docs: improve SEO metadata across docs pages

2026-08-01 01:30:05 +00:00
parent d06ea1875c
commit 26520d4808
218 changed files with 201 additions and 232 deletions
@@ -1,6 +1,6 @@
 ---
 title: AWS Bedrock
-description: "Configure AWS Bedrock as an embedding provider in Mem0 with IAM credentials and boto3 authentication."
+description: "Use AWS Bedrock as a Mem0 embedder with Amazon Titan or Cohere models, boto3 or aws-sdk auth, and configurable vector output dimensions."
 ---

 To use AWS Bedrock embedding models, you need the appropriate AWS credentials and permissions. Python uses `boto3`, and TypeScript uses `@aws-sdk/client-bedrock-runtime`.
@@ -1,6 +1,6 @@
 ---
 title: Azure OpenAI
-description: "Configure Azure OpenAI as an embedding provider in Mem0 with API key, deployment, and endpoint settings."
+description: "Set up Azure OpenAI embeddings in Mem0 with deployment name, endpoint, API version, and optional Azure Identity role-based authentication."
 ---

 To use Azure OpenAI embedding models, set the `EMBEDDING_AZURE_OPENAI_API_KEY`, `EMBEDDING_AZURE_DEPLOYMENT`, `EMBEDDING_AZURE_ENDPOINT` and `EMBEDDING_AZURE_API_VERSION` environment variables. You can obtain the Azure OpenAI API key from the Azure Portal.
@@ -1,6 +1,6 @@
 ---
 title: "FastEmbed"
-description: "Configure FastEmbed as an embedding provider in Mem0 to generate embeddings locally using ONNX-based models without a GPU."
+description: "Run FastEmbed inside Mem0 to generate ONNX-based text embeddings locally on CPU without API keys, using models like gte-large or bge-small."
 ---

 You can use FastEmbed to run embedding models locally in Mem0. FastEmbed is an ONNX-based embedding library that runs efficiently on CPU without requiring a GPU or an external API key.
@@ -1,6 +1,6 @@
 ---
 title: Google AI
-description: "Configure Google AI as an embedding provider in Mem0 using Gemini models and the GOOGLE_API_KEY variable."
+description: "Use Google AI Gemini embedding models in Mem0 with the GOOGLE_API_KEY, including gemini-embedding-001 and configurable output dimensionality."
 ---

 To use Google AI embedding models, set the `GOOGLE_API_KEY` environment variables. You can obtain the Gemini API key from [here](https://aistudio.google.com/app/apikey).
@@ -1,6 +1,6 @@
 ---
 title: Hugging Face
-description: "Configure Hugging Face as an embedding provider in Mem0 for local embedding generation with open-source models."
+description: "Use Hugging Face embeddings in Mem0 via local sentence-transformers or a Text Embeddings Inference (TEI) endpoint for fast, self-hosted vectors."
 ---

 You can use embedding models from Huggingface to run Mem0 locally.
@@ -1,6 +1,6 @@
 ---
 title: LangChain
-description: "Use LangChain as an embedding provider in Mem0 to access a wide range of models through a unified interface."
+description: "Plug LangChain embedding classes into Mem0 to reuse OpenAI, Cohere, HuggingFace, or Ollama embedding models through a single unified interface."
 ---

 Mem0 supports LangChain as a provider to access a wide range of embedding models. LangChain is a framework for developing applications powered by language models, making it easy to integrate various embedding providers through a consistent interface.
@@ -1,6 +1,6 @@
 ---
 title: "LM Studio"
-description: "Configure LM Studio as an embedding provider in Mem0 for local embedding generation with models like nomic-embed-text."
+description: "Run LM Studio locally as a Mem0 embedder using GGUF models like nomic-embed-text through the built-in OpenAI-compatible HTTP server."
 ---
 You can use embedding models from LM Studio to run Mem0 locally.

@@ -1,6 +1,6 @@
 ---
 title: "Ollama"
-description: "Configure Ollama as an embedding provider in Mem0 to generate embeddings locally using open-source models."
+description: "Serve Ollama embedding models like nomic-embed-text or mxbai-embed-large inside Mem0 for private, offline vector generation on your own machine."
 ---
 You can use embedding models from Ollama to run Mem0 locally.

@@ -1,6 +1,6 @@
 ---
 title: OpenAI
-description: "Configure OpenAI as an embedding provider in Mem0 using models like text-embedding-3-large for vector generation."
+description: "Use OpenAI embedding models such as text-embedding-3-small and text-embedding-3-large inside Mem0 with the OPENAI_API_KEY environment variable."
 ---

 To use OpenAI embedding models, set the `OPENAI_API_KEY` environment variable. You can obtain the OpenAI API key from the [OpenAI Platform](https://platform.openai.com/account/api-keys).
@@ -1,6 +1,6 @@
 ---
 title: Together
-description: "Configure Together AI as an embedding provider in Mem0 with support for 1024-dimensional embedding models."
+description: "Use Together AI in Mem0 with the multilingual-e5-large-instruct embedding model at 1024 dimensions for cross-language semantic search."
 ---

 To use Together embedding models, set the `TOGETHER_API_KEY` environment variable. You can obtain the Together API key from the [Together Platform](https://api.together.ai/settings/projects/~current/api-keys).
@@ -1,6 +1,6 @@
 ---
 title: "Vertex AI"
-description: "Configure Google Cloud Vertex AI as an embedding provider in Mem0 with support for task-specific embedding types."
+description: "Use Google Cloud Vertex AI embeddings in Mem0 with ADC authentication, gemini-embedding-001, and task-specific types for add, update, and search."
 ---
 ### Vertex AI