[ENH] Add nomic embedding function

Author: jairad26

chromadb/test/ef/test_ef.py

@@ -37,6 +37,7 @@ def test_get_builtins_holds() -> None:
         "InstructorEmbeddingFunction",
         "JinaEmbeddingFunction",
         "MistralEmbeddingFunction",
+        "NomicEmbeddingFunction",
         "ONNXMiniLM_L6_V2",
         "OllamaEmbeddingFunction",
         "OpenAIEmbeddingFunction",

chromadb/utils/embedding_functions/__init__.py

@@ -65,6 +65,10 @@
 from chromadb.utils.embedding_functions.mistral_embedding_function import (
     MistralEmbeddingFunction,
 )
+from chromadb.utils.embedding_functions.nomic_embedding_function import (
+    NomicEmbeddingFunction,
+    NomicQueryConfig,
+)
 
 try:
     from chromadb.is_thin_client import is_thin_client
@@ -84,7 +88,10 @@
     "OllamaEmbeddingFunction",
     "InstructorEmbeddingFunction",
     "JinaEmbeddingFunction",
+    "JinaQueryConfig",
     "MistralEmbeddingFunction",
+    "NomicEmbeddingFunction",
+    "NomicQueryConfig",
     "VoyageAIEmbeddingFunction",
     "ONNXMiniLM_L6_V2",
     "OpenCLIPEmbeddingFunction",
@@ -146,6 +153,7 @@ def validate_config(config: Dict[str, Any]) -> None:
     "instructor": InstructorEmbeddingFunction,
     "jina": JinaEmbeddingFunction,
     "mistral": MistralEmbeddingFunction,
+    "nomic": NomicEmbeddingFunction,
     "voyageai": VoyageAIEmbeddingFunction,
     "onnx_mini_lm_l6_v2": ONNXMiniLM_L6_V2,
     "open_clip": OpenCLIPEmbeddingFunction,
@@ -235,6 +243,8 @@ def config_to_embedding_function(config: Dict[str, Any]) -> EmbeddingFunction:
     "JinaEmbeddingFunction",
     "JinaQueryConfig",
     "MistralEmbeddingFunction",
+    "NomicEmbeddingFunction",
+    "NomicQueryConfig",
     "VoyageAIEmbeddingFunction",
     "ONNXMiniLM_L6_V2",
     "OpenCLIPEmbeddingFunction",

chromadb/utils/embedding_functions/nomic_embedding_function.py

@@ -0,0 +1,109 @@
+from chromadb.api.types import (
+    Embeddings,
+    Documents,
+    EmbeddingFunction,
+    Space,
+    QueryConfig,
+)
+from chromadb.utils.embedding_functions.schemas import validate_config_schema
+from typing import List, Dict, Any
+from typing_extensions import override
+import os
+import numpy as np
+
+
+class NomicEmbeddingFunction(EmbeddingFunction[Documents]):
+    """
+    This class is used to get embeddings for a list of texts using the Nomic API.
+    """
+
+    def __init__(
+        self,
+        model: str,
+        api_key_env_var: str = "NOMIC_API_KEY",
+        task_type: str = "search_document",
+    ):
+        try:
+            from nomic import embed
+        except ImportError:
+            raise ValueError(
+                "The nomic python package is not installed. Please install it with `pip install nomic`"
+            )
+
+        self.model = model
+        self.task_type = task_type
+        self.api_key_env_var = api_key_env_var
+        self.api_key = os.getenv(api_key_env_var)
+        if not self.api_key:
+            raise ValueError(f"The {api_key_env_var} environment variable is not set.")
+        self.embed = embed
+
+    def __call__(self, input: Documents) -> Embeddings:
+        if not all(isinstance(item, str) for item in input):
+            raise ValueError("Nomic only supports text documents, not images")
+        output = self.embed.text(
+            model=self.model,
+            texts=input,
+            task_type=self.task_type,
+        )
+        return [np.array(data.embedding) for data in output.data]
+
+    @staticmethod
+    def name() -> str:
+        return "nomic"
+
+    def default_space(self) -> Space:
+        return "cosine"
+
+    def supported_spaces(self) -> List[Space]:
+        return ["cosine", "l2", "ip"]
+
+    @staticmethod
+    def build_from_config(config: Dict[str, Any]) -> "EmbeddingFunction[Documents]":
+        model = config.get("model")
+        api_key_env_var = config.get("api_key_env_var")
+        task_type = config.get("task_type")
+        if model is None or api_key_env_var is None or task_type is None:
+            assert False, "This code should not be reached"  # this is for type checking
+        return NomicEmbeddingFunction(
+            model=model, api_key_env_var=api_key_env_var, task_type=task_type
+        )
+
+    def get_config(self) -> Dict[str, Any]:
+        return {
+            "model": self.model,
+            "api_key_env_var": self.api_key_env_var,
+            "task_type": self.task_type,
+        }
+
+    def validate_config_update(
+        self, old_config: Dict[str, Any], new_config: Dict[str, Any]
+    ) -> None:
+        if "model" in new_config:
+            raise ValueError(
+                "The model cannot be changed after the embedding function has been initialized."
+            )
+
+    @staticmethod
+    def validate_config(config: Dict[str, Any]) -> None:
+        """
+        Validate the configuration using the JSON schema.
+
+        Args:
+            config: Configuration to validate
+        """
+        validate_config_schema(config, "nomic")
+
+
+class NomicQueryConfig(QueryConfig):
+    def __init__(self, task_type: str = "search_query"):
+        self.task_type = task_type
+
+    @override
+    def name(self) -> str:
+        return "nomic"
+
+    def get_config(self) -> Dict[str, Any]:
+        return {
+            "task_type": self.task_type,
+        }

schemas/embedding_functions/nomic.json

@@ -0,0 +1,21 @@
+{
+    "$schema": "http://json-schema.org/draft-07/schema#",
+    "title": "Nomic Embedding Function Schema",
+    "description": "Schema for the Nomic embedding function configuration",
+    "version": "1.0.0",
+    "type": "object",
+    "properties": {
+        "model": {
+            "type": "string",
+            "description": "Parameter model for the Nomic embedding function"
+        },
+        "api_key_env_var": {
+            "type": "string",
+            "description": "Parameter api_key_env_var for the Nomic embedding function"
+        },
+        "task_type": {
+            "type": "string",
+            "description": "Parameter task_type for the Nomic embedding function"
+        }
+    }
+}