Compare commits
| Author | SHA1 | Date | |
|---|---|---|---|
 kartik-mem0andClaude Opus 4.6
|
b38f2ef45c | ||
|
kartik-mem0andClaude Opus 4.6
|
b1dbd08c63 | ||
|
kartik-mem0andClaude Sonnet 4.6
|
269d784c0f | ||
|
kartik-mem0andClaude Sonnet 4.6
|
72c2a7f322 | ||
|
kartik-mem0andClaude Sonnet 4.6
|
a930603c12 | ||
|
kartik-mem0andClaude Sonnet 4.6
|
b53507efd3 | ||
|
kartik-mem0andClaude Sonnet 4.6
|
fb430b1a32 | ||
|
Longwei Liu
|
7e0968bbc8 |
@@ -7,11 +7,6 @@ mode: "wide"
|
||||
<Tabs>
|
||||
<Tab title="Python">
|
||||
|
||||
<Update label="2026-03-03" description="v1.0.5">
|
||||
- **Telemetry Fix**
|
||||
- Fixed an issue where the PostHog client was initialized even after telemetry was disabled. Although events were not captured, the client was unnecessarily initialized.
|
||||
</Update>
|
||||
|
||||
<Update label="2026-02-17" description="v1.0.4">
|
||||
|
||||
**New Features & Updates:**
|
||||
|
||||
@@ -107,12 +107,6 @@ client = MemoryClient(api_key="your-api-key")
|
||||
|
||||
# Delete all memories for a specific user
|
||||
client.delete_all(user_id="alice")
|
||||
|
||||
# Delete all memories for a specific agent
|
||||
client.delete_all(agent_id="support-bot")
|
||||
|
||||
# Delete all memories for a specific run
|
||||
client.delete_all(run_id="session-xyz")
|
||||
```
|
||||
|
||||
```javascript JavaScript
|
||||
@@ -133,48 +127,7 @@ You can also filter by other parameters such as:
|
||||
- `metadata` (as JSON string)
|
||||
|
||||
<Warning>
|
||||
**Breaking change:** `delete_all` previously wiped all project memories when called with no filters. It now **raises an error** if no filters are provided. Use `"*"` wildcards for intentional bulk deletion (see below).
|
||||
</Warning>
|
||||
|
||||
### Wildcard deletes
|
||||
|
||||
Setting a filter to `"*"` deletes **all memories** for that entity type across the entire project. This is an intentionally explicit opt-in to bulk deletion.
|
||||
|
||||
<CodeGroup>
|
||||
```python Python
|
||||
from mem0 import MemoryClient
|
||||
|
||||
client = MemoryClient(api_key="your-api-key")
|
||||
|
||||
# Delete all memories across every user in the project
|
||||
client.delete_all(user_id="*")
|
||||
|
||||
# Delete all memories across every agent in the project
|
||||
client.delete_all(agent_id="*")
|
||||
|
||||
# Full project wipe — all four filters must be explicitly set to "*"
|
||||
client.delete_all(user_id="*", agent_id="*", app_id="*", run_id="*")
|
||||
```
|
||||
|
||||
```javascript JavaScript
|
||||
import MemoryClient from 'mem0ai';
|
||||
|
||||
const client = new MemoryClient({ apiKey: "your-api-key" });
|
||||
|
||||
// Delete all memories across every user in the project
|
||||
client.deleteAll({ user_id: "*" })
|
||||
.then(result => console.log(result))
|
||||
.catch(error => console.error(error));
|
||||
|
||||
// Full project wipe — all four filters must be explicitly set to "*"
|
||||
client.deleteAll({ user_id: "*", agent_id: "*", app_id: "*", run_id: "*" })
|
||||
.then(result => console.log(result))
|
||||
.catch(error => console.error(error));
|
||||
```
|
||||
</CodeGroup>
|
||||
|
||||
<Warning>
|
||||
A full project wipe requires **all four** filters set to `"*"`. Setting only some to `"*"` deletes memories only for those entity types, not the entire project.
|
||||
`delete_all` requires at least one filter (user, agent, run, or metadata). Calling it with no filters raises an error to prevent accidental data loss.
|
||||
</Warning>
|
||||
|
||||
## Delete with Mem0 OSS
|
||||
|
||||
@@ -255,28 +255,13 @@ def delete(
|
||||
|
||||
### delete_all() Method
|
||||
|
||||
#### Breaking Change — Empty filter no longer silently deletes everything
|
||||
|
||||
**Before:** calling `delete_all()` with no filters silently deleted **all memories in the project**.
|
||||
|
||||
**After:**
|
||||
- No filters → raises a validation error (prevents accidental full-project wipe).
|
||||
- Concrete ID (e.g. `user_id="alice"`) → deletes memories for that entity (unchanged).
|
||||
- `"*"` for a filter → deletes all memories for that entity type across the project (new).
|
||||
- All four filters set to `"*"` → explicit full project wipe (new, requires opt-in on every parameter).
|
||||
|
||||
This change replaces the silent full-project delete (triggered by an empty or missing filter) with a validation error, and introduces `"*"` wildcards as the intentional path for bulk deletion.
|
||||
|
||||
#### No Breaking Changes
|
||||
```python
|
||||
# v0.x — no filter silently wiped all project memories
|
||||
m.delete_all() # DANGER: deleted everything
|
||||
m.delete_all(user_id="alice") # deleted alice's memories
|
||||
|
||||
# v1.x — no filter now raises an error; use "*" for intentional bulk deletes
|
||||
m.delete_all() # ERROR: at least one filter required
|
||||
m.delete_all(user_id="alice") # unchanged
|
||||
m.delete_all(user_id="*") # NEW — delete all users' memories
|
||||
m.delete_all(user_id="*", agent_id="*", app_id="*", run_id="*") # NEW — full project wipe
|
||||
# Same signature in both versions
|
||||
def delete_all(
|
||||
self,
|
||||
user_id: str
|
||||
) -> dict
|
||||
```
|
||||
|
||||
## Platform Client (MemoryClient) Changes
|
||||
|
||||
+13
-13
@@ -1180,7 +1180,7 @@
|
||||
"tags": [
|
||||
"memories"
|
||||
],
|
||||
"description": "Delete memories by filter. At least one filter is required — previously omitting all filters silently deleted everything; now it returns a validation error.",
|
||||
"description": "Delete memories.",
|
||||
"operationId": "memories_delete",
|
||||
"parameters": [
|
||||
{
|
||||
@@ -1189,7 +1189,7 @@
|
||||
"schema": {
|
||||
"type": "string"
|
||||
},
|
||||
"description": "Filter by user ID. Pass `*` to delete memories for all users."
|
||||
"description": "Filter memories by user ID."
|
||||
},
|
||||
{
|
||||
"name": "agent_id",
|
||||
@@ -1197,7 +1197,7 @@
|
||||
"schema": {
|
||||
"type": "string"
|
||||
},
|
||||
"description": "Filter by agent ID. Pass `*` to delete memories for all agents."
|
||||
"description": "Filter memories by agent ID."
|
||||
},
|
||||
{
|
||||
"name": "app_id",
|
||||
@@ -1205,7 +1205,7 @@
|
||||
"schema": {
|
||||
"type": "string"
|
||||
},
|
||||
"description": "Filter by app ID. Pass `*` to delete memories for all apps."
|
||||
"description": "Filter memories by app ID."
|
||||
},
|
||||
{
|
||||
"name": "run_id",
|
||||
@@ -1213,7 +1213,7 @@
|
||||
"schema": {
|
||||
"type": "string"
|
||||
},
|
||||
"description": "Filter by run ID. Pass `*` to delete memories for all runs."
|
||||
"description": "Filter memories by run ID."
|
||||
},
|
||||
{
|
||||
"name": "metadata",
|
||||
@@ -1263,15 +1263,15 @@
|
||||
"x-code-samples": [
|
||||
{
|
||||
"lang": "Python",
|
||||
"source": "# To use the Python SDK, install the package:\n# pip install mem0ai\n\nfrom mem0 import MemoryClient\nclient = MemoryClient(api_key=\"your_api_key\", org_id=\"your_org_id\", project_id=\"your_project_id\")\n\n# Delete all memories for a specific user\nclient.delete_all(user_id=\"<user_id>\")\n\n# Delete all memories for every user in the project (wildcard)\nclient.delete_all(user_id=\"*\")\n\n# Full project wipe — all four filters must be explicitly set to \"*\"\nclient.delete_all(user_id=\"*\", agent_id=\"*\", app_id=\"*\", run_id=\"*\")\n\n# NOTE: Calling delete_all() with no filters raises a validation error.\n# At least one filter is required to prevent accidental data loss."
|
||||
"source": "# To use the Python SDK, install the package:\n# pip install mem0ai\n\nfrom mem0 import MemoryClient\nclient = MemoryClient(api_key=\"your_api_key\", org_id=\"your_org_id\", project_id=\"your_project_id\")\n\n# Delete all memories for a specific user\nclient.delete_all(user_id=\"<user_id>\")"
|
||||
},
|
||||
{
|
||||
"lang": "JavaScript",
|
||||
"source": "// To use the JavaScript SDK, install the package:\n// npm i mem0ai\n\nimport MemoryClient from 'mem0ai';\nconst client = new MemoryClient({ apiKey: \"your-api-key\" });\n\n// Delete all memories for a specific user\nclient.deleteAll({ user_id: \"<user_id>\" })\n .then(result => console.log(result))\n .catch(error => console.error(error));\n\n// Delete all memories for every user in the project (wildcard)\nclient.deleteAll({ user_id: \"*\" })\n .then(result => console.log(result))\n .catch(error => console.error(error));\n\n// Full project wipe — all four filters must be explicitly set to \"*\"\nclient.deleteAll({ user_id: \"*\", agent_id: \"*\", app_id: \"*\", run_id: \"*\" })\n .then(result => console.log(result))\n .catch(error => console.error(error));"
|
||||
"source": "// To use the JavaScript SDK, install the package:\n// npm i mem0ai\n\nimport MemoryClient from 'mem0ai';\nconst client = new MemoryClient({ apiKey: \"your-api-key\" });\n\n// Delete all memories for a specific user\nclient.deleteAll({ user_id: \"<user_id>\" })\n .then(result => console.log(result))\n .catch(error => console.error(error));"
|
||||
},
|
||||
{
|
||||
"lang": "cURL",
|
||||
"source": "# Delete memories for a specific user\ncurl --request DELETE \\\n --url 'https://api.mem0.ai/v1/memories/?user_id=<user_id>' \\\n --header 'Authorization: Token <api-key>'\n\n# Delete memories for all users (wildcard)\ncurl --request DELETE \\\n --url 'https://api.mem0.ai/v1/memories/?user_id=*' \\\n --header 'Authorization: Token <api-key>'\n\n# Full project wipe — all four filters must be set to *\ncurl --request DELETE \\\n --url 'https://api.mem0.ai/v1/memories/?user_id=*&agent_id=*&app_id=*&run_id=*' \\\n --header 'Authorization: Token <api-key>'"
|
||||
"source": "curl --request DELETE \\\n --url https://api.mem0.ai/v1/memories/ \\\n --header 'Authorization: Token <api-key>'"
|
||||
},
|
||||
{
|
||||
"lang": "Go",
|
||||
@@ -5570,26 +5570,26 @@
|
||||
},
|
||||
"DeleteMemoriesInput": {
|
||||
"type": "object",
|
||||
"description": "Filters for bulk memory deletion. At least one field is required. Pass \"*\" for a field to delete all memories for that entity type. Set all four to \"*\" for a full project wipe.",
|
||||
"description": "Input for deleting memories associated with a specific user, agent, app, or run.",
|
||||
"properties": {
|
||||
"user_id": {
|
||||
"type": "string",
|
||||
"description": "User ID to delete memories for. Pass \"*\" for all users.",
|
||||
"description": "The unique identifier of the user whose memories should be deleted.",
|
||||
"nullable": true
|
||||
},
|
||||
"agent_id": {
|
||||
"type": "string",
|
||||
"description": "Agent ID to delete memories for. Pass \"*\" for all agents.",
|
||||
"description": "The unique identifier of the agent whose memories should be deleted.",
|
||||
"nullable": true
|
||||
},
|
||||
"app_id": {
|
||||
"type": "string",
|
||||
"description": "App ID to delete memories for. Pass \"*\" for all apps.",
|
||||
"description": "The unique identifier of the application whose memories should be deleted.",
|
||||
"nullable": true
|
||||
},
|
||||
"run_id": {
|
||||
"type": "string",
|
||||
"description": "Run ID to delete memories for. Pass \"*\" for all runs.",
|
||||
"description": "The unique identifier of the run whose memories should be deleted.",
|
||||
"nullable": true
|
||||
}
|
||||
},
|
||||
|
||||
@@ -123,10 +123,6 @@ await client.deleteAll({ user_id: "alice" });
|
||||
|
||||
</CodeGroup>
|
||||
|
||||
<Note>
|
||||
At least one filter (`user_id`, `agent_id`, `app_id`, or `run_id`) is required — calling `delete_all` with no filters raises an error to prevent accidental data loss. You can pass `"*"` as a value to delete all memories for a given entity type (e.g., `user_id="*"` removes memories for every user). A full project wipe requires all four filters set to `"*"`.
|
||||
</Note>
|
||||
|
||||
### History
|
||||
|
||||
Get the history of a specific memory asynchronously.
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "mem0ai",
|
||||
"version": "2.2.4",
|
||||
"version": "2.2.3",
|
||||
"description": "The Memory Layer For Your AI Apps",
|
||||
"main": "./dist/index.js",
|
||||
"module": "./dist/index.mjs",
|
||||
@@ -91,7 +91,7 @@
|
||||
"typescript": "5.5.4"
|
||||
},
|
||||
"dependencies": {
|
||||
"axios": "1.13.6",
|
||||
"axios": "1.7.7",
|
||||
"openai": "^4.93.0",
|
||||
"uuid": "9.0.1",
|
||||
"zod": "^3.24.1"
|
||||
|
||||
Generated
+10
-25
@@ -44,8 +44,8 @@ importers:
|
||||
specifier: 3.1.11
|
||||
version: 3.1.11
|
||||
axios:
|
||||
specifier: 1.13.6
|
||||
version: 1.13.6
|
||||
specifier: 1.7.7
|
||||
version: 1.7.7
|
||||
cloudflare:
|
||||
specifier: ^4.2.0
|
||||
version: 4.3.0(encoding@0.1.13)
|
||||
@@ -1621,10 +1621,10 @@ packages:
|
||||
integrity: sha512-Oei9OH4tRh0YqU3GxhX79dM/mwVgvbZJaSNaRk+bshkj0S5cfHcgYakreBjrHwatXKbz+IoIdYLxrKim2MjW0Q==,
|
||||
}
|
||||
|
||||
axios@1.13.6:
|
||||
axios@1.7.7:
|
||||
resolution:
|
||||
{
|
||||
integrity: sha512-ChTCHMouEe2kn713WHbQGcuYrr6fXTBiu460OTwWrWob16g1bXn4vtz07Ope7ewMozJAnEquLk5lWQWtBig9DQ==,
|
||||
integrity: sha512-S4kL7XrjgBmvdGut0sN3yJxqYzrDOnivkBiN0OFs6hLiUam3UPvswUo0kqGyhqUZGEOytHyumEdXsAkgCOUf3Q==,
|
||||
}
|
||||
|
||||
babel-jest@29.7.0:
|
||||
@@ -2560,10 +2560,10 @@ packages:
|
||||
}
|
||||
hasBin: true
|
||||
|
||||
follow-redirects@1.15.11:
|
||||
follow-redirects@1.15.9:
|
||||
resolution:
|
||||
{
|
||||
integrity: sha512-deG2P0JfjrTxl50XGCDyfI97ZGVCxIpfKYmfyrQ54n5FO/0gfIES8C/Psl6kWVDolizcaaxZJnTS0QSMxvnsBQ==,
|
||||
integrity: sha512-gew4GsXizNgdoRyqmyfMHyAmXsZDk6mHkSxZFCzW9gwlbtOW44CDtYavM+y+72qD/Vq2l550kMF52DT8fOLJqQ==,
|
||||
}
|
||||
engines: { node: ">=4.0" }
|
||||
peerDependencies:
|
||||
@@ -2592,13 +2592,6 @@ packages:
|
||||
}
|
||||
engines: { node: ">= 6" }
|
||||
|
||||
form-data@4.0.5:
|
||||
resolution:
|
||||
{
|
||||
integrity: sha512-8RipRLol37bNs2bhoV67fiTEvdTrbMUYcFTiy3+wuuOnUog2QBHCZWXDRijWQfAkhBj2Uf5UnVaiWwA5vdd82w==,
|
||||
}
|
||||
engines: { node: ">= 6" }
|
||||
|
||||
formdata-node@4.4.1:
|
||||
resolution:
|
||||
{
|
||||
@@ -6573,10 +6566,10 @@ snapshots:
|
||||
|
||||
asynckit@0.4.0: {}
|
||||
|
||||
axios@1.13.6:
|
||||
axios@1.7.7:
|
||||
dependencies:
|
||||
follow-redirects: 1.15.11
|
||||
form-data: 4.0.5
|
||||
follow-redirects: 1.15.9
|
||||
form-data: 4.0.2
|
||||
proxy-from-env: 1.1.0
|
||||
transitivePeerDependencies:
|
||||
- debug
|
||||
@@ -7177,7 +7170,7 @@ snapshots:
|
||||
kolorist: 1.8.0
|
||||
read-pkg: 8.1.0
|
||||
|
||||
follow-redirects@1.15.11: {}
|
||||
follow-redirects@1.15.9: {}
|
||||
|
||||
foreground-child@3.3.1:
|
||||
dependencies:
|
||||
@@ -7193,14 +7186,6 @@ snapshots:
|
||||
es-set-tostringtag: 2.1.0
|
||||
mime-types: 2.1.35
|
||||
|
||||
form-data@4.0.5:
|
||||
dependencies:
|
||||
asynckit: 0.4.0
|
||||
combined-stream: 1.0.8
|
||||
es-set-tostringtag: 2.1.0
|
||||
hasown: 2.0.2
|
||||
mime-types: 2.1.35
|
||||
|
||||
formdata-node@4.4.1:
|
||||
dependencies:
|
||||
node-domexception: 1.0.0
|
||||
|
||||
+1
-4
@@ -28,7 +28,6 @@ from mem0.memory.telemetry import capture_event
|
||||
from mem0.memory.utils import (
|
||||
extract_json,
|
||||
get_fact_retrieval_messages,
|
||||
normalize_facts,
|
||||
parse_messages,
|
||||
parse_vision_messages,
|
||||
process_telemetry_filters,
|
||||
@@ -38,8 +37,8 @@ from mem0.utils.factory import (
|
||||
EmbedderFactory,
|
||||
GraphStoreFactory,
|
||||
LlmFactory,
|
||||
RerankerFactory,
|
||||
VectorStoreFactory,
|
||||
RerankerFactory,
|
||||
)
|
||||
|
||||
# Suppress SWIG deprecation warnings globally
|
||||
@@ -452,7 +451,6 @@ class Memory(MemoryBase):
|
||||
# Try extracting JSON from response using built-in function
|
||||
extracted_json = extract_json(response)
|
||||
new_retrieved_facts = json.loads(extracted_json)["facts"]
|
||||
new_retrieved_facts = normalize_facts(new_retrieved_facts)
|
||||
except Exception as e:
|
||||
logger.error(f"Error in new_retrieved_facts: {e}")
|
||||
new_retrieved_facts = []
|
||||
@@ -1479,7 +1477,6 @@ class AsyncMemory(MemoryBase):
|
||||
# Try extracting JSON from response using built-in function
|
||||
extracted_json = extract_json(response)
|
||||
new_retrieved_facts = json.loads(extracted_json)["facts"]
|
||||
new_retrieved_facts = normalize_facts(new_retrieved_facts)
|
||||
except Exception as e:
|
||||
logger.error(f"Error in new_retrieved_facts: {e}")
|
||||
new_retrieved_facts = []
|
||||
|
||||
@@ -24,18 +24,14 @@ logging.getLogger("urllib3").setLevel(logging.CRITICAL + 1)
|
||||
|
||||
class AnonymousTelemetry:
|
||||
def __init__(self, vector_store=None):
|
||||
if not MEM0_TELEMETRY:
|
||||
self.posthog = None
|
||||
self.user_id = None
|
||||
return
|
||||
|
||||
self.posthog = Posthog(project_api_key=PROJECT_API_KEY, host=HOST)
|
||||
|
||||
self.user_id = get_or_create_user_id(vector_store)
|
||||
|
||||
def capture_event(self, event_name, properties=None, user_email=None):
|
||||
if self.posthog is None:
|
||||
return
|
||||
if not MEM0_TELEMETRY:
|
||||
self.posthog.disabled = True
|
||||
|
||||
def capture_event(self, event_name, properties=None, user_email=None):
|
||||
if properties is None:
|
||||
properties = {}
|
||||
properties = {
|
||||
@@ -53,17 +49,13 @@ class AnonymousTelemetry:
|
||||
self.posthog.capture(distinct_id=distinct_id, event=event_name, properties=properties)
|
||||
|
||||
def close(self):
|
||||
if self.posthog is not None:
|
||||
self.posthog.shutdown()
|
||||
self.posthog.shutdown()
|
||||
|
||||
|
||||
client_telemetry = AnonymousTelemetry()
|
||||
|
||||
|
||||
def capture_event(event_name, memory_instance, additional_data=None):
|
||||
if not MEM0_TELEMETRY:
|
||||
return
|
||||
|
||||
oss_telemetry = AnonymousTelemetry(
|
||||
vector_store=memory_instance._telemetry_vector_store
|
||||
if hasattr(memory_instance, "_telemetry_vector_store")
|
||||
@@ -89,9 +81,6 @@ def capture_event(event_name, memory_instance, additional_data=None):
|
||||
|
||||
|
||||
def capture_client_event(event_name, instance, additional_data=None):
|
||||
if not MEM0_TELEMETRY:
|
||||
return
|
||||
|
||||
event_data = {
|
||||
"function": f"{instance.__class__.__module__}.{instance.__class__.__name__}",
|
||||
}
|
||||
|
||||
+1
-28
@@ -1,15 +1,12 @@
|
||||
import hashlib
|
||||
import logging
|
||||
import re
|
||||
|
||||
from mem0.configs.prompts import (
|
||||
AGENT_MEMORY_EXTRACTION_PROMPT,
|
||||
FACT_RETRIEVAL_PROMPT,
|
||||
USER_MEMORY_EXTRACTION_PROMPT,
|
||||
AGENT_MEMORY_EXTRACTION_PROMPT,
|
||||
)
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
def get_fact_retrieval_messages(message, is_agent_memory=False):
|
||||
"""Get fact retrieval messages based on the memory type.
|
||||
@@ -55,30 +52,6 @@ def format_entities(entities):
|
||||
|
||||
return "\n".join(formatted_lines)
|
||||
|
||||
def normalize_facts(raw_facts):
|
||||
"""Normalize LLM-extracted facts to a list of strings.
|
||||
|
||||
Smaller LLMs (e.g. llama3.1:8b) sometimes return facts as objects
|
||||
like {"fact": "..."} or {"text": "..."} instead of plain strings.
|
||||
This mirrors the TypeScript FactRetrievalSchema validation.
|
||||
"""
|
||||
if not raw_facts:
|
||||
return []
|
||||
normalized = []
|
||||
for item in raw_facts:
|
||||
if isinstance(item, str):
|
||||
fact = item
|
||||
elif isinstance(item, dict):
|
||||
fact = item.get("fact") or item.get("text")
|
||||
if fact is None:
|
||||
logger.warning("Unexpected fact shape from LLM, skipping: %s", item)
|
||||
continue
|
||||
else:
|
||||
fact = str(item)
|
||||
if fact:
|
||||
normalized.append(fact)
|
||||
return normalized
|
||||
|
||||
|
||||
def remove_code_blocks(content: str) -> str:
|
||||
"""
|
||||
|
||||
@@ -1,12 +1,16 @@
|
||||
import logging
|
||||
import os
|
||||
import shutil
|
||||
from typing import Optional
|
||||
|
||||
from qdrant_client import QdrantClient
|
||||
from qdrant_client.models import (
|
||||
Distance,
|
||||
FieldCondition,
|
||||
Filter,
|
||||
MatchAny,
|
||||
MatchExcept,
|
||||
MatchText,
|
||||
MatchValue,
|
||||
PointIdsList,
|
||||
PointStruct,
|
||||
@@ -138,26 +142,139 @@ class Qdrant(VectorStoreBase):
|
||||
]
|
||||
self.client.upsert(collection_name=self.collection_name, points=points)
|
||||
|
||||
def _create_filter(self, filters: dict) -> Filter:
|
||||
def _build_field_condition(self, key: str, value) -> Optional[FieldCondition]:
|
||||
"""
|
||||
Build a single FieldCondition from a key-value filter pair.
|
||||
|
||||
Supports the enhanced filter syntax documented at
|
||||
https://docs.mem0.ai/open-source/features/metadata-filtering
|
||||
|
||||
Args:
|
||||
key (str): The payload field name.
|
||||
value: A scalar for simple equality, or a dict with one operator key.
|
||||
|
||||
Returns:
|
||||
Optional[FieldCondition]: The Qdrant field condition, or None if the
|
||||
value is the wildcard '*' (match any / field exists — skip filter).
|
||||
"""
|
||||
if not isinstance(value, dict):
|
||||
if value == "*":
|
||||
# Wildcard: match any value. Qdrant has no direct "field exists"
|
||||
# condition via FieldCondition, so we skip this filter (match all).
|
||||
return None
|
||||
# Simple equality: {"field": "value"}
|
||||
return FieldCondition(key=key, match=MatchValue(value=value))
|
||||
|
||||
ops = set(value.keys())
|
||||
range_ops = {"gt", "gte", "lt", "lte"}
|
||||
non_range_ops = ops - range_ops
|
||||
|
||||
if ops & range_ops:
|
||||
if non_range_ops:
|
||||
raise ValueError(
|
||||
f"Cannot mix range operators ({ops & range_ops}) with "
|
||||
f"non-range operators ({non_range_ops}) for field '{key}'. "
|
||||
f"Use AND to combine them as separate conditions."
|
||||
)
|
||||
range_kwargs = {op: value[op] for op in range_ops if op in value}
|
||||
return FieldCondition(key=key, range=Range(**range_kwargs))
|
||||
elif "eq" in value:
|
||||
return FieldCondition(key=key, match=MatchValue(value=value["eq"]))
|
||||
elif "ne" in value:
|
||||
return FieldCondition(key=key, match=MatchExcept(**{"except": [value["ne"]]}))
|
||||
elif "in" in value:
|
||||
return FieldCondition(key=key, match=MatchAny(any=value["in"]))
|
||||
elif "nin" in value:
|
||||
return FieldCondition(key=key, match=MatchExcept(**{"except": value["nin"]}))
|
||||
elif "contains" in value or "icontains" in value:
|
||||
# MatchText: with a full-text index, tokenized matching (all words must appear).
|
||||
# Without a full-text index, exact substring match.
|
||||
op = "icontains" if "icontains" in value else "contains"
|
||||
text = value[op]
|
||||
if op == "icontains":
|
||||
logger.debug(
|
||||
"icontains on field '%s': Qdrant MatchText case sensitivity depends on "
|
||||
"full-text index configuration. Without a full-text index this behaves "
|
||||
"as a case-sensitive substring match (same as 'contains').",
|
||||
key,
|
||||
)
|
||||
return FieldCondition(key=key, match=MatchText(text=text))
|
||||
else:
|
||||
supported = {"eq", "ne", "gt", "gte", "lt", "lte", "in", "nin", "contains", "icontains"}
|
||||
raise ValueError(
|
||||
f"Unsupported filter operator(s) for field '{key}': {ops}. "
|
||||
f"Supported operators: {supported}"
|
||||
)
|
||||
|
||||
def _create_filter(self, filters: dict) -> Optional[Filter]:
|
||||
"""
|
||||
Create a Filter object from the provided filters.
|
||||
|
||||
Supports the enhanced filter syntax with comparison operators (eq, ne,
|
||||
gt, gte, lt, lte), list operators (in, nin), string operators (contains,
|
||||
icontains), and logical operators (AND, OR, NOT).
|
||||
|
||||
Args:
|
||||
filters (dict): Filters to apply.
|
||||
|
||||
Returns:
|
||||
Filter: The created Filter object.
|
||||
Filter: The created Filter object, or None if filters is empty.
|
||||
"""
|
||||
if not filters:
|
||||
return None
|
||||
|
||||
conditions = []
|
||||
|
||||
# Normalize $or/$not/$and → OR/NOT/AND and deduplicate.
|
||||
# Memory._process_metadata_filters() renames OR→$or and NOT→$not,
|
||||
# but effective_filters retains the original OR/NOT keys from
|
||||
# deepcopy(input_filters). Without dedup the same sub-conditions
|
||||
# would be evaluated twice.
|
||||
key_map = {"$or": "OR", "$not": "NOT", "$and": "AND"}
|
||||
normalized = {}
|
||||
for key, value in filters.items():
|
||||
if isinstance(value, dict) and "gte" in value and "lte" in value:
|
||||
conditions.append(FieldCondition(key=key, range=Range(gte=value["gte"], lte=value["lte"])))
|
||||
norm_key = key_map.get(key, key)
|
||||
if norm_key not in normalized:
|
||||
normalized[norm_key] = value
|
||||
|
||||
must = []
|
||||
should = []
|
||||
must_not = []
|
||||
|
||||
for key, value in normalized.items():
|
||||
if key in ("AND", "OR", "NOT"):
|
||||
if not isinstance(value, list):
|
||||
raise ValueError(
|
||||
f"{key} filter value must be a list of filter dicts, "
|
||||
f"got {type(value).__name__}"
|
||||
)
|
||||
|
||||
if key == "AND":
|
||||
for sub in value:
|
||||
built = self._create_filter(sub)
|
||||
if built:
|
||||
must.append(built)
|
||||
elif key == "OR":
|
||||
for sub in value:
|
||||
built = self._create_filter(sub)
|
||||
if built:
|
||||
should.append(built)
|
||||
elif key == "NOT":
|
||||
for sub in value:
|
||||
built = self._create_filter(sub)
|
||||
if built:
|
||||
must_not.append(built)
|
||||
else:
|
||||
conditions.append(FieldCondition(key=key, match=MatchValue(value=value)))
|
||||
return Filter(must=conditions) if conditions else None
|
||||
condition = self._build_field_condition(key, value)
|
||||
if condition is not None:
|
||||
must.append(condition)
|
||||
|
||||
if not any([must, should, must_not]):
|
||||
return None
|
||||
|
||||
return Filter(
|
||||
must=must or None,
|
||||
should=should or None,
|
||||
must_not=must_not or None,
|
||||
)
|
||||
|
||||
def search(self, query: str, vectors: list, limit: int = 5, filters: dict = None) -> list:
|
||||
"""
|
||||
|
||||
+1
-1
@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
|
||||
|
||||
[project]
|
||||
name = "mem0ai"
|
||||
version = "1.0.5"
|
||||
version = "1.0.4"
|
||||
description = "Long-term memory for AI Agents"
|
||||
authors = [
|
||||
{ name = "Mem0", email = "founders@mem0.ai" }
|
||||
|
||||
+1
-76
@@ -1,11 +1,9 @@
|
||||
import json
|
||||
from unittest.mock import MagicMock, patch
|
||||
|
||||
import pytest
|
||||
|
||||
from mem0 import Memory
|
||||
from mem0.configs.base import MemoryConfig
|
||||
from mem0.memory.utils import normalize_facts
|
||||
|
||||
|
||||
class MockVectorMemory:
|
||||
@@ -246,77 +244,4 @@ def test_get_all_handles_flat_list_from_postgres(mock_sqlite, mock_llm_factory,
|
||||
|
||||
assert len(result) == 2
|
||||
assert result[0]["memory"] == "Memory 1"
|
||||
assert result[1]["memory"] == "Memory 2"
|
||||
|
||||
|
||||
@patch('mem0.utils.factory.EmbedderFactory.create')
|
||||
@patch('mem0.utils.factory.VectorStoreFactory.create')
|
||||
@patch('mem0.utils.factory.LlmFactory.create')
|
||||
@patch('mem0.memory.storage.SQLiteManager')
|
||||
def test_add_infer_with_malformed_llm_facts(mock_sqlite, mock_llm_factory, mock_vector_factory, mock_embedder_factory):
|
||||
"""
|
||||
Repro for: 'list' object has no attribute 'replace' on infer=true.
|
||||
|
||||
When an LLM (especially smaller models like llama3.1:8b) returns facts as
|
||||
objects ({"fact": "..."} or {"text": "..."}) instead of plain strings,
|
||||
the embedding model's .replace() call crashes with AttributeError.
|
||||
"""
|
||||
mock_embedder = MagicMock()
|
||||
mock_embedder.embed.side_effect = lambda text, action: (_ for _ in ()).throw(
|
||||
AttributeError("'dict' object has no attribute 'replace'")
|
||||
) if not isinstance(text, str) else [0.1, 0.2, 0.3]
|
||||
mock_embedder_factory.return_value = mock_embedder
|
||||
|
||||
mock_vector_store = MagicMock()
|
||||
mock_vector_store.search.return_value = []
|
||||
mock_vector_factory.return_value = mock_vector_store
|
||||
|
||||
# LLM returns malformed facts: dicts instead of strings
|
||||
malformed_response = json.dumps({
|
||||
"facts": [
|
||||
{"fact": "User likes Python"},
|
||||
{"text": "User is a developer"},
|
||||
]
|
||||
})
|
||||
mock_llm = MagicMock()
|
||||
mock_llm.generate_response.return_value = malformed_response
|
||||
mock_llm_factory.return_value = mock_llm
|
||||
|
||||
mock_sqlite.return_value = MagicMock()
|
||||
|
||||
from mem0.memory.main import Memory as MemoryClass
|
||||
config = MemoryConfig()
|
||||
memory = MemoryClass(config)
|
||||
|
||||
# This should NOT raise AttributeError
|
||||
memory._add_to_vector_store(
|
||||
messages=[{"role": "user", "content": "I like Python and I'm a developer"}],
|
||||
metadata={"user_id": "test_user"},
|
||||
filters={"user_id": "test_user"},
|
||||
infer=True,
|
||||
)
|
||||
|
||||
|
||||
def test_normalize_facts_plain_strings():
|
||||
assert normalize_facts(["fact one", "fact two"]) == ["fact one", "fact two"]
|
||||
|
||||
|
||||
def test_normalize_facts_dict_with_fact_key():
|
||||
assert normalize_facts([{"fact": "User likes Python"}]) == ["User likes Python"]
|
||||
|
||||
|
||||
def test_normalize_facts_dict_with_text_key():
|
||||
assert normalize_facts([{"text": "User is a developer"}]) == ["User is a developer"]
|
||||
|
||||
|
||||
def test_normalize_facts_mixed():
|
||||
raw = [
|
||||
"plain string",
|
||||
{"fact": "from fact key"},
|
||||
{"text": "from text key"},
|
||||
]
|
||||
assert normalize_facts(raw) == ["plain string", "from fact key", "from text key"]
|
||||
|
||||
|
||||
def test_normalize_facts_filters_empty_strings():
|
||||
assert normalize_facts(["", "valid", ""]) == ["valid"]
|
||||
assert result[1]["memory"] == "Memory 2"
|
||||
|
||||
+25
-104
@@ -1,114 +1,35 @@
|
||||
import threading
|
||||
from unittest.mock import MagicMock, patch
|
||||
import os
|
||||
from unittest.mock import patch
|
||||
|
||||
import pytest
|
||||
|
||||
import mem0.memory.telemetry as telemetry_module
|
||||
MEM0_TELEMETRY = os.environ.get("MEM0_TELEMETRY", "True")
|
||||
|
||||
if isinstance(MEM0_TELEMETRY, str):
|
||||
MEM0_TELEMETRY = MEM0_TELEMETRY.lower() in ("true", "1", "yes")
|
||||
|
||||
|
||||
class TestTelemetryDisabled:
|
||||
"""Verify PostHog is never instantiated when telemetry is disabled."""
|
||||
|
||||
def test_posthog_not_created_when_disabled(self):
|
||||
"""Posthog() constructor should never be called when MEM0_TELEMETRY=False."""
|
||||
with patch.object(telemetry_module, "MEM0_TELEMETRY", False):
|
||||
with patch("mem0.memory.telemetry.Posthog") as mock_posthog:
|
||||
at = telemetry_module.AnonymousTelemetry()
|
||||
mock_posthog.assert_not_called()
|
||||
assert at.posthog is None
|
||||
assert at.user_id is None
|
||||
|
||||
def test_capture_event_noop_when_disabled(self):
|
||||
"""capture_event() should return immediately without creating AnonymousTelemetry."""
|
||||
with patch.object(telemetry_module, "MEM0_TELEMETRY", False):
|
||||
with patch("mem0.memory.telemetry.AnonymousTelemetry") as mock_cls:
|
||||
telemetry_module.capture_event("test.event", MagicMock())
|
||||
mock_cls.assert_not_called()
|
||||
|
||||
def test_capture_client_event_noop_when_disabled(self):
|
||||
"""capture_client_event() should return immediately without calling posthog."""
|
||||
with patch.object(telemetry_module, "MEM0_TELEMETRY", False):
|
||||
mock_instance = MagicMock()
|
||||
mock_client_telemetry = MagicMock()
|
||||
with patch.object(telemetry_module, "client_telemetry", mock_client_telemetry):
|
||||
telemetry_module.capture_client_event("test.event", mock_instance)
|
||||
mock_client_telemetry.capture_event.assert_not_called()
|
||||
|
||||
def test_instance_capture_event_noop_when_posthog_is_none(self):
|
||||
"""AnonymousTelemetry.capture_event() should be a no-op when posthog is None."""
|
||||
with patch.object(telemetry_module, "MEM0_TELEMETRY", False):
|
||||
at = telemetry_module.AnonymousTelemetry()
|
||||
at.capture_event("test.event", {"key": "value"}) # should not raise
|
||||
|
||||
def test_close_noop_when_posthog_is_none(self):
|
||||
"""close() should not raise when posthog is None."""
|
||||
with patch.object(telemetry_module, "MEM0_TELEMETRY", False):
|
||||
at = telemetry_module.AnonymousTelemetry()
|
||||
at.close() # should not raise
|
||||
|
||||
def test_no_threads_spawned_when_disabled(self):
|
||||
"""No consumer threads should be created when telemetry is disabled."""
|
||||
with patch.object(telemetry_module, "MEM0_TELEMETRY", False):
|
||||
threads_before = threading.active_count()
|
||||
telemetry_module.AnonymousTelemetry()
|
||||
threads_after = threading.active_count()
|
||||
assert threads_after == threads_before
|
||||
def use_telemetry():
|
||||
if os.getenv("MEM0_TELEMETRY", "true").lower() == "true":
|
||||
return True
|
||||
return False
|
||||
|
||||
|
||||
class TestTelemetryEnabled:
|
||||
"""Verify PostHog works normally when telemetry is enabled."""
|
||||
|
||||
def test_posthog_created_when_enabled(self):
|
||||
"""Posthog() should be instantiated when MEM0_TELEMETRY=True."""
|
||||
with patch.object(telemetry_module, "MEM0_TELEMETRY", True):
|
||||
with patch("mem0.memory.telemetry.Posthog") as mock_posthog:
|
||||
with patch("mem0.memory.telemetry.get_or_create_user_id", return_value="test-user"):
|
||||
at = telemetry_module.AnonymousTelemetry()
|
||||
mock_posthog.assert_called_once()
|
||||
assert at.posthog is not None
|
||||
assert at.user_id == "test-user"
|
||||
|
||||
def test_capture_event_sends_when_enabled(self):
|
||||
"""capture_event() should create AnonymousTelemetry and call capture when enabled."""
|
||||
with patch.object(telemetry_module, "MEM0_TELEMETRY", True):
|
||||
with patch("mem0.memory.telemetry.AnonymousTelemetry") as mock_cls:
|
||||
mock_at = MagicMock()
|
||||
mock_cls.return_value = mock_at
|
||||
mock_memory = MagicMock()
|
||||
mock_memory.config.graph_store.config = None
|
||||
mock_memory.api_version = "v1"
|
||||
telemetry_module.capture_event("test.event", mock_memory)
|
||||
mock_at.capture_event.assert_called_once()
|
||||
|
||||
def test_capture_client_event_sends_when_enabled(self):
|
||||
"""capture_client_event() should call client_telemetry.capture_event when enabled."""
|
||||
with patch.object(telemetry_module, "MEM0_TELEMETRY", True):
|
||||
mock_client_telemetry = MagicMock()
|
||||
with patch.object(telemetry_module, "client_telemetry", mock_client_telemetry):
|
||||
mock_instance = MagicMock()
|
||||
mock_instance.user_email = "test@example.com"
|
||||
telemetry_module.capture_client_event("test.event", mock_instance)
|
||||
mock_client_telemetry.capture_event.assert_called_once()
|
||||
@pytest.fixture(autouse=True)
|
||||
def reset_env():
|
||||
with patch.dict(os.environ, {}, clear=True):
|
||||
yield
|
||||
|
||||
|
||||
class TestTelemetryEnvVar:
|
||||
"""Verify the MEM0_TELEMETRY env var parsing logic."""
|
||||
def test_telemetry_enabled():
|
||||
with patch.dict(os.environ, {"MEM0_TELEMETRY": "true"}):
|
||||
assert use_telemetry() is True
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"value,expected",
|
||||
[
|
||||
("true", True),
|
||||
("True", True),
|
||||
("TRUE", True),
|
||||
("1", True),
|
||||
("yes", True),
|
||||
("false", False),
|
||||
("False", False),
|
||||
("0", False),
|
||||
("no", False),
|
||||
("anything_else", False),
|
||||
],
|
||||
)
|
||||
def test_env_var_parsing(self, value, expected):
|
||||
result = value.lower() in ("true", "1", "yes")
|
||||
assert result == expected
|
||||
|
||||
def test_telemetry_disabled():
|
||||
with patch.dict(os.environ, {"MEM0_TELEMETRY": "false"}):
|
||||
assert use_telemetry() is False
|
||||
|
||||
|
||||
def test_telemetry_default_enabled():
|
||||
assert use_telemetry() is True
|
||||
|
||||
@@ -5,9 +5,15 @@ from unittest.mock import MagicMock
|
||||
from qdrant_client import QdrantClient
|
||||
from qdrant_client.models import (
|
||||
Distance,
|
||||
FieldCondition,
|
||||
Filter,
|
||||
MatchAny,
|
||||
MatchExcept,
|
||||
MatchText,
|
||||
MatchValue,
|
||||
PointIdsList,
|
||||
PointStruct,
|
||||
Range,
|
||||
VectorParams,
|
||||
)
|
||||
|
||||
@@ -298,3 +304,433 @@ class TestQdrant(unittest.TestCase):
|
||||
|
||||
def tearDown(self):
|
||||
del self.qdrant
|
||||
|
||||
|
||||
class TestQdrantEnhancedFilters(unittest.TestCase):
|
||||
"""Tests for enhanced metadata filtering operators (issue #3975)."""
|
||||
|
||||
def setUp(self):
|
||||
self.client_mock = MagicMock(spec=QdrantClient)
|
||||
self.qdrant = Qdrant(
|
||||
collection_name="test_collection",
|
||||
embedding_model_dims=128,
|
||||
client=self.client_mock,
|
||||
)
|
||||
|
||||
# ------------------------------------------------------------------ #
|
||||
# _build_field_condition #
|
||||
# ------------------------------------------------------------------ #
|
||||
|
||||
def test_simple_equality(self):
|
||||
"""Plain value maps to MatchValue."""
|
||||
cond = self.qdrant._build_field_condition("category", "programming")
|
||||
self.assertIsInstance(cond, FieldCondition)
|
||||
self.assertEqual(cond.key, "category")
|
||||
self.assertIsInstance(cond.match, MatchValue)
|
||||
self.assertEqual(cond.match.value, "programming")
|
||||
|
||||
def test_eq_operator(self):
|
||||
"""{\"eq\": v} maps to MatchValue."""
|
||||
cond = self.qdrant._build_field_condition("category", {"eq": "programming"})
|
||||
self.assertIsInstance(cond.match, MatchValue)
|
||||
self.assertEqual(cond.match.value, "programming")
|
||||
|
||||
def test_ne_operator(self):
|
||||
"""{\"ne\": v} maps to MatchExcept with a single-element list."""
|
||||
cond = self.qdrant._build_field_condition("category", {"ne": "spam"})
|
||||
self.assertIsInstance(cond.match, MatchExcept)
|
||||
self.assertIn("spam", getattr(cond.match, "except_", None) or getattr(cond.match, "except"))
|
||||
|
||||
def test_in_operator(self):
|
||||
"""{\"in\": [...]} maps to MatchAny."""
|
||||
cond = self.qdrant._build_field_condition("category", {"in": ["a", "b", "c"]})
|
||||
self.assertIsInstance(cond.match, MatchAny)
|
||||
self.assertEqual(cond.match.any, ["a", "b", "c"])
|
||||
|
||||
def test_nin_operator(self):
|
||||
"""{\"nin\": [...]} maps to MatchExcept."""
|
||||
cond = self.qdrant._build_field_condition("status", {"nin": ["deleted", "banned"]})
|
||||
self.assertIsInstance(cond.match, MatchExcept)
|
||||
excluded = getattr(cond.match, "except_", None) or getattr(cond.match, "except")
|
||||
self.assertIn("deleted", excluded)
|
||||
self.assertIn("banned", excluded)
|
||||
|
||||
def test_contains_operator(self):
|
||||
"""{\"contains\": x} maps to MatchText."""
|
||||
cond = self.qdrant._build_field_condition("bio", {"contains": "python"})
|
||||
self.assertIsInstance(cond.match, MatchText)
|
||||
self.assertEqual(cond.match.text, "python")
|
||||
|
||||
def test_icontains_operator(self):
|
||||
"""{\"icontains\": x} maps to MatchText (same as contains for Qdrant)."""
|
||||
cond = self.qdrant._build_field_condition("bio", {"icontains": "Python"})
|
||||
self.assertIsInstance(cond.match, MatchText)
|
||||
self.assertEqual(cond.match.text, "Python")
|
||||
|
||||
def test_gt_operator(self):
|
||||
"""{\"gt\": v} maps to Range with gt only."""
|
||||
cond = self.qdrant._build_field_condition("priority", {"gt": 5})
|
||||
self.assertIsInstance(cond.range, Range)
|
||||
self.assertEqual(cond.range.gt, 5)
|
||||
self.assertIsNone(cond.range.gte)
|
||||
self.assertIsNone(cond.range.lt)
|
||||
self.assertIsNone(cond.range.lte)
|
||||
|
||||
def test_gte_operator(self):
|
||||
"""{\"gte\": v} maps to Range with gte only."""
|
||||
cond = self.qdrant._build_field_condition("priority", {"gte": 5})
|
||||
self.assertIsInstance(cond.range, Range)
|
||||
self.assertEqual(cond.range.gte, 5)
|
||||
self.assertIsNone(cond.range.gt)
|
||||
|
||||
def test_lt_operator(self):
|
||||
"""{\"lt\": v} maps to Range with lt only."""
|
||||
cond = self.qdrant._build_field_condition("priority", {"lt": 10})
|
||||
self.assertIsInstance(cond.range, Range)
|
||||
self.assertEqual(cond.range.lt, 10)
|
||||
|
||||
def test_lte_operator(self):
|
||||
"""{\"lte\": v} maps to Range with lte only."""
|
||||
cond = self.qdrant._build_field_condition("priority", {"lte": 10})
|
||||
self.assertIsInstance(cond.range, Range)
|
||||
self.assertEqual(cond.range.lte, 10)
|
||||
|
||||
def test_range_gte_lte(self):
|
||||
"""Combined {\"gte\": x, \"lte\": y} maps to Range with both bounds."""
|
||||
cond = self.qdrant._build_field_condition("priority", {"gte": 5, "lte": 10})
|
||||
self.assertIsInstance(cond.range, Range)
|
||||
self.assertEqual(cond.range.gte, 5)
|
||||
self.assertEqual(cond.range.lte, 10)
|
||||
|
||||
def test_range_gt_lt(self):
|
||||
"""Open interval {\"gt\": x, \"lt\": y} maps to Range with both bounds."""
|
||||
cond = self.qdrant._build_field_condition("score", {"gt": 0.5, "lt": 0.9})
|
||||
self.assertIsInstance(cond.range, Range)
|
||||
self.assertEqual(cond.range.gt, 0.5)
|
||||
self.assertEqual(cond.range.lt, 0.9)
|
||||
|
||||
# ------------------------------------------------------------------ #
|
||||
# _create_filter — comparison and list operators #
|
||||
# ------------------------------------------------------------------ #
|
||||
|
||||
def test_create_filter_eq(self):
|
||||
result = self.qdrant._create_filter({"category": {"eq": "programming"}})
|
||||
self.assertIsInstance(result, Filter)
|
||||
self.assertEqual(len(result.must), 1)
|
||||
self.assertIsInstance(result.must[0].match, MatchValue)
|
||||
|
||||
def test_create_filter_ne(self):
|
||||
result = self.qdrant._create_filter({"category": {"ne": "spam"}})
|
||||
self.assertIsInstance(result, Filter)
|
||||
self.assertIsInstance(result.must[0].match, MatchExcept)
|
||||
|
||||
def test_create_filter_in(self):
|
||||
result = self.qdrant._create_filter({"category": {"in": ["prog", "data"]}})
|
||||
self.assertIsInstance(result, Filter)
|
||||
self.assertIsInstance(result.must[0].match, MatchAny)
|
||||
self.assertEqual(result.must[0].match.any, ["prog", "data"])
|
||||
|
||||
def test_create_filter_nin(self):
|
||||
result = self.qdrant._create_filter({"status": {"nin": ["deleted", "banned"]}})
|
||||
self.assertIsInstance(result, Filter)
|
||||
self.assertIsInstance(result.must[0].match, MatchExcept)
|
||||
|
||||
def test_create_filter_gt(self):
|
||||
result = self.qdrant._create_filter({"priority": {"gt": 7}})
|
||||
self.assertIsInstance(result, Filter)
|
||||
self.assertIsInstance(result.must[0].range, Range)
|
||||
self.assertEqual(result.must[0].range.gt, 7)
|
||||
|
||||
def test_create_filter_gte_lte_range(self):
|
||||
result = self.qdrant._create_filter({"priority": {"gte": 5, "lte": 9}})
|
||||
self.assertIsInstance(result, Filter)
|
||||
r = result.must[0].range
|
||||
self.assertEqual(r.gte, 5)
|
||||
self.assertEqual(r.lte, 9)
|
||||
|
||||
def test_create_filter_contains(self):
|
||||
result = self.qdrant._create_filter({"bio": {"contains": "python"}})
|
||||
self.assertIsInstance(result, Filter)
|
||||
self.assertIsInstance(result.must[0].match, MatchText)
|
||||
|
||||
# ------------------------------------------------------------------ #
|
||||
# _create_filter — logical operators #
|
||||
# ------------------------------------------------------------------ #
|
||||
|
||||
def test_and_operator(self):
|
||||
"""AND populates Filter.must with nested Filter objects."""
|
||||
filters = {"AND": [{"category": "programming"}, {"priority": 10}]}
|
||||
result = self.qdrant._create_filter(filters)
|
||||
self.assertIsInstance(result, Filter)
|
||||
self.assertEqual(len(result.must), 2)
|
||||
# Each item is a Filter that wraps a single FieldCondition
|
||||
for item in result.must:
|
||||
self.assertIsInstance(item, Filter)
|
||||
|
||||
def test_or_operator(self):
|
||||
"""OR populates Filter.should with nested Filter objects."""
|
||||
filters = {"OR": [{"category": "programming"}, {"category": "data"}]}
|
||||
result = self.qdrant._create_filter(filters)
|
||||
self.assertIsInstance(result, Filter)
|
||||
self.assertEqual(len(result.should), 2)
|
||||
self.assertIsNone(result.must)
|
||||
|
||||
def test_not_operator(self):
|
||||
"""NOT populates Filter.must_not with nested Filter objects."""
|
||||
filters = {"NOT": [{"category": "spam"}]}
|
||||
result = self.qdrant._create_filter(filters)
|
||||
self.assertIsInstance(result, Filter)
|
||||
self.assertEqual(len(result.must_not), 1)
|
||||
self.assertIsNone(result.must)
|
||||
self.assertIsNone(result.should)
|
||||
|
||||
def test_mixed_field_and_and(self):
|
||||
"""Top-level field conditions and AND can coexist in must."""
|
||||
filters = {
|
||||
"user_id": "alice",
|
||||
"AND": [{"priority": {"gte": 5}}, {"category": "programming"}],
|
||||
}
|
||||
result = self.qdrant._create_filter(filters)
|
||||
self.assertIsInstance(result, Filter)
|
||||
# user_id FieldCondition + 2 nested AND Filters = 3 items in must
|
||||
self.assertEqual(len(result.must), 3)
|
||||
|
||||
def test_nested_and_or(self):
|
||||
"""AND containing an OR sub-condition produces correct nesting."""
|
||||
filters = {
|
||||
"AND": [
|
||||
{"OR": [{"category": "prog"}, {"category": "data"}]},
|
||||
{"priority": {"gt": 3}},
|
||||
]
|
||||
}
|
||||
result = self.qdrant._create_filter(filters)
|
||||
self.assertIsInstance(result, Filter)
|
||||
self.assertEqual(len(result.must), 2)
|
||||
# First item is a Filter with should (the OR)
|
||||
or_filter = result.must[0]
|
||||
self.assertIsInstance(or_filter, Filter)
|
||||
self.assertEqual(len(or_filter.should), 2)
|
||||
|
||||
# ------------------------------------------------------------------ #
|
||||
# Edge cases #
|
||||
# ------------------------------------------------------------------ #
|
||||
|
||||
def test_empty_filter_returns_none(self):
|
||||
self.assertIsNone(self.qdrant._create_filter({}))
|
||||
self.assertIsNone(self.qdrant._create_filter(None))
|
||||
|
||||
def test_backward_compat_simple_equality(self):
|
||||
"""Plain scalar equality still works as before."""
|
||||
result = self.qdrant._create_filter({"user_id": "alice", "run_id": "r1"})
|
||||
self.assertIsInstance(result, Filter)
|
||||
keys = [c.key for c in result.must]
|
||||
self.assertIn("user_id", keys)
|
||||
self.assertIn("run_id", keys)
|
||||
|
||||
def test_backward_compat_gte_lte_range(self):
|
||||
"""Original gte+lte range filter still produces a Range condition."""
|
||||
result = self.qdrant._create_filter({"count": {"gte": 5, "lte": 10}})
|
||||
self.assertIsInstance(result, Filter)
|
||||
self.assertIsInstance(result.must[0].range, Range)
|
||||
self.assertEqual(result.must[0].range.gte, 5)
|
||||
self.assertEqual(result.must[0].range.lte, 10)
|
||||
|
||||
def test_unknown_operator_raises_error(self):
|
||||
"""Unknown operator dict should raise ValueError, not ValidationError."""
|
||||
with self.assertRaises(ValueError) as ctx:
|
||||
self.qdrant._build_field_condition("field", {"unknown_op": "foo"})
|
||||
self.assertIn("Unsupported", str(ctx.exception))
|
||||
|
||||
def test_mixed_range_and_non_range_raises_error(self):
|
||||
"""Mixing range ops with non-range ops should raise ValueError."""
|
||||
with self.assertRaises(ValueError):
|
||||
self.qdrant._build_field_condition("priority", {"gte": 5, "ne": 10})
|
||||
|
||||
def test_mixed_range_and_eq_raises_error(self):
|
||||
"""Mixing range ops with eq should raise ValueError."""
|
||||
with self.assertRaises(ValueError):
|
||||
self.qdrant._build_field_condition("score", {"gt": 0.5, "eq": 1.0})
|
||||
|
||||
def test_wildcard_returns_none(self):
|
||||
"""Wildcard '*' should return None (skip filter — match any)."""
|
||||
result = self.qdrant._build_field_condition("category", "*")
|
||||
self.assertIsNone(result)
|
||||
|
||||
def test_create_filter_with_wildcard_skips_it(self):
|
||||
"""Wildcard fields should be skipped in the final filter."""
|
||||
result = self.qdrant._create_filter({"category": "*", "user_id": "alice"})
|
||||
self.assertIsInstance(result, Filter)
|
||||
self.assertEqual(len(result.must), 1)
|
||||
self.assertEqual(result.must[0].key, "user_id")
|
||||
|
||||
def test_create_filter_only_wildcard_returns_none(self):
|
||||
"""Filter with only wildcard should return None."""
|
||||
result = self.qdrant._create_filter({"category": "*"})
|
||||
self.assertIsNone(result)
|
||||
|
||||
def test_and_with_non_list_raises_error(self):
|
||||
"""AND with non-list value should raise ValueError."""
|
||||
with self.assertRaises(ValueError):
|
||||
self.qdrant._create_filter({"AND": "not_a_list"})
|
||||
|
||||
def test_or_with_non_list_raises_error(self):
|
||||
"""OR with non-list value should raise ValueError."""
|
||||
with self.assertRaises(ValueError):
|
||||
self.qdrant._create_filter({"OR": {"category": "work"}})
|
||||
|
||||
def test_not_with_non_list_raises_error(self):
|
||||
"""NOT with non-list value should raise ValueError."""
|
||||
with self.assertRaises(ValueError):
|
||||
self.qdrant._create_filter({"NOT": "invalid"})
|
||||
|
||||
def test_empty_and_list(self):
|
||||
"""AND with empty list should return None."""
|
||||
result = self.qdrant._create_filter({"AND": []})
|
||||
self.assertIsNone(result)
|
||||
|
||||
def test_empty_or_list(self):
|
||||
"""OR with empty list should return None."""
|
||||
result = self.qdrant._create_filter({"OR": []})
|
||||
self.assertIsNone(result)
|
||||
|
||||
def test_empty_not_list(self):
|
||||
"""NOT with empty list should return None."""
|
||||
result = self.qdrant._create_filter({"NOT": []})
|
||||
self.assertIsNone(result)
|
||||
|
||||
def test_deeply_nested_logical(self):
|
||||
"""3-level nesting: AND > OR > NOT."""
|
||||
filters = {
|
||||
"AND": [
|
||||
{
|
||||
"OR": [
|
||||
{"category": "work"},
|
||||
{"category": "personal"}
|
||||
]
|
||||
},
|
||||
{"priority": {"gte": 5}},
|
||||
{
|
||||
"NOT": [
|
||||
{"status": "archived"}
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
result = self.qdrant._create_filter(filters)
|
||||
self.assertIsInstance(result, Filter)
|
||||
self.assertEqual(len(result.must), 3)
|
||||
|
||||
def test_boolean_equality(self):
|
||||
"""Boolean values should work with MatchValue."""
|
||||
cond = self.qdrant._build_field_condition("active", True)
|
||||
self.assertIsInstance(cond.match, MatchValue)
|
||||
self.assertEqual(cond.match.value, True)
|
||||
|
||||
def test_integer_equality(self):
|
||||
"""Integer values should work with MatchValue."""
|
||||
cond = self.qdrant._build_field_condition("count", 42)
|
||||
self.assertIsInstance(cond.match, MatchValue)
|
||||
self.assertEqual(cond.match.value, 42)
|
||||
|
||||
def test_eq_with_boolean(self):
|
||||
"""eq operator with boolean should work."""
|
||||
cond = self.qdrant._build_field_condition("active", {"eq": False})
|
||||
self.assertIsInstance(cond.match, MatchValue)
|
||||
self.assertEqual(cond.match.value, False)
|
||||
|
||||
def test_in_with_integers(self):
|
||||
"""in operator with integer list should use MatchAny."""
|
||||
cond = self.qdrant._build_field_condition("priority", {"in": [1, 2, 3]})
|
||||
self.assertIsInstance(cond.match, MatchAny)
|
||||
self.assertEqual(cond.match.any, [1, 2, 3])
|
||||
|
||||
def test_wildcard_inside_and(self):
|
||||
"""Wildcard inside AND should be skipped, other conditions preserved."""
|
||||
result = self.qdrant._create_filter({
|
||||
"AND": [{"category": "*"}, {"user_id": "alice"}]
|
||||
})
|
||||
self.assertIsInstance(result, Filter)
|
||||
# AND produces nested Filters; the wildcard sub-filter returns None and is skipped
|
||||
# Only the user_id sub-filter remains
|
||||
self.assertEqual(len(result.must), 1)
|
||||
|
||||
def test_empty_dict_value_raises_error(self):
|
||||
"""Empty dict as filter value should raise ValueError."""
|
||||
with self.assertRaises(ValueError):
|
||||
self.qdrant._build_field_condition("field", {})
|
||||
|
||||
def test_ne_alone_does_not_trigger_mixed_error(self):
|
||||
"""ne as sole operator should NOT trigger mixed-operator error (regression guard)."""
|
||||
cond = self.qdrant._build_field_condition("status", {"ne": "deleted"})
|
||||
self.assertIsInstance(cond.match, MatchExcept)
|
||||
|
||||
def test_eq_with_literal_star(self):
|
||||
"""eq operator with literal '*' should match the string '*', not wildcard."""
|
||||
cond = self.qdrant._build_field_condition("category", {"eq": "*"})
|
||||
self.assertIsInstance(cond.match, MatchValue)
|
||||
self.assertEqual(cond.match.value, "*")
|
||||
|
||||
# ------------------------------------------------------------------ #
|
||||
# $or / $not normalization (Memory._process_metadata_filters injects #
|
||||
# these keys alongside the original OR/NOT) #
|
||||
# ------------------------------------------------------------------ #
|
||||
|
||||
def test_dollar_or_handled_as_or(self):
|
||||
"""$or injected by Memory middleware should be treated as OR."""
|
||||
filters = {
|
||||
"user_id": "alice",
|
||||
"$or": [{"category": "programming"}, {"category": "data"}],
|
||||
}
|
||||
result = self.qdrant._create_filter(filters)
|
||||
self.assertIsInstance(result, Filter)
|
||||
self.assertIsNotNone(result.should)
|
||||
self.assertEqual(len(result.should), 2)
|
||||
|
||||
def test_dollar_not_handled_as_not(self):
|
||||
"""$not injected by Memory middleware should be treated as NOT."""
|
||||
filters = {
|
||||
"user_id": "alice",
|
||||
"$not": [{"category": "spam"}],
|
||||
}
|
||||
result = self.qdrant._create_filter(filters)
|
||||
self.assertIsInstance(result, Filter)
|
||||
self.assertIsNotNone(result.must_not)
|
||||
self.assertEqual(len(result.must_not), 1)
|
||||
|
||||
def test_memory_search_or_shape(self):
|
||||
"""Simulate exact shape Memory.search() sends for OR filters.
|
||||
|
||||
effective_filters keeps the original OR key (via deepcopy of
|
||||
input_filters) and _process_metadata_filters adds $or with the
|
||||
same content. _create_filter should deduplicate so only the
|
||||
first occurrence (OR) is used — exactly 2 should entries.
|
||||
"""
|
||||
filters = {
|
||||
"OR": [{"category": "programming"}, {"category": "data"}],
|
||||
"user_id": "test_user",
|
||||
"$or": [{"category": "programming"}, {"category": "data"}],
|
||||
}
|
||||
result = self.qdrant._create_filter(filters)
|
||||
self.assertIsInstance(result, Filter)
|
||||
self.assertIsNotNone(result.should)
|
||||
# Deduplicated: OR wins, $or is skipped — exactly 2 entries
|
||||
self.assertEqual(len(result.should), 2)
|
||||
|
||||
def test_memory_search_not_shape(self):
|
||||
"""Simulate exact shape Memory.search() sends for NOT filters.
|
||||
|
||||
Same deduplication as OR: NOT wins, $not is skipped.
|
||||
"""
|
||||
filters = {
|
||||
"NOT": [{"category": "spam"}],
|
||||
"user_id": "test_user",
|
||||
"$not": [{"category": "spam"}],
|
||||
}
|
||||
result = self.qdrant._create_filter(filters)
|
||||
self.assertIsInstance(result, Filter)
|
||||
self.assertIsNotNone(result.must_not)
|
||||
# Deduplicated: NOT wins, $not is skipped — exactly 1 entry
|
||||
self.assertEqual(len(result.must_not), 1)
|
||||
|
||||
def tearDown(self):
|
||||
del self.qdrant
|
||||
|
||||
Reference in New Issue
Block a user