fix: update mem0 and qdrant dependencies#13292
Merged
Merged
Conversation
Contributor
WalkthroughThis PR upgrades mem0ai from 0.1.34 to 2.0.2+, updates qdrant-client to 1.12.0–1.x, and migrates ChangesMem0 2.x library upgrade
Estimated code review effort🎯 2 (Simple) | ⏱️ ~12 minutes Possibly related PRs
Suggested labels
Suggested reviewers
🚥 Pre-merge checks | ✅ 7 | ❌ 2❌ Failed checks (2 warnings)
✅ Passed checks (7 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches📝 Generate docstrings
🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
github-actions
Bot
added
bug
Adam-Aghili
approved these changes
May 22, 2026
Contributor
✅ Test Coverage AdvisorNo source changes detected without accompanying tests. Thanks for keeping coverage up! 🎉
|
github-actions
Bot
added
bug
Codecov Report✅ All modified and coverable lines are covered by tests. Additional details and impacted files@@ Coverage Diff @@
## release-1.10.0 #13292 +/- ##
==================================================
+ Coverage 55.57% 55.61% +0.04%
==================================================
Files 2178 2178
Lines 205682 205657 -25
Branches 31089 29436 -1653
==================================================
+ Hits 114309 114384 +75
+ Misses 90053 89954 -99
+ Partials 1320 1319 -1
Flags with carried forward coverage won't be shown. Click here to find out more. 🚀 New features to boost your workflow:
|
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@src/lfx/src/lfx/_assets/component_index.json`:
- Line 92004: In build_search_results, add an early guard that checks if
self.user_id is falsy and avoid calling mem0_memory.search or get_all with
filters containing a null user_id; instead log a warning (using logger.warning)
and return an empty/neutral Data result appropriate for build_search_results (so
callers don’t get null-scoped Mem0 results). Update build_search_results (and
its interaction with ingest_data if needed) to perform this check before
constructing filters or calling mem0_memory.search/get_all.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
Run ID: 19db78ef-e630-4008-9b55-4c3d86760d2c
⛔ Files ignored due to path filters (2)
src/backend/base/uv.lockis excluded by!**/*.lockuv.lockis excluded by!**/*.lock
📒 Files selected for processing (4)
src/backend/base/pyproject.tomlsrc/backend/tests/unit/components/bundles/mem0/test_mem0_component.pysrc/lfx/src/lfx/_assets/component_index.jsonsrc/lfx/src/lfx/components/mem0/mem0_chat_memory.py
| "title_case": false, | ||
| "type": "code", | ||
| "value": "import os\n\nfrom mem0 import Memory, MemoryClient\n\nfrom lfx.base.memory.model import LCChatMemoryComponent\nfrom lfx.inputs.inputs import DictInput, HandleInput, MessageTextInput, NestedDictInput, SecretStrInput\nfrom lfx.io import Output\nfrom lfx.log.logger import logger\nfrom lfx.schema.data import Data\nfrom lfx.utils.validate_cloud import raise_error_if_astra_cloud_disable_component\n\ndisable_component_in_astra_cloud_msg = (\n \"Mem0 chat memory is not supported in Astra cloud environment. Please use local storage mode or mem0 cloud.\"\n)\n\n\nclass Mem0MemoryComponent(LCChatMemoryComponent):\n display_name = \"Mem0 Chat Memory\"\n description = \"Retrieves and stores chat messages using Mem0 memory storage.\"\n name = \"mem0_chat_memory\"\n icon: str = \"Mem0\"\n inputs = [\n NestedDictInput(\n name=\"mem0_config\",\n display_name=\"Mem0 Configuration\",\n info=\"\"\"Configuration dictionary for initializing Mem0 memory instance.\n Example:\n {\n \"graph_store\": {\n \"provider\": \"neo4j\",\n \"config\": {\n \"url\": \"neo4j+s://your-neo4j-url\",\n \"username\": \"neo4j\",\n \"password\": \"your-password\"\n }\n },\n \"version\": \"v1.1\"\n }\"\"\",\n input_types=[\"Data\", \"JSON\"],\n ),\n MessageTextInput(\n name=\"ingest_message\",\n display_name=\"Message to Ingest\",\n info=\"The message content to be ingested into Mem0 memory.\",\n ),\n HandleInput(\n name=\"existing_memory\",\n display_name=\"Existing Memory Instance\",\n input_types=[\"Memory\"],\n info=\"Optional existing Mem0 memory instance. If not provided, a new instance will be created.\",\n ),\n MessageTextInput(\n name=\"user_id\", display_name=\"User ID\", info=\"Identifier for the user associated with the messages.\"\n ),\n MessageTextInput(\n name=\"search_query\", display_name=\"Search Query\", info=\"Input text for searching related memories in Mem0.\"\n ),\n SecretStrInput(\n name=\"mem0_api_key\",\n display_name=\"Mem0 API Key\",\n info=\"API key for Mem0 platform. Leave empty to use the local version.\",\n ),\n DictInput(\n name=\"metadata\",\n display_name=\"Metadata\",\n info=\"Additional metadata to associate with the ingested message.\",\n advanced=True,\n ),\n SecretStrInput(\n name=\"openai_api_key\",\n display_name=\"OpenAI API Key\",\n required=False,\n info=\"API key for OpenAI. Required if using OpenAI Embeddings without a provided configuration.\",\n ),\n ]\n\n outputs = [\n Output(name=\"memory\", display_name=\"Mem0 Memory\", method=\"ingest_data\"),\n Output(\n name=\"search_results\",\n display_name=\"Search Results\",\n method=\"build_search_results\",\n ),\n ]\n\n def build_mem0(self) -> Memory:\n \"\"\"Initializes a Mem0 memory instance based on provided configuration and API keys.\"\"\"\n # Check if we're in Astra cloud environment and raise an error if we are.\n raise_error_if_astra_cloud_disable_component(disable_component_in_astra_cloud_msg)\n if self.openai_api_key:\n os.environ[\"OPENAI_API_KEY\"] = self.openai_api_key\n\n try:\n if not self.mem0_api_key:\n return Memory.from_config(config_dict=dict(self.mem0_config)) if self.mem0_config else Memory()\n if self.mem0_config:\n return MemoryClient.from_config(api_key=self.mem0_api_key, config_dict=dict(self.mem0_config))\n return MemoryClient(api_key=self.mem0_api_key)\n except ImportError as e:\n msg = \"Mem0 is not properly installed. Please install it with 'pip install -U mem0ai'.\"\n raise ImportError(msg) from e\n\n def ingest_data(self) -> Memory:\n \"\"\"Ingests a new message into Mem0 memory and returns the updated memory instance.\"\"\"\n # Check if we're in Astra cloud environment and raise an error if we are.\n raise_error_if_astra_cloud_disable_component(disable_component_in_astra_cloud_msg)\n mem0_memory = self.existing_memory or self.build_mem0()\n\n if not self.ingest_message or not self.user_id:\n logger.warning(\"Missing 'ingest_message' or 'user_id'; cannot ingest data.\")\n return mem0_memory\n\n metadata = self.metadata or {}\n\n logger.info(\"Ingesting message for user_id: %s\", self.user_id)\n\n try:\n mem0_memory.add(self.ingest_message, user_id=self.user_id, metadata=metadata)\n except Exception:\n logger.exception(\"Failed to add message to Mem0 memory.\")\n raise\n\n return mem0_memory\n\n def build_search_results(self) -> Data:\n \"\"\"Searches the Mem0 memory for related messages based on the search query and returns the results.\"\"\"\n # Check if we're in Astra cloud environment and raise an error if we are.\n raise_error_if_astra_cloud_disable_component(disable_component_in_astra_cloud_msg)\n mem0_memory = self.ingest_data()\n search_query = self.search_query\n user_id = self.user_id\n\n logger.info(\"Search query: %s\", search_query)\n\n try:\n if search_query:\n logger.info(\"Performing search with query.\")\n related_memories = mem0_memory.search(query=search_query, user_id=user_id)\n else:\n logger.info(\"Retrieving all memories for user_id: %s\", user_id)\n related_memories = mem0_memory.get_all(user_id=user_id)\n except Exception:\n logger.exception(\"Failed to retrieve related memories from Mem0.\")\n raise\n\n logger.info(\"Related memories retrieved: %s\", related_memories)\n return related_memories\n" | ||
| "value": "import os\n\nfrom mem0 import Memory, MemoryClient\n\nfrom lfx.base.memory.model import LCChatMemoryComponent\nfrom lfx.inputs.inputs import DictInput, HandleInput, MessageTextInput, NestedDictInput, SecretStrInput\nfrom lfx.io import Output\nfrom lfx.log.logger import logger\nfrom lfx.schema.data import Data\nfrom lfx.utils.validate_cloud import raise_error_if_astra_cloud_disable_component\n\ndisable_component_in_astra_cloud_msg = (\n \"Mem0 chat memory is not supported in Astra cloud environment. Please use local storage mode or mem0 cloud.\"\n)\n\n\nclass Mem0MemoryComponent(LCChatMemoryComponent):\n display_name = \"Mem0 Chat Memory\"\n description = \"Retrieves and stores chat messages using Mem0 memory storage.\"\n name = \"mem0_chat_memory\"\n icon: str = \"Mem0\"\n inputs = [\n NestedDictInput(\n name=\"mem0_config\",\n display_name=\"Mem0 Configuration\",\n info=\"\"\"Configuration dictionary for initializing Mem0 memory instance.\n Example:\n {\n \"graph_store\": {\n \"provider\": \"neo4j\",\n \"config\": {\n \"url\": \"neo4j+s://your-neo4j-url\",\n \"username\": \"neo4j\",\n \"password\": \"your-password\"\n }\n },\n \"version\": \"v1.1\"\n }\"\"\",\n input_types=[\"Data\", \"JSON\"],\n ),\n MessageTextInput(\n name=\"ingest_message\",\n display_name=\"Message to Ingest\",\n info=\"The message content to be ingested into Mem0 memory.\",\n ),\n HandleInput(\n name=\"existing_memory\",\n display_name=\"Existing Memory Instance\",\n input_types=[\"Memory\"],\n info=\"Optional existing Mem0 memory instance. If not provided, a new instance will be created.\",\n ),\n MessageTextInput(\n name=\"user_id\", display_name=\"User ID\", info=\"Identifier for the user associated with the messages.\"\n ),\n MessageTextInput(\n name=\"search_query\", display_name=\"Search Query\", info=\"Input text for searching related memories in Mem0.\"\n ),\n SecretStrInput(\n name=\"mem0_api_key\",\n display_name=\"Mem0 API Key\",\n info=\"API key for Mem0 platform. Leave empty to use the local version.\",\n ),\n DictInput(\n name=\"metadata\",\n display_name=\"Metadata\",\n info=\"Additional metadata to associate with the ingested message.\",\n advanced=True,\n ),\n SecretStrInput(\n name=\"openai_api_key\",\n display_name=\"OpenAI API Key\",\n required=False,\n info=\"API key for OpenAI. Required if using OpenAI Embeddings without a provided configuration.\",\n ),\n ]\n\n outputs = [\n Output(name=\"memory\", display_name=\"Mem0 Memory\", method=\"ingest_data\"),\n Output(\n name=\"search_results\",\n display_name=\"Search Results\",\n method=\"build_search_results\",\n ),\n ]\n\n def build_mem0(self) -> Memory:\n \"\"\"Initializes a Mem0 memory instance based on provided configuration and API keys.\"\"\"\n # Check if we're in Astra cloud environment and raise an error if we are.\n raise_error_if_astra_cloud_disable_component(disable_component_in_astra_cloud_msg)\n if self.openai_api_key:\n os.environ[\"OPENAI_API_KEY\"] = self.openai_api_key\n\n try:\n if not self.mem0_api_key:\n return Memory.from_config(config_dict=dict(self.mem0_config)) if self.mem0_config else Memory()\n if self.mem0_config:\n return MemoryClient.from_config(api_key=self.mem0_api_key, config_dict=dict(self.mem0_config))\n return MemoryClient(api_key=self.mem0_api_key)\n except ImportError as e:\n msg = \"Mem0 is not properly installed. Please install it with 'pip install -U mem0ai'.\"\n raise ImportError(msg) from e\n\n def ingest_data(self) -> Memory:\n \"\"\"Ingests a new message into Mem0 memory and returns the updated memory instance.\"\"\"\n # Check if we're in Astra cloud environment and raise an error if we are.\n raise_error_if_astra_cloud_disable_component(disable_component_in_astra_cloud_msg)\n mem0_memory = self.existing_memory or self.build_mem0()\n\n if not self.ingest_message or not self.user_id:\n logger.warning(\"Missing 'ingest_message' or 'user_id'; cannot ingest data.\")\n return mem0_memory\n\n metadata = self.metadata or {}\n\n logger.info(\"Ingesting message for user_id: %s\", self.user_id)\n\n try:\n mem0_memory.add(self.ingest_message, user_id=self.user_id, metadata=metadata)\n except Exception:\n logger.exception(\"Failed to add message to Mem0 memory.\")\n raise\n\n return mem0_memory\n\n def build_search_results(self) -> Data:\n \"\"\"Searches the Mem0 memory for related messages based on the search query and returns the results.\"\"\"\n # Check if we're in Astra cloud environment and raise an error if we are.\n raise_error_if_astra_cloud_disable_component(disable_component_in_astra_cloud_msg)\n mem0_memory = self.ingest_data()\n search_query = self.search_query\n user_id = self.user_id\n\n logger.info(\"Search query: %s\", search_query)\n\n try:\n if search_query:\n logger.info(\"Performing search with query.\")\n related_memories = mem0_memory.search(query=search_query, filters={\"user_id\": user_id})\n else:\n logger.info(\"Retrieving all memories for user_id: %s\", user_id)\n related_memories = mem0_memory.get_all(filters={\"user_id\": user_id})\n except Exception:\n logger.exception(\"Failed to retrieve related memories from Mem0.\")\n raise\n\n logger.info(\"Related memories retrieved: %s\", related_memories)\n return related_memories\n" |
Contributor
There was a problem hiding this comment.
🧩 Analysis chain
🌐 Web query:
For mem0ai 2.x, what is the behavior of Memory.search() and Memory.get_all() when filters={"user_id": None} (or when user_id is omitted)? Does it return unscoped/all-user memories?
💡 Result:
In mem0ai 2.x (OSS “Memory” SDK), the documented behavior is that entity scoping is done via the filters object; passing entity IDs as top-level kwargs is rejected, and reads are “scoped by filters”.[1][2][3] 1) If filters={"user_id": None} - The docs state that entity IDs must be passed inside filters and reads return memories “scoped by filters”.[1][2][3] - However, the specific case of filters with user_id=None (or JSON null) is not explicitly documented as returning “all-user/unscoped” memories. The platform feature page instead describes “implicit null scoping”: records where other primary entities are null are treated specially, and wildcards behave differently than null-only values.[3] - Therefore, based on the documented entity-scoping model, filters={"user_id": None} should not be interpreted as “unscoped/all users”; it would target the null-valued user scope (i.e., records created with user_id null / absent), not every user.[3] 2) If user_id is omitted from filters - The docs describe filters-based scoping but do not say that omitting user_id means “return all users”.[2][3] - The entity-scoped-memory feature page explains that records are partitioned by primary entity and that “wildcards” ("") are required to include broader sets; it contrasts wildcard behavior with null-only scoping and gives examples of constructing broader joins using OR and wildcards.[3] - So, omitting user_id is best treated as “use the default scoping behavior for your entity identifiers”, which is not equivalent to all-user retrieval; to retrieve broader sets you’d need explicit wildcard logic (e.g., user_id="") as described by the feature docs.[3] Practical conclusion - No: filters={"user_id": None} is not documented to return unscoped/all-user memories; it aligns with “null scoping” rather than “no scope”.[3] - Also not: omitting user_id is not documented to automatically mean “all-user”; if you want all users, you should use the documented wildcard mechanism in the filters (e.g., "user_id": "*") or an OR-based broadening pattern, rather than relying on null/omitted behavior.[3]
Citations:
- 1: https://docs.mem0.ai/api-reference/memory/search-memories
- 2: https://docs.mem0.ai/api-reference/memory/get-memories
- 3: https://docs.mem0.ai/platform/features/entity-scoped-memory
Avoid querying Mem0 when user_id is missing in build_search_results.
build_search_results always calls mem0_memory.search/get_all with filters={"user_id": user_id}; when self.user_id is empty/None, Mem0’s “entity scoping” via filters will apply “null scoping” (targeting only null/absent user_id records, not all users), leading to incorrect/unexpected results. Add an early guard before calling search()/get_all() when user_id is falsy.
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@src/lfx/src/lfx/_assets/component_index.json` at line 92004, In
build_search_results, add an early guard that checks if self.user_id is falsy
and avoid calling mem0_memory.search or get_all with filters containing a null
user_id; instead log a warning (using logger.warning) and return an
empty/neutral Data result appropriate for build_search_results (so callers don’t
get null-scoped Mem0 results). Update build_search_results (and its interaction
with ingest_data if needed) to perform this check before constructing filters or
calling mem0_memory.search/get_all.
Contributor
Frontend Unit Test Coverage ReportCoverage Summary
Unit Test Results
|
Adam-Aghili
added a commit
that referenced
this pull request
May 25, 2026
Adam-Aghili
added a commit
that referenced
this pull request
May 26, 2026
erichare
pushed a commit
that referenced
this pull request
May 27, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Validation
Summary by CodeRabbit