repositories
loading repo index
repositories
loading repo index
repository
loading code, commits, and activity
public Clawd ADK gateway launch mirror
stars
latest
clone command
git clone gitlawb://did:key:z6Mkq5mY...iFZ5/my-project-publ...git clone gitlawb://did:key:z6Mkq5mY.../my-project-publ...2fa351d6docs: add automaton and perps launch sources16d ago| #1 | --- |
| #2 | title: Overview |
| #3 | --- |
| #4 | |
| #5 | Mem0 includes built-in support for various popular large language models. Memory can utilize the LLM provided by the user, ensuring efficient use for specific needs. |
| #6 | |
| #7 | ## Usage |
| #8 | |
| #9 | To use a llm, you must provide a configuration to customize its usage. If no configuration is supplied, a default configuration will be applied, and `OpenAI` will be used as the llm. |
| #10 | |
| #11 | For a comprehensive list of available parameters for llm configuration, please refer to [Config](./config). |
| #12 | |
| #13 | ## Supported LLMs |
| #14 | |
| #15 | See the list of supported LLMs below. |
| #16 | |
| #17 | <Note> |
| #18 | All LLMs are supported in Python. The following LLMs are also supported in TypeScript: **OpenAI**, **Anthropic**, and **Groq**. |
| #19 | </Note> |
| #20 | |
| #21 | <CardGroup cols={4}> |
| #22 | <Card title="OpenAI" href="/components/llms/models/openai" /> |
| #23 | <Card title="Ollama" href="/components/llms/models/ollama" /> |
| #24 | <Card title="Azure OpenAI" href="/components/llms/models/azure_openai" /> |
| #25 | <Card title="Anthropic" href="/components/llms/models/anthropic" /> |
| #26 | <Card title="Together" href="/components/llms/models/together" /> |
| #27 | <Card title="Groq" href="/components/llms/models/groq" /> |
| #28 | <Card title="Litellm" href="/components/llms/models/litellm" /> |
| #29 | <Card title="Mistral AI" href="/components/llms/models/mistral_AI" /> |
| #30 | <Card title="Google AI" href="/components/llms/models/google_AI" /> |
| #31 | <Card title="AWS bedrock" href="/components/llms/models/aws_bedrock" /> |
| #32 | <Card title="DeepSeek" href="/components/llms/models/deepseek" /> |
| #33 | <Card title="xAI" href="/components/llms/models/xAI" /> |
| #34 | <Card title="Sarvam AI" href="/components/llms/models/sarvam" /> |
| #35 | <Card title="LM Studio" href="/components/llms/models/lmstudio" /> |
| #36 | <Card title="Langchain" href="/components/llms/models/langchain" /> |
| #37 | </CardGroup> |
| #38 | |
| #39 | ## Structured vs Unstructured Outputs |
| #40 | |
| #41 | Mem0 supports two types of OpenAI LLM formats, each with its own strengths and use cases: |
| #42 | |
| #43 | ### Structured Outputs |
| #44 | |
| #45 | Structured outputs are LLMs that align with OpenAI's structured outputs model: |
| #46 | |
| #47 | - **Optimized for:** Returning structured responses (e.g., JSON objects) |
| #48 | - **Benefits:** Precise, easily parseable data |
| #49 | - **Ideal for:** Data extraction, form filling, API responses |
| #50 | - **Learn more:** [OpenAI Structured Outputs Guide](https://platform.openai.com/docs/guides/structured-outputs/introduction) |
| #51 | |
| #52 | ### Unstructured Outputs |
| #53 | |
| #54 | Unstructured outputs correspond to OpenAI's standard, free-form text model: |
| #55 | |
| #56 | - **Flexibility:** Returns open-ended, natural language responses |
| #57 | - **Customization:** Use the `response_format` parameter to guide output |
| #58 | - **Trade-off:** Less efficient than structured outputs for specific data needs |
| #59 | - **Best for:** Creative writing, explanations, general conversation |
| #60 | |
| #61 | Choose the format that best suits your application's requirements for optimal performance and usability. |
| #62 |