Merge pull request #94 from philippgille/add-new-embedding-models

Update embedding model constants
philippgille · Aug 11, 2024 · a194428 · a194428
2 parents 55f437c + a43daf6
commit a194428
Show file tree

Hide file tree

Showing 3 changed files with 32 additions and 14 deletions.
diff --git a/embed_cohere.go b/embed_cohere.go
@@ -15,9 +15,10 @@ import (
 type EmbeddingModelCohere string
 
 const (
-	EmbeddingModelCohereMultilingualV2      EmbeddingModelCohere = "embed-multilingual-v2.0"
-	EmbeddingModelCohereEnglishLightV2      EmbeddingModelCohere = "embed-english-light-v2.0"
-	EmbeddingModelCohereEnglishV2           EmbeddingModelCohere = "embed-english-v2.0"
+	EmbeddingModelCohereMultilingualV2 EmbeddingModelCohere = "embed-multilingual-v2.0"
+	EmbeddingModelCohereEnglishLightV2 EmbeddingModelCohere = "embed-english-light-v2.0"
+	EmbeddingModelCohereEnglishV2      EmbeddingModelCohere = "embed-english-v2.0"
+
 	EmbeddingModelCohereMultilingualLightV3 EmbeddingModelCohere = "embed-multilingual-light-v3.0"
 	EmbeddingModelCohereEnglishLightV3      EmbeddingModelCohere = "embed-english-light-v3.0"
 	EmbeddingModelCohereMultilingualV3      EmbeddingModelCohere = "embed-multilingual-v3.0"

diff --git a/embed_compat.go b/embed_compat.go
@@ -23,10 +23,14 @@ const baseURLJina = "https://api.jina.ai/v1"
 type EmbeddingModelJina string
 
 const (
-	EmbeddingModelJina2BaseEN   EmbeddingModelJina = "jina-embeddings-v2-base-en"
-	EmbeddingModelJina2BaseDE   EmbeddingModelJina = "jina-embeddings-v2-base-de"
+	EmbeddingModelJina2BaseEN EmbeddingModelJina = "jina-embeddings-v2-base-en"
+	EmbeddingModelJina2BaseES EmbeddingModelJina = "jina-embeddings-v2-base-es"
+	EmbeddingModelJina2BaseDE EmbeddingModelJina = "jina-embeddings-v2-base-de"
+	EmbeddingModelJina2BaseZH EmbeddingModelJina = "jina-embeddings-v2-base-zh"
+
 	EmbeddingModelJina2BaseCode EmbeddingModelJina = "jina-embeddings-v2-base-code"
-	EmbeddingModelJina2BaseZH   EmbeddingModelJina = "jina-embeddings-v2-base-zh"
+
+	EmbeddingModelJinaClipV1 EmbeddingModelJina = "jina-clip-v1"
 )
 
 // NewEmbeddingFuncJina returns a function that creates embeddings for a text
@@ -40,14 +44,26 @@ const baseURLMixedbread = "https://api.mixedbread.ai"
 type EmbeddingModelMixedbread string
 
 const (
-	EmbeddingModelMixedbreadUAELargeV1          EmbeddingModelMixedbread = "UAE-Large-V1"
-	EmbeddingModelMixedbreadBGELargeENV15       EmbeddingModelMixedbread = "bge-large-en-v1.5"
-	EmbeddingModelMixedbreadGTELarge            EmbeddingModelMixedbread = "gte-large"
-	EmbeddingModelMixedbreadE5LargeV2           EmbeddingModelMixedbread = "e5-large-v2"
+	// Possibly outdated / not available anymore
+	EmbeddingModelMixedbreadUAELargeV1 EmbeddingModelMixedbread = "UAE-Large-V1"
+	// Possibly outdated / not available anymore
+	EmbeddingModelMixedbreadBGELargeENV15 EmbeddingModelMixedbread = "bge-large-en-v1.5"
+	// Possibly outdated / not available anymore
+	EmbeddingModelMixedbreadGTELarge EmbeddingModelMixedbread = "gte-large"
+	// Possibly outdated / not available anymore
+	EmbeddingModelMixedbreadE5LargeV2 EmbeddingModelMixedbread = "e5-large-v2"
+	// Possibly outdated / not available anymore
 	EmbeddingModelMixedbreadMultilingualE5Large EmbeddingModelMixedbread = "multilingual-e5-large"
-	EmbeddingModelMixedbreadMultilingualE5Base  EmbeddingModelMixedbread = "multilingual-e5-base"
-	EmbeddingModelMixedbreadAllMiniLML6V2       EmbeddingModelMixedbread = "all-MiniLM-L6-v2"
-	EmbeddingModelMixedbreadGTELargeZh          EmbeddingModelMixedbread = "gte-large-zh"
+	// Possibly outdated / not available anymore
+	EmbeddingModelMixedbreadMultilingualE5Base EmbeddingModelMixedbread = "multilingual-e5-base"
+	// Possibly outdated / not available anymore
+	EmbeddingModelMixedbreadAllMiniLML6V2 EmbeddingModelMixedbread = "all-MiniLM-L6-v2"
+	// Possibly outdated / not available anymore
+	EmbeddingModelMixedbreadGTELargeZh EmbeddingModelMixedbread = "gte-large-zh"
+
+	EmbeddingModelMixedbreadLargeV1          EmbeddingModelMixedbread = "mxbai-embed-large-v1"
+	EmbeddingModelMixedbreadDeepsetDELargeV1 EmbeddingModelMixedbread = "deepset-mxbai-embed-de-large-v1"
+	EmbeddingModelMixedbread2DLargeV1        EmbeddingModelMixedbread = "mxbai-embed-2d-large-v1"
 )
 
 // NewEmbeddingFuncMixedbread returns a function that creates embeddings for a text

diff --git a/embed_openai.go b/embed_openai.go
@@ -17,7 +17,8 @@ const BaseURLOpenAI = "https://api.openai.com/v1"
 type EmbeddingModelOpenAI string
 
 const (
-	EmbeddingModelOpenAI2Ada   EmbeddingModelOpenAI = "text-embedding-ada-002"
+	EmbeddingModelOpenAI2Ada EmbeddingModelOpenAI = "text-embedding-ada-002"
+
 	EmbeddingModelOpenAI3Small EmbeddingModelOpenAI = "text-embedding-3-small"
 	EmbeddingModelOpenAI3Large EmbeddingModelOpenAI = "text-embedding-3-large"
 )