JDSS/mem0
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(sdk): removing deprecating param from our sdk and docs changes with it (#4740)

Browse Source
This commit is contained in:
Kartik
2026-04-12 00:34:58 +05:30
committed by GitHub
parent 3882af7450
commit e44b46ef2e
138 changed files with 1186 additions and 2840 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/open-source/features/async-memory.mdx
+2 -2
View File
@@ -240,7 +240,7 @@ async_openai_client = AsyncOpenAI()
async_memory = AsyncMemory()
async def chat_with_memories(message: str, user_id: str = "default_user") -> str:
search_result = await async_memory.search(query=message, user_id=user_id, limit=3)
search_result = await async_memory.search(query=message, user_id=user_id, top_k=3)
relevant_memories = search_result["results"]
memories_str = "\n".join(f"- {entry['memory']}" for entry in relevant_memories)
@@ -326,7 +326,7 @@ async def add_memory(messages: list, user_id: str):
@app.get("/memories/search")
async def search_memories(query: str, user_id: str, limit: int = 10):
try:
result = await memory.search(query=query, user_id=user_id, limit=limit)
result = await memory.search(query=query, user_id=user_id, top_k=limit)
return {"status": "success", "data": result}
except Exception as exc:
raise HTTPException(status_code=500, detail=str(exc))
docs/open-source/features/custom-fact-extraction-prompt.mdx → docs/open-source/features/custom-instructions.mdx
+17 -13
View File
@@ -1,13 +1,13 @@
---
title: Custom Fact Extraction Prompt
title: Custom Instructions
description: Tailor fact extraction so Mem0 stores only the details you care about.
icon: "wand-magic-sparkles"
---
Custom fact extraction prompts let you decide exactly which facts Mem0 records from a conversation. Define a focused prompt, give a few examples, and Mem0 will add only the memories that match your use case.
Custom instructions let you decide exactly which facts Mem0 records from a conversation. Define a focused prompt, give a few examples, and Mem0 will add only the memories that match your use case.
<Info>
**You’ll use this when…**
**You'll use this when...**
- A project needs domain-specific facts (order numbers, customer info) without storing casual chatter.
- You already have a clear schema for memories and want the LLM to follow it.
- You must prevent irrelevant details from entering long-term storage.
@@ -17,6 +17,10 @@ Custom fact extraction prompts let you decide exactly which facts Mem0 records f
Prompts that are too broad cause unrelated facts to slip through. Keep instructions tight and test them with real transcripts.
</Warning>
<Note>
The `custom_fact_extraction_prompt` parameter has been renamed to `custom_instructions`. If you are upgrading from an older version, update your configuration accordingly.
</Note>
---
## Feature anatomy
@@ -24,13 +28,13 @@ Custom fact extraction prompts let you decide exactly which facts Mem0 records f
- **Prompt instructions:** Describe which entities or phrases to keep. Specific guidance keeps the extractor focused.
- **Few-shot examples:** Show positive and negative cases so the model copies the right format.
- **Structured output:** Responses return JSON with a `facts` array that Mem0 converts into individual memories.
- **LLM configuration:** `custom_fact_extraction_prompt` (Python) or `customPrompt` (TypeScript) lives alongside your model settings.
- **LLM configuration:** `custom_instructions` (Python) or `customInstructions` (TypeScript) lives alongside your model settings.
<AccordionGroup>
<Accordion title="Prompt blueprint">
1. State the allowed fact types.
2. Include short examples that mirror production messages.
3. Show both empty (`[]`) and populated outputs.
1. State the allowed fact types.
2. Include short examples that mirror production messages.
3. Show both empty (`[]`) and populated outputs.
4. Remind the model to return JSON with a `facts` key only.
</Accordion>
</AccordionGroup>
@@ -43,8 +47,8 @@ Custom fact extraction prompts let you decide exactly which facts Mem0 records f
<CodeGroup>
```python Python
custom_fact_extraction_prompt = """
Please only extract entities containing customer support information, order details, and user information.
custom_instructions = """
Please only extract entities containing customer support information, order details, and user information.
Here are some few shot examples:
Input: Hi.
@@ -67,8 +71,8 @@ Return the facts and customer information in a json format as shown above.
```
```ts TypeScript
const customPrompt = `
Please only extract entities containing customer support information, order details, and user information.
const customInstructions = `
Please only extract entities containing customer support information, order details, and user information.
Here are some few shot examples:
Input: Hi.
@@ -110,7 +114,7 @@ config = {
"max_tokens": 2000,
}
},
"custom_fact_extraction_prompt": custom_fact_extraction_prompt,
"custom_instructions": custom_instructions,
"version": "v1.1"
}
@@ -131,7 +135,7 @@ const config = {
maxTokens: 1500,
},
},
customPrompt: customPrompt,
customInstructions: customInstructions,
};
const memory = new Memory(config);
docs/open-source/features/custom-update-memory-prompt.mdx
+3 -3
View File
@@ -263,7 +263,7 @@ Please note to return the IDs in the output from the input IDs only and do not g
- Log each decision so product teams can review why a change happened.
<Note>
The prompt works alongside `custom_fact_extraction_prompt`—fact extraction identifies candidate facts, and the update prompt decides how to merge them into long-term storage.
The prompt works alongside `custom_instructions`—fact extraction identifies candidate facts, and the update prompt decides how to merge them into long-term storage.
</Note>
---
@@ -288,7 +288,7 @@ Please note to return the IDs in the output from the input IDs only and do not g
## Compare prompts
| Feature | `custom_update_memory_prompt` | `custom_fact_extraction_prompt` |
| Feature | `custom_update_memory_prompt` | `custom_instructions` |
| --- | --- | --- |
| Primary job | Decide memory actions (ADD/UPDATE/DELETE/NONE) | Pull facts from user and assistant messages |
| Inputs | Retrieved facts + existing memory entries | Raw conversation turns |
@@ -297,7 +297,7 @@ Please note to return the IDs in the output from the input IDs only and do not g
---
<CardGroup cols={2}>
<Card title="Design Fact Extraction" icon="sparkles" href="/open-source/features/custom-fact-extraction-prompt">
<Card title="Design Fact Extraction" icon="sparkles" href="/open-source/features/custom-instructions">
Coordinate both prompts so fact extraction feeds clean inputs into the update flow.
</Card>
<Card title="Build Email Automations" icon="inbox" href="/cookbooks/operations/email-automation">
docs/open-source/features/graph-memory.mdx
+4 -4
View File
@@ -94,7 +94,7 @@ memory.add(conversation, user_id="demo-user")
results = memory.search(
"Who did Alice meet at GraphConf?",
user_id="demo-user",
limit=3,
top_k=3,
rerank=True,
)
@@ -146,7 +146,7 @@ await memory.add(conversation, { userId: "demo-user" });
const results = await memory.search(
"Who did Alice meet at GraphConf?",
{ userId: "demo-user", limit: 3, rerank: true }
{ userId: "demo-user", topK: 3, rerank: true }
);
results.results.forEach((hit) => {
@@ -204,7 +204,7 @@ const config = {
username: process.env.NEO4J_USERNAME!,
password: process.env.NEO4J_PASSWORD!,
},
customPrompt: "Please only capture people, organisations, and project links.",
customInstructions: "Please only capture people, organisations, and project links.",
}
};
@@ -265,7 +265,7 @@ Monitor graph growth, especially on free tiers, by periodically cleaning dormant
## Decision Points
- Select the graph store that fits your deployment (managed Aura vs. self-hosted Neo4j vs. AWS Neptune vs. local Kuzu vs. Apache AGE on PostgreSQL).
- Decide when to enable graph writes per request; routine conversations may stay vector-only to save latency.
- Decide whether to include a graph store in your config; routine conversations may stay vector-only to save latency.
- Set a policy for pruning stale relationships so your graph stays fast and affordable.
## Provider setup
docs/open-source/features/openai_compatibility.mdx
+1 -1
View File
@@ -131,7 +131,7 @@ print(response.choices[0].message.content)
| `run_id` | `str` | Optional session/run identifier for short-lived flows. |
| `metadata` | `dict` | Store extra fields alongside each memory entry. |
| `filters` | `dict` | Restrict retrieval to specific memories while responding. |
| `limit` | `int` | Cap how many memories Mem0 pulls into the context (default 10). |
| `top_k` | `int` | Cap how many memories Mem0 pulls into the context (default 10). |
Other request fields mirror OpenAI’s chat completion API.
docs/open-source/features/overview.mdx
+1 -1
View File
@@ -30,7 +30,7 @@ Mem0 Open Source ships with capabilities that adapt memory behavior for producti
<Card title="Multimodal Support" icon="image" href="/open-source/features/multimodal-support">
Process images, audio, and video memories.
</Card>
<Card title="Custom Fact Extraction" icon="wand-magic-sparkles" href="/open-source/features/custom-fact-extraction-prompt">
<Card title="Custom Instructions" icon="wand-magic-sparkles" href="/open-source/features/custom-instructions">
Tailor how facts are extracted from text.
</Card>
</CardGroup>
docs/open-source/features/reranker-search.mdx
+2 -2
View File
@@ -321,7 +321,7 @@ results = m.search(
]
},
rerank=True,
limit=20
top_k=20
)
```
@@ -366,7 +366,7 @@ results = m.search(
user_id="reader123",
filters={"content_type": "book_recommendation"},
rerank=True,
limit=10
top_k=10
)
for result in results["results"]:
docs/open-source/node-quickstart.mdx
+2 -2
View File
@@ -230,7 +230,7 @@ Mem0 offers granular configuration across vector stores, LLMs, embedders, and hi
| --- | --- | --- |
| `historyDbPath` | Path to history database | `"{mem0_dir}/history.db"` |
| `version` | API version | `"v1.0"` |
| `customPrompt` | Custom processing prompt | `undefined` |
| `customInstructions` | Custom processing prompt | `undefined` |
</Accordion>
<Accordion title="History store">
| Parameter | Description | Default |
@@ -273,7 +273,7 @@ const config = {
}
},
disableHistory: false,
customPrompt: "I'm a virtual assistant. I'm here to help you with your queries."
customInstructions: "I'm a virtual assistant. I'm here to help you with your queries."
};
```
</Accordion>