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
Updated docs to add the "Direct Memory Storage" feature (#1966)
Prateek Chhikara4661d55913dc
diff --git a/docs/features/direct-import.mdx b/docs/features/direct-import.mdxnew file mode 100644index 000000000..94901952a--- /dev/null+++ b/docs/features/direct-import.mdx@@ -0,0 +1,102 @@+---+title: Direct Import+description: 'Bypass the memory deduction phase and directly store pre-defined memories for efficient retrieval'+---++## How to use Direct Import?+The Direct Import feature allows users to skip the memory deduction phase and directly input pre-defined memories into the system for storage and retrieval.+To enable this feature, you need to set the `infer` parameter to `False` in the `add` method.+++<CodeGroup>+++```python Python+messages = [+ {"role": "user", "content": "Alice loves playing badminton"},+ {"role": "assistant", "content": "That's great! Alice is a fitness freak"},+ {"role": "user", "content": "Alice mostly cook at home because of gym plan"},+]+++client.add(messages, user_id="alice", infer=False)+```++```markdown Output+[]+```+</CodeGroup>++You can see that the output of add call is an empty list.++<Note> Only messages with the role "user" will be used for storage. Messages with roles such as "assistant" or "system" will be ignored during the storage process. </Note>+++## How to retrieve memories?++You can retrieve memories using the `search` method.++<CodeGroup>++```python Python+client.search(query="What is Alice's favorite sport?", user_id="alice", output_format="v1.1")+```++```json Output+{+ "results": [+ {+ "id": "19d6d7aa-2454-4e58-96fc-e74d9e9f8dd1",+ "memory": "Alice loves playing badminton",+ "user_id": "pc123",+ "metadata": null,+ "categories": null,+ "created_at": "2024-10-15T21:52:11.474901-07:00",+ "updated_at": "2024-10-15T21:52:11.474912-07:00"+ }+ ]+}+```++</CodeGroup>++## How to retrieve all memories?++You can retrieve all memories using the `get_all` method.++<CodeGroup>++```python Python+client.get_all(query="What is Alice's favorite sport?", user_id="alice", output_format="v1.1")+```++```json Output+{+ "results": [+ {+ "id": "19d6d7aa-2454-4e58-96fc-e74d9e9f8dd1",+ "memory": "Alice loves playing badminton",+ "user_id": "pc123",+ "metadata": null,+ "categories": null,+ "created_at": "2024-10-15T21:52:11.474901-07:00",+ "updated_at": "2024-10-15T21:52:11.474912-07:00"+ },+ {+ "id": "8557f05d-7b3c-47e5-b409-9886f9e314fc",+ "memory": "Alice mostly cook at home because of gym plan",+ "user_id": "pc123",+ "metadata": null,+ "categories": null,+ "created_at": "2024-10-15T21:52:11.474929-07:00",+ "updated_at": "2024-10-15T21:52:11.474932-07:00"+ }+ ]+}+```++</CodeGroup>++If you have any questions, please feel free to reach out to us using one of the following methods:++<Snippet file="get-help.mdx" />\ No newline at end of filediff --git a/docs/mint.json b/docs/mint.jsonindex 2e54ba3c5..f5a168f76 100644--- a/docs/mint.json+++ b/docs/mint.json@@ -64,7 +64,7 @@"platform/quickstart",{"group": "Features",- "pages": ["features/selective-memory", "features/custom-categories"]+ "pages": ["features/selective-memory", "features/custom-categories", "features/direct-import"]}]},