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 | description: 'Pick the right reranker path to boost Mem0 search relevance.' |
| #4 | --- |
| #5 | |
| #6 | Mem0 rerankers rescore vector search hits so your agents surface the most relevant memories. Use this hub to decide when reranking helps, configure a provider, and fine-tune performance. |
| #7 | |
| #8 | <Info> |
| #9 | Reranking trades extra latency for better precision. Start once you have baseline search working and measure before/after relevance. |
| #10 | </Info> |
| #11 | |
| #12 | <CardGroup cols={3}> |
| #13 | <Card |
| #14 | title="Understand Reranking" |
| #15 | description="See how reranker-enhanced search changes your retrieval flow." |
| #16 | icon="search" |
| #17 | href="/open-source/features/reranker-search" |
| #18 | /> |
| #19 | <Card |
| #20 | title="Configure Providers" |
| #21 | description="Add reranker blocks to your memory configuration." |
| #22 | icon="settings" |
| #23 | href="/components/rerankers/config" |
| #24 | /> |
| #25 | <Card |
| #26 | title="Optimize Performance" |
| #27 | description="Balance relevance, latency, and cost with tuning tactics." |
| #28 | icon="speedometer" |
| #29 | href="/components/rerankers/optimization" |
| #30 | /> |
| #31 | <Card |
| #32 | title="Custom Prompts" |
| #33 | description="Shape LLM-based reranking with tailored instructions." |
| #34 | icon="code" |
| #35 | href="/components/rerankers/custom-prompts" |
| #36 | /> |
| #37 | <Card |
| #38 | title="Zero Entropy Guide" |
| #39 | description="Adopt the managed neural reranker for production workloads." |
| #40 | icon="sparkles" |
| #41 | href="/components/rerankers/models/zero_entropy" |
| #42 | /> |
| #43 | <Card |
| #44 | title="Sentence Transformers" |
| #45 | description="Keep reranking on-device with cross-encoder models." |
| #46 | icon="cpu" |
| #47 | href="/components/rerankers/models/sentence_transformer" |
| #48 | /> |
| #49 | </CardGroup> |
| #50 | |
| #51 | ## Picking the Right Reranker |
| #52 | |
| #53 | - **API-first** when you need top quality and can absorb request costs (Cohere, Zero Entropy). |
| #54 | - **Self-hosted** for privacy-sensitive deployments that must stay on your hardware (Sentence Transformer, Hugging Face). |
| #55 | - **LLM-driven** when you need bespoke scoring logic or complex prompts. |
| #56 | - **Hybrid** by enabling reranking only on premium journeys to control spend. |
| #57 | |
| #58 | ## Implementation Checklist |
| #59 | |
| #60 | 1. Confirm baseline search KPIs so you can measure uplift. |
| #61 | 2. Select a provider and add the `reranker` block to your config. |
| #62 | 3. Test latency impact with production-like query batches. |
| #63 | 4. Decide whether to enable reranking globally or per-search via the `rerank` flag. |
| #64 | |
| #65 | <CardGroup cols={2}> |
| #66 | <Card |
| #67 | title="Set Up Reranking" |
| #68 | description="Walk through the configuration fields and defaults." |
| #69 | icon="settings" |
| #70 | href="/components/rerankers/config" |
| #71 | /> |
| #72 | <Card |
| #73 | title="Example: Reranker Search" |
| #74 | description="Follow the feature guide to see reranking in action." |
| #75 | icon="rocket" |
| #76 | href="/open-source/features/reranker-search" |
| #77 | /> |
| #78 | </CardGroup> |
| #79 |