From 5bc0f0c87cb5d640d4be773b149305ce29daa3bd Mon Sep 17 00:00:00 2001 From: agumpandey Date: Tue, 12 May 2026 23:58:38 +0530 Subject: [PATCH] docs: clean temporal reasoning wording --- docs/platform/features/temporal-reasoning.mdx | 24 +++++++++---------- 1 file changed, 12 insertions(+), 12 deletions(-) diff --git a/docs/platform/features/temporal-reasoning.mdx b/docs/platform/features/temporal-reasoning.mdx index 8133c0825..144f95044 100644 --- a/docs/platform/features/temporal-reasoning.mdx +++ b/docs/platform/features/temporal-reasoning.mdx @@ -30,22 +30,22 @@ client = MemoryClient(api_key="your-api-key") ## How it works -Temporal Reasoning has two public-facing parts: +Temporal Reasoning works in two parts: - **Write-time enrichment**: when Mem0 stores a memory, it can infer internal temporal structure when that information is present in the text. - **Search-time interpretation**: when a query includes time language like `last week`, `upcoming`, or `right now`, Mem0 uses internal temporal signals to return more appropriate results. -### Memory types +### Temporal patterns -Mem0 normalizes temporal memories into a small set of internal classes: +Mem0 handles several common temporal patterns: -| Type | What it represents | Example | +| Pattern | What it represents | Example | | --- | --- | --- | -| `event` | A dated occurrence | "I finished the Q1 review on March 10, 2025." | -| `plan` | A future commitment or scheduled item | "I have a dentist appointment on March 18, 2025." | -| `state` | An ongoing fact that can remain true over time | "I am the product lead at Acme Corp." | -| `relationship` | A durable connection between people or entities | "Priya manages Jordan." | -| `preference` | A stable preference or habit | "I prefer morning meetings." | +| Dated occurrence | Something that happened at a known time | "I finished the Q1 review on March 10, 2025." | +| Future plan | A future commitment or scheduled item | "I have a dentist appointment on March 18, 2025." | +| Ongoing state | A fact that can remain true over time | "I am the product lead at Acme Corp." | +| Relationship | A durable connection between people or entities | "Priya manages Jordan." | +| Preference | A stable preference or habit | "I prefer morning meetings." | At search time, Temporal Reasoning influences how results are ranked. The ranking effect is transparent: results come back in the normal shape. @@ -96,7 +96,7 @@ const results = await client.search("what did I do last week?", { - `reference_date` is especially useful for tests, backfills, and cookbook examples because it makes relative phrases reproducible. + `reference_date` is especially useful for tests and backfills because it makes relative phrases reproducible. ## See it in action @@ -170,7 +170,7 @@ results.results.forEach((item) => { - Expected behavior: the March 10 review appears as a past `event`, the April 18 appointment does not lead this result set, and the ongoing role at Acme does not crowd out the dated answer. + Expected behavior: the March 10 review leads this result set, the April 18 appointment does not, and the ongoing role at Acme does not crowd out the dated answer. ## Supported query patterns @@ -206,7 +206,7 @@ results.results.forEach((item) => { - Keep search scoped with `filters` so time-aware ranking runs inside the right entity boundary. - Use `reference_date` in automated tests and reproducible demos. - + Anchor imported memories to when they actually happened.