
+    - embeddings
+    - gguf
+    - cpu
+    - gpu
+  files:
+    - filename: bge-small-en-v1.5-f16.gguf
+      sha256: f0b2fef971e8366438bfd2d9aefea1b0115919389448806d290237f638bae999
+      uri: https://huggingface.co/CompendiumLabs/bge-small-en-v1.5-gguf/resolve/d32f8c040ea3b516330eeb75b72bcc2d3a780ab7/bge-small-en-v1.5-f16.gguf
+  overrides:
+    backend: llama-cpp
+    context_size: 512
+    embeddings: true
+    options:
+      - pooling:cls
+    parameters:
+      model: bge-small-en-v1.5-f16.gguf
+  variants:
+    - model: bge-small-en-v1.5-q8-0
+    - model: bge-small-en-v1.5-q4-k-m
+- url: github:mudler/LocalAI/gallery/virtual.yaml@master
+  name: bge-small-en-v1.5-q8-0
+  description: |
+    BGE-small-en-v1.5 is a 33M English embedding model for semantic search
+    and retrieval. This Q8_0 GGUF build produces 384-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-small-en-v1.5
+    - https://huggingface.co/CompendiumLabs/bge-small-en-v1.5-gguf
+  tags:
+    - embeddings
+    - gguf
+    - cpu
+    - gpu
+  files:
+    - filename: bge-small-en-v1.5-q8_0.gguf
+      sha256: ec38e8da142596baa913124ae50550de284b6916bf59577ef2f0cb9660c2f514
+      uri: https://huggingface.co/CompendiumLabs/bge-small-en-v1.5-gguf/resolve/d32f8c040ea3b516330eeb75b72bcc2d3a780ab7/bge-small-en-v1.5-q8_0.gguf
+  overrides:
+    backend: llama-cpp
+    context_size: 512
+    embeddings: true
+    options:
+      - pooling:cls
+    parameters:
+      model: bge-small-en-v1.5-q8_0.gguf
+- url: github:mudler/LocalAI/gallery/virtual.yaml@master
+  name: bge-small-en-v1.5-q4-k-m
+  description: |
+    BGE-small-en-v1.5 is a 33M English embedding model for semantic search
+    and retrieval. This Q4_K_M GGUF build produces 384-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-small-en-v1.5
+    - https://huggingface.co/CompendiumLabs/bge-small-en-v1.5-gguf
+  tags:
+    - embeddings
+    - gguf
+    - cpu
+    - gpu
+  files:
+    - filename: bge-small-en-v1.5-q4_k_m.gguf
+      sha256: 363a0a4855dff6c653e06efe3209157debcf7f74e52d0d7c71e2747cd523043e
+      uri: https://huggingface.co/CompendiumLabs/bge-small-en-v1.5-gguf/resolve/d32f8c040ea3b516330eeb75b72bcc2d3a780ab7/bge-small-en-v1.5-q4_k_m.gguf
+  overrides:
+    backend: llama-cpp
+    context_size: 512
+    embeddings: true
+    options:
+      - pooling:cls
+    parameters:
+      model: bge-small-en-v1.5-q4_k_m.gguf
 - url: github:mudler/LocalAI/gallery/virtual.yaml@master
   name: qwen3.5-0.8b-artemis-q5
   description: |
diff --git a/gallery/models/index.yaml b/gallery/models/index.yaml
index 629d4ccd3..724c624cb 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-small-en-v1.5-f16
+  name: bge-small-en-v1.5-f16
+  version: 0.0.0-gallery.69aff1cad742
+  description: |
+    BGE-small-en-v1.5 is a 33M English embedding model for semantic search
+    and retrieval. This F16 GGUF build produces 384-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-small-en-v1.5
+    - https://huggingface.co/CompendiumLabs/bge-small-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-small-en-v1.5-f16.gguf
+        sha256: f0b2fef971e8366438bfd2d9aefea1b0115919389448806d290237f638bae999
+        uri: https://huggingface.co/CompendiumLabs/bge-small-en-v1.5-gguf/resolve/d32f8c040ea3b516330eeb75b72bcc2d3a780ab7/bge-small-en-v1.5-f16.gguf
+    overrides:
+      backend: llama-cpp
+      context_size: 512
+      embeddings: true
+      options:
+        - pooling:cls
+      parameters:
+        model: bge-small-en-v1.5-f16.gguf
+    variants:
+      - model: bge-small-en-v1.5-q8-0
+      - model: bge-small-en-v1.5-q4-k-m
+- kind: model
+  id: bge-small-en-v1.5-q8-0
+  name: bge-small-en-v1.5-q8-0
+  version: 0.0.0-gallery.a32f5a726b57
+  description: |
+    BGE-small-en-v1.5 is a 33M English embedding model for semantic search
+    and retrieval. This Q8_0 GGUF build produces 384-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-small-en-v1.5
+    - https://huggingface.co/CompendiumLabs/bge-small-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-small-en-v1.5-q8_0.gguf
+        sha256: ec38e8da142596baa913124ae50550de284b6916bf59577ef2f0cb9660c2f514
+        uri: https://huggingface.co/CompendiumLabs/bge-small-en-v1.5-gguf/resolve/d32f8c040ea3b516330eeb75b72bcc2d3a780ab7/bge-small-en-v1.5-q8_0.gguf
+    overrides:
+      backend: llama-cpp
+      context_size: 512
+      embeddings: true
+      options:
+        - pooling:cls
+      parameters:
+        model: bge-small-en-v1.5-q8_0.gguf
+- kind: model
+  id: bge-small-en-v1.5-q4-k-m
+  name: bge-small-en-v1.5-q4-k-m
+  version: 0.0.0-gallery.1c97a0fa0ac9
+  description: |
+    BGE-small-en-v1.5 is a 33M English embedding model for semantic search
+    and retrieval. This Q4_K_M GGUF build produces 384-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-small-en-v1.5
+    - https://huggingface.co/CompendiumLabs/bge-small-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-small-en-v1.5-q4_k_m.gguf
+        sha256: 363a0a4855dff6c653e06efe3209157debcf7f74e52d0d7c71e2747cd523043e
+        uri: https://huggingface.co/CompendiumLabs/bge-small-en-v1.5-gguf/resolve/d32f8c040ea3b516330eeb75b72bcc2d3a780ab7/bge-small-en-v1.5-q4_k_m.gguf
+    overrides:
+      backend: llama-cpp
+      context_size: 512
+      embeddings: true
+      options:
+        - pooling:cls
+      parameters:
+        model: bge-small-en-v1.5-q4_k_m.gguf
 - kind: model
   id: qwen3.5-0.8b-artemis-q5
   name: qwen3.5-0.8b-artemis-q5