Skip to content

armgit / mem0

Public Imported from GitHub
0

The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.

fix(reranker): align llm_reranker default model with SDK default (#6703)

Kartikcf3355e2ca37
diff --git a/docs/components/rerankers/config.mdx b/docs/components/rerankers/config.mdx
index c789b7709..25d8691c4 100644
--- a/docs/components/rerankers/config.mdx
+++ b/docs/components/rerankers/config.mdx
@@ -52,7 +52,7 @@ All rerankers share these common configuration parameters:
| Parameter | Description | Type | Default |
| ---------------- | ------------------------------------------ | ------- | ---------------------- |
-| `model` | LLM model to use for scoring | `str` | `"gpt-4o-mini"` |
+| `model` | LLM model to use for scoring | `str` | `"gpt-5-mini"` |
| `provider` | LLM provider (`openai`, `anthropic`, etc.) | `str` | `"openai"` |
| `api_key` | API key for LLM provider | `str` | `None` |
| `temperature` | Temperature for LLM generation | `float` | `0.0` |
@@ -114,7 +114,7 @@ The self-hosted [TypeScript SDK](/open-source/features/reranker-search#typescrip
| `zero_entropy` | `pnpm add zeroentropy` | `zerank-1` | `apiKey`, `model`, `topK` |
| `sentence_transformer` | `pnpm add @huggingface/transformers` | `Xenova/ms-marco-MiniLM-L-6-v2` | `model`, `device`, `maxLength`, `normalize`, `topK` |
| `huggingface` | `pnpm add @huggingface/transformers` | `Xenova/bge-reranker-base` | `model`, `device`, `maxLength`, `normalize`, `topK` |
-| `llm_reranker` | None (uses your LLM provider's own SDK) | `openai` / `gpt-4o-mini` | `provider`, `model`, `apiKey`, `llm` (nested override), `topK` |
+| `llm_reranker` | None (uses your LLM provider's own SDK) | `openai` / `gpt-5-mini` | `provider`, `model`, `apiKey`, `llm` (nested override), `topK` |
```typescript
import { Memory } from "mem0ai/oss";
diff --git a/docs/components/rerankers/custom-prompts.mdx b/docs/components/rerankers/custom-prompts.mdx
index 6d7ba7ed1..a9e383b24 100644
--- a/docs/components/rerankers/custom-prompts.mdx
+++ b/docs/components/rerankers/custom-prompts.mdx
@@ -48,7 +48,7 @@ config = {
"provider": "llm_reranker",
"config": {
"provider": "openai",
- "model": "gpt-4o-mini",
+ "model": "gpt-5-mini",
"api_key": "your-openai-key",
"scoring_prompt": custom_prompt,
"top_k": 5
diff --git a/docs/components/rerankers/models/cohere.mdx b/docs/components/rerankers/models/cohere.mdx
index 53ea0c28f..050c4ff6b 100644
--- a/docs/components/rerankers/models/cohere.mdx
+++ b/docs/components/rerankers/models/cohere.mdx
@@ -101,7 +101,7 @@ os.environ["COHERE_API_KEY"] = "your-api-key"
# Initialize memory with Cohere reranker
config = {
"vector_store": {"provider": "chroma"},
- "llm": {"provider": "openai", "config": {"model": "gpt-4o-mini"}},
+ "llm": {"provider": "openai", "config": {"model": "gpt-5-mini"}},
"rerank": {
"provider": "cohere",
"config": {
diff --git a/docs/components/rerankers/models/llm_reranker.mdx b/docs/components/rerankers/models/llm_reranker.mdx
index e615fe07f..a4fdb57e0 100644
--- a/docs/components/rerankers/models/llm_reranker.mdx
+++ b/docs/components/rerankers/models/llm_reranker.mdx
@@ -19,7 +19,7 @@ config = {
"provider": "llm_reranker",
"config": {
"provider": "openai",
- "model": "gpt-4o-mini",
+ "model": "gpt-5-mini",
"api_key": "your-openai-api-key"
}
}
@@ -33,7 +33,7 @@ m = Memory.from_config(config)
| Parameter | Type | Default | Description |
|-----------|------|---------|-------------|
| `provider` | str | `"openai"` | LLM provider (openai, anthropic, etc.) |
-| `model` | str | `"gpt-4o-mini"` | LLM model to use for reranking |
+| `model` | str | `"gpt-5-mini"` | LLM model to use for reranking |
| `api_key` | str | None | API key for the LLM provider |
| `top_k` | int | None | Number of top documents to return after reranking |
| `temperature` | float | 0.0 | LLM temperature for consistency |
@@ -69,7 +69,7 @@ config = {
## TypeScript (self-hosted)
-The [TypeScript OSS SDK](/open-source/features/reranker-search#typescript-sdk) (`mem0ai/oss`) ships the LLM reranker under the provider name `llm_reranker`. It does **not** reuse the Memory's main `llm` instance; it builds its own LLM from the reranker's own config, defaulting to `openai` / `gpt-4o-mini`. Set `provider`/`model`/`apiKey` directly on `config`, or nest a fully separate `config.llm: { provider, config }` (its `provider`/`config` take priority over the top-level fields, which only backfill values missing from the nested config).
+The [TypeScript OSS SDK](/open-source/features/reranker-search#typescript-sdk) (`mem0ai/oss`) ships the LLM reranker under the provider name `llm_reranker`. It does **not** reuse the Memory's main `llm` instance; it builds its own LLM from the reranker's own config, defaulting to `openai` / `gpt-5-mini`. Set `provider`/`model`/`apiKey` directly on `config`, or nest a fully separate `config.llm: { provider, config }` (its `provider`/`config` take priority over the top-level fields, which only backfill values missing from the nested config).
```typescript
import { Memory } from "mem0ai/oss";
@@ -114,7 +114,7 @@ config = {
"provider": "llm_reranker",
"config": {
"provider": "openai",
- "model": "gpt-4o-mini",
+ "model": "gpt-5-mini",
"api_key": "your-openai-api-key",
"temperature": 0.0
}
@@ -170,15 +170,15 @@ config = {
"provider": "llm_reranker",
"config": {
"provider": "azure_openai",
- "model": "gpt-4o-mini",
+ "model": "gpt-5-mini",
"api_key": "your-azure-api-key",
"llm": {
"provider": "azure_openai",
"config": {
- "model": "gpt-4o-mini",
+ "model": "gpt-5-mini",
"api_key": "your-azure-api-key",
"azure_endpoint": "https://your-resource.openai.azure.com/",
- "azure_deployment": "gpt-4o-mini-deployment"
+ "azure_deployment": "gpt-5-mini-deployment"
}
}
}
@@ -232,7 +232,7 @@ config = {
"provider": "llm_reranker",
"config": {
"provider": "openai",
- "model": "gpt-4o-mini",
+ "model": "gpt-5-mini",
"api_key": "your-api-key",
"scoring_prompt": custom_prompt
}
@@ -351,7 +351,7 @@ fast_config = {
"provider": "llm_reranker",
"config": {
"provider": "openai",
- "model": "gpt-4o-mini",
+ "model": "gpt-5-mini",
"api_key": "your-api-key",
"top_k": 5,
"temperature": 0.0
@@ -444,7 +444,7 @@ fallback_config = {
"provider": "llm_reranker",
"config": {
"provider": "openai",
- "model": "gpt-4o-mini",
+ "model": "gpt-5-mini",
"api_key": "your-api-key"
}
}
diff --git a/docs/components/rerankers/models/sentence_transformer.mdx b/docs/components/rerankers/models/sentence_transformer.mdx
index f0631c45f..3304e1f27 100644
--- a/docs/components/rerankers/models/sentence_transformer.mdx
+++ b/docs/components/rerankers/models/sentence_transformer.mdx
@@ -36,7 +36,7 @@ config = {
"llm": {
"provider": "openai",
"config": {
- "model": "gpt-4o-mini"
+ "model": "gpt-5-mini"
}
},
"rerank": {
@@ -113,7 +113,7 @@ from mem0 import Memory
# Initialize memory with local reranker
config = {
"vector_store": {"provider": "chroma"},
- "llm": {"provider": "openai", "config": {"model": "gpt-4o-mini"}},
+ "llm": {"provider": "openai", "config": {"model": "gpt-5-mini"}},
"rerank": {
"provider": "sentence_transformer",
"config": {
diff --git a/docs/components/rerankers/models/zero_entropy.mdx b/docs/components/rerankers/models/zero_entropy.mdx
index e453ff748..cfad212c2 100644
--- a/docs/components/rerankers/models/zero_entropy.mdx
+++ b/docs/components/rerankers/models/zero_entropy.mdx
@@ -34,7 +34,7 @@ config = {
"llm": {
"provider": "openai",
"config": {
- "model": "gpt-4o-mini"
+ "model": "gpt-5-mini"
}
},
"rerank": {
@@ -98,7 +98,7 @@ os.environ["ZERO_ENTROPY_API_KEY"] = "your-api-key"
# Initialize memory with Zero Entropy reranker
config = {
"vector_store": {"provider": "chroma"},
- "llm": {"provider": "openai", "config": {"model": "gpt-4o-mini"}},
+ "llm": {"provider": "openai", "config": {"model": "gpt-5-mini"}},
"rerank": {"provider": "zero_entropy", "config": {"model": "zerank-1"}}
}
diff --git a/docs/open-source/features/reranker-search.mdx b/docs/open-source/features/reranker-search.mdx
index 535134bc2..2ae8b7dc7 100644
--- a/docs/open-source/features/reranker-search.mdx
+++ b/docs/open-source/features/reranker-search.mdx
@@ -97,7 +97,7 @@ const results = await memory.search("What movies do I like?", {
### LLM reranker
-To score with an LLM instead of a dedicated reranker, use the `llm_reranker` provider. It builds its own LLM from the reranker's config (defaulting to `openai` / `gpt-4o-mini`) rather than reusing the Memory's main `llm`:
+To score with an LLM instead of a dedicated reranker, use the `llm_reranker` provider. It builds its own LLM from the reranker's config (defaulting to `openai` / `gpt-5-mini`) rather than reusing the Memory's main `llm`:
```typescript
const memory = new Memory({
@@ -137,7 +137,7 @@ const memory = new Memory({
| `zero_entropy` | `zerank-1` | `apiKey`, `model`, `topK` |
| `sentence_transformer` | `Xenova/ms-marco-MiniLM-L-6-v2` | `model`, `device`, `maxLength`, `normalize`, `topK` |
| `huggingface` | `Xenova/bge-reranker-base` | `model`, `device`, `maxLength`, `normalize`, `topK` |
-| `llm_reranker` | `openai` / `gpt-4o-mini` | `provider`, `model`, `apiKey`, `llm` (nested override), `topK` |
+| `llm_reranker` | `openai` / `gpt-5-mini` | `provider`, `model`, `apiKey`, `llm` (nested override), `topK` |
<Note>
`rerank` is opt-in per search and a no-op when no `reranker` is configured. If the reranker call fails, Mem0 logs a warning and returns the original vector-ranked results.
diff --git a/mem0-ts/src/oss/src/utils/factory.ts b/mem0-ts/src/oss/src/utils/factory.ts
index c7ae468c4..5100867dc 100644
--- a/mem0-ts/src/oss/src/utils/factory.ts
+++ b/mem0-ts/src/oss/src/utils/factory.ts
@@ -247,7 +247,7 @@ export class RerankerFactory {
llmProvider = nested.provider || config.provider || "openai";
llmConfig = { ...(nested.config || {}) };
if (llmConfig.model === undefined) {
- llmConfig.model = config.model ?? "gpt-4o-mini";
+ llmConfig.model = config.model ?? "gpt-5-mini";
}
if (llmConfig.temperature === undefined) {
llmConfig.temperature = config.temperature ?? 0.0;
@@ -261,7 +261,7 @@ export class RerankerFactory {
} else {
llmProvider = config.provider || "openai";
llmConfig = {
- model: config.model ?? "gpt-4o-mini",
+ model: config.model ?? "gpt-5-mini",
temperature: config.temperature ?? 0.0,
maxTokens: config.maxTokens ?? 100,
};
diff --git a/mem0/configs/rerankers/llm.py b/mem0/configs/rerankers/llm.py
index de64818b5..8c398c43e 100644
--- a/mem0/configs/rerankers/llm.py
+++ b/mem0/configs/rerankers/llm.py
@@ -10,7 +10,7 @@ class LLMRerankerConfig(BaseRerankerConfig):
Configuration for LLM-based reranker.
Attributes:
- model (str): LLM model to use for reranking. Defaults to "gpt-4o-mini".
+ model (str): LLM model to use for reranking. Defaults to "gpt-5-mini".
api_key (str): API key for the LLM provider.
provider (str): LLM provider. Defaults to "openai".
top_k (int): Number of top documents to return after reranking.
@@ -20,7 +20,7 @@ class LLMRerankerConfig(BaseRerankerConfig):
"""
model: str = Field(
- default="gpt-4o-mini",
+ default="gpt-5-mini",
description="LLM model to use for reranking"
)
api_key: Optional[str] = Field(
diff --git a/mem0/reranker/llm_reranker.py b/mem0/reranker/llm_reranker.py
index cef2dee66..c5fecb14f 100644
--- a/mem0/reranker/llm_reranker.py
+++ b/mem0/reranker/llm_reranker.py
@@ -27,7 +27,7 @@ class LLMReranker(BaseReranker):
# Convert BaseRerankerConfig to LLMRerankerConfig with defaults
config = LLMRerankerConfig(
provider=getattr(config, 'provider', 'openai'),
- model=getattr(config, 'model', 'gpt-4o-mini'),
+ model=getattr(config, 'model', 'gpt-5-mini'),
api_key=getattr(config, 'api_key', None),
top_k=getattr(config, 'top_k', None),
temperature=0.0, # Default for reranking
diff --git a/tests/rerankers/test_llm_reranker_config.py b/tests/rerankers/test_llm_reranker_config.py
index d3577a49b..69f4df96d 100644
--- a/tests/rerankers/test_llm_reranker_config.py
+++ b/tests/rerankers/test_llm_reranker_config.py
@@ -6,7 +6,7 @@ from mem0.reranker.llm_reranker import LLMReranker
class TestLLMRerankerConfig:
def test_default_config(self):
config = LLMRerankerConfig()
- assert config.model == "gpt-4o-mini"
+ assert config.model == "gpt-5-mini"
assert config.provider == "openai"
assert config.temperature == 0.0
assert config.max_tokens == 100