The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.
Python agentic-memoryagentic-memory-systemagentsaiai-agentschatgptgenaillmlong-term-memorymemorymemory-managementpythonragstate-management
Added custom prompt support (#1849)
Prateek Chhikaraac7b7aa20a6b
diff --git a/docs/features/custom-prompts.mdx b/docs/features/custom-prompts.mdxnew file mode 100644index 000000000..ff6fe0e67--- /dev/null+++ b/docs/features/custom-prompts.mdx@@ -0,0 +1,109 @@+---+title: Custom Prompts+description: 'Enhance your product experience by adding custom prompts tailored to your needs'+---++## Introduction to Custom Prompts++Custom prompts allow you to tailor the behavior of your Mem0 instance to specific use cases or domains.+By defining a custom prompt, you can control how information is extracted, processed, and stored in your memory system.++To create an effective custom prompt:+1. Be specific about the information to extract.+2. Provide few-shot examples to guide the LLM.+3. Ensure examples follow the format shown below.++Example of a custom prompt:++```python+custom_prompt = """+Please only extract entities containing customer support information, order details, and user information.+Here are some few shot examples:++Input: Hi.+Output: {{"facts" : []}}++Input: The weather is nice today.+Output: {{"facts" : []}}++Input: My order #12345 hasn't arrived yet.+Output: {{"facts" : ["Order #12345 not received"]}}++Input: I'm John Doe, and I'd like to return the shoes I bought last week.+Output: {{"facts" : ["Customer name: John Doe", "Wants to return shoes", "Purchase made last week"]}}++Input: I ordered a red shirt, size medium, but received a blue one instead.+Output: {{"facts" : ["Ordered red shirt, size medium", "Received blue shirt instead"]}}++Return the facts and customer information in a json format as shown above.+"""++```++Here we initialize the custom prompt in the config.++```python+from mem0 import Memory++config = {+ "llm": {+ "provider": "openai",+ "config": {+ "model": "gpt-4o",+ "temperature": 0.2,+ "max_tokens": 1500,+ }+ },+ "custom_prompt": custom_prompt,+ "version": "v1.1"+}++m = Memory.from_config(config_dict=config, user_id="alice")+```++### Example 1++In this example, we are adding a memory of a user ordering a laptop. As seen in the output, the custom prompt is used to extract the relevant information from the user's message.++<CodeGroup>+```python Code+m.add("Yesterday, I ordered a laptop, the order id is 12345", user_id="alice")+```++```json Output+{+ "results": [+ {+ "memory": "Ordered a laptop",+ "event": "ADD"+ },+ {+ "memory": "Order ID: 12345",+ "event": "ADD"+ },+ {+ "memory": "Order placed yesterday",+ "event": "ADD"+ }+ ],+ "relations": []+}+```+</CodeGroup>++### Example 2++In this example, we are adding a memory of a user liking to go on hikes. This add message is not specific to the use-case mentioned in the custom prompt.+Hence, the memory is not added.+<CodeGroup>+```python Code+m.add("I like going to hikes", user_id="alice")+```++```json Output+{+ "results": [],+ "relations": []+}+```+</CodeGroup>diff --git a/docs/mint.json b/docs/mint.jsonindex 481b79286..a21c0ccaa 100644--- a/docs/mint.json+++ b/docs/mint.json@@ -131,7 +131,7 @@},{"group": "Features",- "pages": ["features/openai_compatibility"]+ "pages": ["features/openai_compatibility", "features/custom-prompts"]}]},diff --git a/mem0/configs/base.py b/mem0/configs/base.pyindex 42a0a2b24..a83e00d6f 100644--- a/mem0/configs/base.py+++ b/mem0/configs/base.py@@ -56,6 +56,10 @@ class MemoryConfig(BaseModel):description="The version of the API",default="v1.0",)+ custom_prompt: Optional[str] = Field(+ description="Custom prompt for the memory",+ default=None,+ )class AzureConfig(BaseModel):diff --git a/mem0/memory/main.py b/mem0/memory/main.pyindex a3bb50247..5516227cb 100644--- a/mem0/memory/main.py+++ b/mem0/memory/main.py@@ -28,6 +28,8 @@ logger = logging.getLogger(__name__)class Memory(MemoryBase):def __init__(self, config: MemoryConfig = MemoryConfig()):self.config = config++ self.custom_prompt = self.config.custom_promptself.embedding_model = EmbedderFactory.create(self.config.embedder.provider, self.config.embedder.config)@@ -131,7 +133,11 @@ class Memory(MemoryBase):def _add_to_vector_store(self, messages, metadata, filters):parsed_messages = parse_messages(messages)- system_prompt, user_prompt = get_fact_retrieval_messages(parsed_messages)+ if self.custom_prompt:+ system_prompt=self.custom_prompt+ user_prompt=f"Input: {parsed_messages}"+ else:+ system_prompt, user_prompt = get_fact_retrieval_messages(parsed_messages)response = self.llm.generate_response(messages=[{"role": "system", "content": system_prompt}, {"role": "user", "content": user_prompt}],diff --git a/pyproject.toml b/pyproject.tomlindex f006eb78f..df07a5188 100644--- a/pyproject.toml+++ b/pyproject.toml@@ -1,6 +1,6 @@[tool.poetry]name = "mem0ai"-version = "0.1.12"+version = "0.1.13"description = "Long-term memory for AI Agents"authors = ["Mem0 <[email protected]>"]exclude = [