Skip to content

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

feature: Introducing VoyageAI (#1871)

fzowl3fecde49b689
diff --git a/docs/concepts/knowledge.mdx b/docs/concepts/knowledge.mdx
index 254a56bb8..e4e40ba3e 100644
--- a/docs/concepts/knowledge.mdx
+++ b/docs/concepts/knowledge.mdx
@@ -288,6 +288,7 @@ The `embedder` parameter supports various embedding model providers that include
- `ollama`: Local embeddings with Ollama
- `vertexai`: Google Cloud VertexAI embeddings
- `cohere`: Cohere's embedding models
+- `voyageai`: VoyageAI's embedding models
- `bedrock`: AWS Bedrock embeddings
- `huggingface`: Hugging Face models
- `watson`: IBM Watson embeddings
diff --git a/docs/concepts/memory.mdx b/docs/concepts/memory.mdx
index b04b29c64..751b6dd2e 100644
--- a/docs/concepts/memory.mdx
+++ b/docs/concepts/memory.mdx
@@ -293,6 +293,26 @@ my_crew = Crew(
}
)
```
+### Using VoyageAI embeddings
+
+```python Code
+from crewai import Crew, Agent, Task, Process
+
+my_crew = Crew(
+ agents=[...],
+ tasks=[...],
+ process=Process.sequential,
+ memory=True,
+ verbose=True,
+ embedder={
+ "provider": "voyageai",
+ "config": {
+ "api_key": "YOUR_API_KEY",
+ "model_name": "<model_name>"
+ }
+ }
+)
+```
### Using HuggingFace embeddings
```python Code
diff --git a/docs/how-to/llm-connections.mdx b/docs/how-to/llm-connections.mdx
index 25509c299..33be323b7 100644
--- a/docs/how-to/llm-connections.mdx
+++ b/docs/how-to/llm-connections.mdx
@@ -23,6 +23,7 @@ LiteLLM supports a wide range of providers, including but not limited to:
- Azure OpenAI
- AWS (Bedrock, SageMaker)
- Cohere
+- VoyageAI
- Hugging Face
- Ollama
- Mistral AI
diff --git a/src/crewai/utilities/embedding_configurator.py b/src/crewai/utilities/embedding_configurator.py
index 44e832ec2..71965bf53 100644
--- a/src/crewai/utilities/embedding_configurator.py
+++ b/src/crewai/utilities/embedding_configurator.py
@@ -14,6 +14,7 @@ class EmbeddingConfigurator:
"vertexai": self._configure_vertexai,
"google": self._configure_google,
"cohere": self._configure_cohere,
+ "voyageai": self._configure_voyageai,
"bedrock": self._configure_bedrock,
"huggingface": self._configure_huggingface,
"watson": self._configure_watson,
@@ -124,6 +125,17 @@ class EmbeddingConfigurator:
api_key=config.get("api_key"),
)
+ @staticmethod
+ def _configure_voyageai(config, model_name):
+ from chromadb.utils.embedding_functions.voyageai_embedding_function import (
+ VoyageAIEmbeddingFunction,
+ )
+
+ return VoyageAIEmbeddingFunction(
+ model_name=model_name,
+ api_key=config.get("api_key"),
+ )
+
@staticmethod
def _configure_bedrock(config, model_name):
from chromadb.utils.embedding_functions.amazon_bedrock_embedding_function import (