cognee 0.3.4.dev3__py3-none-any.whl → 0.3.5__py3-none-any.whl

cognee/modules/retrieval/utils/brute_force_triplet_search.py

@@ -89,7 +89,6 @@ async def get_memory_fragment(
 
 async def brute_force_triplet_search(
     query: str,
-    user: User,
     top_k: int = 5,
     collections: Optional[List[str]] = None,
     properties_to_project: Optional[List[str]] = None,
@@ -102,7 +101,6 @@ async def brute_force_triplet_search(
 
     Args:
         query (str): The search query.
-        user (User): The user performing the search.
         top_k (int): The number of top results to retrieve.
         collections (Optional[List[str]]): List of collections to query.
         properties_to_project (Optional[List[str]]): List of properties to project.
@@ -139,12 +137,10 @@ async def brute_force_triplet_search(
 
     query_vector = (await vector_engine.embedding_engine.embed_text([query]))[0]
 
-    send_telemetry("cognee.brute_force_triplet_search EXECUTION STARTED", user.id)
-
     async def search_in_collection(collection_name: str):
         try:
             return await vector_engine.search(
-                collection_name=collection_name, query_vector=query_vector, limit=0
+                collection_name=collection_name, query_vector=query_vector, limit=None
             )
         except CollectionNotFoundError:
             return []
@@ -176,20 +172,14 @@ async def brute_force_triplet_search(
 
         results = await memory_fragment.calculate_top_triplet_importances(k=top_k)
 
-        send_telemetry("cognee.brute_force_triplet_search EXECUTION COMPLETED", user.id)
-
         return results
 
     except CollectionNotFoundError:
         return []
     except Exception as error:
         logger.error(
-            "Error during brute force search for user: %s, query: %s. Error: %s",
-            user.id,
+            "Error during brute force search for query: %s. Error: %s",
             query,
             error,
         )
-        send_telemetry(
-            "cognee.brute_force_triplet_search EXECUTION FAILED", user.id, {"error": str(error)}
-        )
         raise error

cognee/modules/retrieval/utils/completion.py

@@ -1,5 +1,6 @@
 from typing import Optional
 from cognee.infrastructure.llm.LLMGateway import LLMGateway
+from cognee.infrastructure.llm.prompts import render_prompt, read_query_prompt
 
 
 async def generate_completion(
@@ -11,10 +12,8 @@ async def generate_completion(
 ) -> str:
     """Generates a completion using LLM with given context and prompts."""
     args = {"question": query, "context": context}
-    user_prompt = LLMGateway.render_prompt(user_prompt_path, args)
-    system_prompt = (
-        system_prompt if system_prompt else LLMGateway.read_query_prompt(system_prompt_path)
-    )
+    user_prompt = render_prompt(user_prompt_path, args)
+    system_prompt = system_prompt if system_prompt else read_query_prompt(system_prompt_path)
 
     return await LLMGateway.acreate_structured_output(
         text_input=user_prompt,
@@ -29,9 +28,7 @@ async def summarize_text(
     system_prompt: str = None,
 ) -> str:
     """Summarizes text using LLM with the specified prompt."""
-    system_prompt = (
-        system_prompt if system_prompt else LLMGateway.read_query_prompt(system_prompt_path)
-    )
+    system_prompt = system_prompt if system_prompt else read_query_prompt(system_prompt_path)
 
     return await LLMGateway.acreate_structured_output(
         text_input=text,

cognee/modules/search/methods/get_search_type_tools.py

@@ -15,6 +15,7 @@ from cognee.modules.retrieval.completion_retriever import CompletionRetriever
 from cognee.modules.retrieval.graph_completion_retriever import GraphCompletionRetriever
 from cognee.modules.retrieval.temporal_retriever import TemporalRetriever
 from cognee.modules.retrieval.coding_rules_retriever import CodingRulesRetriever
+from cognee.modules.retrieval.jaccard_retrival import JaccardChunksRetriever
 from cognee.modules.retrieval.graph_summary_completion_retriever import (
     GraphSummaryCompletionRetriever,
 )
@@ -152,6 +153,12 @@ async def get_search_type_tools(
             TemporalRetriever(top_k=top_k).get_completion,
             TemporalRetriever(top_k=top_k).get_context,
         ],
+        SearchType.CHUNKS_LEXICAL: (
+            lambda _r=JaccardChunksRetriever(top_k=top_k): [
+                _r.get_completion,
+                _r.get_context,
+            ]
+        )(),
         SearchType.CODING_RULES: [
             CodingRulesRetriever(rules_nodeset_name=node_name).get_existing_rules,
         ],

cognee/modules/search/methods/no_access_control_search.py

@@ -35,7 +35,7 @@ async def no_access_control_search(
         [get_completion, get_context] = search_tools
 
         if only_context:
-            return await get_context(query_text)
+            return None, await get_context(query_text), []
 
         context = await get_context(query_text)
         result = await get_completion(query_text, context)

cognee/modules/search/methods/search.py

@@ -19,7 +19,9 @@ from cognee.modules.search.types import (
 from cognee.modules.search.operations import log_query, log_result
 from cognee.modules.users.models import User
 from cognee.modules.data.models import Dataset
-from cognee.modules.users.permissions.methods import get_specific_user_permission_datasets
+from cognee.modules.data.methods.get_authorized_existing_datasets import (
+    get_authorized_existing_datasets,
+)
 
 from .get_search_type_tools import get_search_type_tools
 from .no_access_control_search import no_access_control_search
@@ -143,20 +145,35 @@ async def search(
                 context = prepared_search_results["context"]
                 datasets = prepared_search_results["datasets"]
 
-                return_value.append(
-                    {
-                        "search_result": [result] if result else None,
-                        "dataset_id": datasets[0].id,
-                        "dataset_name": datasets[0].name,
-                        "graphs": graphs,
-                    }
-                )
+                if only_context:
+                    return_value.append(
+                        {
+                            "search_result": [context] if context else None,
+                            "dataset_id": datasets[0].id,
+                            "dataset_name": datasets[0].name,
+                            "graphs": graphs,
+                        }
+                    )
+                else:
+                    return_value.append(
+                        {
+                            "search_result": [result] if result else None,
+                            "dataset_id": datasets[0].id,
+                            "dataset_name": datasets[0].name,
+                            "graphs": graphs,
+                        }
+                    )
             return return_value
         else:
             return_value = []
-            for search_result in search_results:
-                result, context, datasets = search_result
-                return_value.append(result)
+            if only_context:
+                for search_result in search_results:
+                    prepared_search_results = await prepare_search_result(search_result)
+                    return_value.append(prepared_search_results["context"])
+            else:
+                for search_result in search_results:
+                    result, context, datasets = search_result
+                    return_value.append(result)
             # For maintaining backwards compatibility
             if len(return_value) == 1 and isinstance(return_value[0], list):
                 return return_value[0]
@@ -187,7 +204,9 @@ async def authorized_search(
     Not to be used outside of active access control mode.
     """
     # Find datasets user has read access for (if datasets are provided only return them. Provided user has read access)
-    search_datasets = await get_specific_user_permission_datasets(user.id, "read", dataset_ids)
+    search_datasets = await get_authorized_existing_datasets(
+        datasets=dataset_ids, permission_type="read", user=user
+    )
 
     if use_combined_context:
         search_responses = await search_in_datasets_context(

cognee/modules/search/types/SearchType.py

@@ -17,3 +17,4 @@ class SearchType(Enum):
     FEEDBACK = "FEEDBACK"
     TEMPORAL = "TEMPORAL"
     CODING_RULES = "CODING_RULES"
+    CHUNKS_LEXICAL = "CHUNKS_LEXICAL"

cognee/modules/users/methods/create_user.py

@@ -61,8 +61,6 @@ async def create_user(
                     if auto_login:
                         await session.refresh(user)
 
-                    await _create_tutorial_notebook(user.id, session)
-
                     return user
     except UserAlreadyExists as error:
         print(f"User {email} already exists")

cognee/modules/users/permissions/methods/authorized_give_permission_on_datasets.py

@@ -9,6 +9,18 @@ from uuid import UUID
 async def authorized_give_permission_on_datasets(
     principal_id: UUID, dataset_ids: Union[List[UUID], UUID], permission_name: str, owner_id: UUID
 ):
+    """
+        Give permission to certain datasets to a user.
+        The request owner must have the necessary permission to share the datasets.
+    Args:
+        principal_id: Id of user to whom datasets are shared
+        dataset_ids: Ids of datasets to share
+        permission_name: Name of permission to give
+        owner_id: Id of the request owner
+
+    Returns:
+        None
+    """
     # If only a single dataset UUID is provided transform it to a list
     if not isinstance(dataset_ids, list):
         dataset_ids = [dataset_ids]

cognee/modules/users/permissions/methods/check_permission_on_dataset.py

@@ -10,6 +10,17 @@ logger = get_logger()
 
 
 async def check_permission_on_dataset(user: User, permission_type: str, dataset_id: UUID):
+    """
+        Check if a user has a specific permission on a dataset.
+    Args:
+        user: User whose permission is checked
+        permission_type: Type of permission to check
+        dataset_id: Id of the dataset
+
+    Returns:
+        None
+
+    """
     if user is None:
         user = await get_default_user()
 

cognee/modules/users/permissions/methods/get_all_user_permission_datasets.py

@@ -11,6 +11,16 @@ logger = get_logger()
 
 
 async def get_all_user_permission_datasets(user: User, permission_type: str) -> list[Dataset]:
+    """
+        Return a list of datasets the user has permission for.
+        If the user is part of a tenant, return datasets his roles have permission for.
+    Args:
+        user
+        permission_type
+
+    Returns:
+        list[Dataset]: List of datasets user has permission for
+    """
     datasets = list()
     # Get all datasets User has explicit access to
     datasets.extend(await get_principal_datasets(user, permission_type))

cognee/modules/users/permissions/methods/get_document_ids_for_user.py

@@ -8,6 +8,16 @@ from ...models import ACL, Permission
 
 
 async def get_document_ids_for_user(user_id: UUID, datasets: list[str] = None) -> list[str]:
+    """
+        Return a list of documents ids for which the user has read permission.
+        If datasets are specified, return only documents from those datasets.
+    Args:
+        user_id: Id of the user
+        datasets: List of datasets
+
+    Returns:
+        list[str]: List of documents for which the user has read permission
+    """
     db_engine = get_relational_engine()
 
     async with db_engine.get_async_session() as session:

cognee/modules/users/permissions/methods/get_principal.py

@@ -6,6 +6,15 @@ from ...models.Principal import Principal
 
 
 async def get_principal(principal_id: UUID):
+    """
+        Return information about a user based on their id
+    Args:
+        principal_id: Id of the user
+
+    Returns:
+        principal: Information about the user (principal)
+
+    """
     db_engine = get_relational_engine()
 
     async with db_engine.get_async_session() as session:

cognee/modules/users/permissions/methods/get_principal_datasets.py

@@ -9,6 +9,17 @@ from ...models.ACL import ACL
 
 
 async def get_principal_datasets(principal: Principal, permission_type: str) -> list[Dataset]:
+    """
+        Return a list of datasets for which the user (principal) has a certain permission.
+    Args:
+        principal: Information about the user
+        permission_type: Type of permission
+
+    Returns:
+        list[Dataset]: List of datasets for which the user (principal)
+        has the permission (permission_type).
+
+    """
     db_engine = get_relational_engine()
 
     async with db_engine.get_async_session() as session:

cognee/modules/users/permissions/methods/get_role.py

@@ -9,6 +9,16 @@ from ...models.Role import Role
 
 
 async def get_role(tenant_id: UUID, role_name: str):
+    """
+        Return the role with the name role_name of the given tenant.
+    Args:
+        tenant_id: Id of the given tenant
+        role_name: Name of the role
+
+    Returns
+        The role for the given tenant.
+
+    """
     db_engine = get_relational_engine()
 
     async with db_engine.get_async_session() as session:

cognee/modules/users/permissions/methods/get_specific_user_permission_datasets.py

@@ -15,9 +15,9 @@ async def get_specific_user_permission_datasets(
         Return a list of datasets user has given permission for. If a list of datasets is provided,
         verify for which datasets user has appropriate permission for and return list of datasets he has permission for.
     Args:
-        user_id:
-        permission_type:
-        dataset_ids:
+        user_id: Id of the user.
+        permission_type: Type of the permission.
+        dataset_ids: Ids of the provided datasets
 
     Returns:
         list[Dataset]: List of datasets user has permission for

cognee/modules/users/permissions/methods/get_tenant.py

@@ -8,6 +8,15 @@ from ...models.Tenant import Tenant
 
 
 async def get_tenant(tenant_id: UUID):
+    """
+        Return information about the tenant based on the given id.
+    Args:
+        tenant_id: Id of the given tenant
+
+    Returns
+        Information about the given tenant.
+
+    """
     db_engine = get_relational_engine()
 
     async with db_engine.get_async_session() as session:

cognee/modules/users/permissions/methods/give_default_permission_to_role.py

@@ -16,6 +16,15 @@ from cognee.modules.users.models import (
 
 
 async def give_default_permission_to_role(role_id: UUID, permission_name: str):
+    """
+        Give the permission with given name to the role with the given id as a default permission.
+    Args:
+        role_id: Id of the role
+        permission_name: Name of the permission
+
+    Returns:
+        None
+    """
     db_engine = get_relational_engine()
 
     async with db_engine.get_async_session() as session:

cognee/modules/users/permissions/methods/give_default_permission_to_tenant.py

@@ -16,6 +16,15 @@ from cognee.modules.users.models import (
 
 
 async def give_default_permission_to_tenant(tenant_id: UUID, permission_name: str):
+    """
+        Give the permission with given name to the tenant with the given id as a default permission.
+    Args:
+        tenant_id: Id of the tenant
+        permission_name: Name of the permission
+
+    Returns:
+        None
+    """
     db_engine = get_relational_engine()
     async with db_engine.get_async_session() as session:
         tenant = (

cognee/modules/users/permissions/methods/give_default_permission_to_user.py

@@ -16,6 +16,15 @@ from cognee.modules.users.models import (
 
 
 async def give_default_permission_to_user(user_id: UUID, permission_name: str):
+    """
+        Give the permission with given name to the user with the given id as a default permission.
+    Args:
+        user_id: Id of the tenant
+        permission_name: Name of the permission
+
+    Returns:
+        None
+    """
     db_engine = get_relational_engine()
     async with db_engine.get_async_session() as session:
         user = (await session.execute(select(User).where(User.id == user_id))).scalars().first()

cognee/modules/users/permissions/methods/give_permission_on_dataset.py

@@ -24,6 +24,16 @@ async def give_permission_on_dataset(
     dataset_id: UUID,
     permission_name: str,
 ):
+    """
+        Give a specific permission on a dataset to a user.
+    Args:
+        principal: User who is being given the permission on the dataset
+        dataset_id: Id of the dataset
+        permission_name: Name of permission to give
+
+    Returns:
+        None
+    """
     db_engine = get_relational_engine()
 
     async with db_engine.get_async_session() as session:

cognee/modules/users/roles/methods/add_user_to_role.py

@@ -21,6 +21,17 @@ from cognee.modules.users.models import (
 
 
 async def add_user_to_role(user_id: UUID, role_id: UUID, owner_id: UUID):
+    """
+        Add a user with the given id to the role with the given id.
+    Args:
+        user_id: Id of the user.
+        role_id: Id of the role.
+        owner_id: Id of the request owner.
+
+    Returns:
+        None
+
+    """
     db_engine = get_relational_engine()
     async with db_engine.get_async_session() as session:
         user = (await session.execute(select(User).where(User.id == user_id))).scalars().first()

cognee/modules/users/roles/methods/create_role.py

@@ -15,7 +15,17 @@ from cognee.modules.users.models import (
 async def create_role(
     role_name: str,
     owner_id: UUID,
-):
+) -> UUID:
+    """
+        Create a new role with the given name, if the request owner with the given id
+        has the necessary permission.
+    Args:
+        role_name: Name of the new role.
+        owner_id: Id of the request owner.
+
+    Returns:
+        None
+    """
     db_engine = get_relational_engine()
     async with db_engine.get_async_session() as session:
         user = await get_user(owner_id)
@@ -35,3 +45,4 @@ async def create_role(
 
         await session.commit()
         await session.refresh(role)
+        return role.id

cognee/modules/users/tenants/methods/add_user_to_tenant.py

@@ -13,6 +13,18 @@ from cognee.modules.users.exceptions import (
 
 
 async def add_user_to_tenant(user_id: UUID, tenant_id: UUID, owner_id: UUID):
+    """
+        Add a user with the given id to the tenant with the given id.
+        This can only be successful if the request owner with the given id is the tenant owner.
+    Args:
+        user_id: Id of the user.
+        tenant_id: Id of the tenant.
+        owner_id: Id of the request owner.
+
+    Returns:
+        None
+
+    """
     db_engine = get_relational_engine()
     async with db_engine.get_async_session() as session:
         user = await get_user(user_id)

cognee/modules/users/tenants/methods/create_tenant.py

@@ -7,7 +7,17 @@ from cognee.modules.users.models import Tenant
 from cognee.modules.users.methods import get_user
 
 
-async def create_tenant(tenant_name: str, user_id: UUID):
+async def create_tenant(tenant_name: str, user_id: UUID) -> UUID:
+    """
+        Create a new tenant with the given name, for the user with the given id.
+        This user is the owner of the tenant.
+    Args:
+        tenant_name: Name of the new tenant.
+        user_id: Id of the user.
+
+    Returns:
+        None
+    """
     db_engine = get_relational_engine()
     async with db_engine.get_async_session() as session:
         try:
@@ -24,5 +34,6 @@ async def create_tenant(tenant_name: str, user_id: UUID):
             user.tenant_id = tenant.id
             await session.merge(user)
             await session.commit()
+            return tenant.id
         except IntegrityError:
             raise EntityAlreadyExistsError(message="Tenant already exists.")

cognee/modules/visualization/cognee_network_visualization.py

@@ -1,6 +1,5 @@
 import os
 import json
-import networkx
 
 from cognee.shared.logging_utils import get_logger
 from cognee.infrastructure.files.storage.LocalFileStorage import LocalFileStorage
@@ -9,6 +8,8 @@ logger = get_logger()
 
 
 async def cognee_network_visualization(graph_data, destination_file_path: str = None):
+    import networkx
+
     nodes_data, edges_data = graph_data
 
     G = networkx.DiGraph()
@@ -22,6 +23,9 @@ async def cognee_network_visualization(graph_data, destination_file_path: str =
         "TableRow": "#f47710",
         "TableType": "#6510f4",
         "ColumnValue": "#13613a",
+        "SchemaTable": "#f47710",
+        "DatabaseSchema": "#6510f4",
+        "SchemaRelationship": "#13613a",
         "default": "#D3D3D3",
     }
 
@@ -104,7 +108,7 @@ async def cognee_network_visualization(graph_data, destination_file_path: str =
             .nodes circle { stroke: white; stroke-width: 0.5px; filter: drop-shadow(0 0 5px rgba(255,255,255,0.3)); }
             .node-label { font-size: 5px; font-weight: bold; fill: white; text-anchor: middle; dominant-baseline: middle; font-family: 'Inter', sans-serif; pointer-events: none; }
             .edge-label { font-size: 3px; fill: rgba(255, 255, 255, 0.7); text-anchor: middle; dominant-baseline: middle; font-family: 'Inter', sans-serif; pointer-events: none; }
-            
+
             .tooltip {
                 position: absolute;
                 text-align: left;
@@ -166,7 +170,7 @@ async def cognee_network_visualization(graph_data, destination_file_path: str =
                     // Create tooltip content for edge
                     var content = "<strong>Edge Information</strong><br/>";
                     content += "Relationship: " + d.relation + "<br/>";
-                    
+
                     // Show all weights
                     if (d.all_weights && Object.keys(d.all_weights).length > 0) {
                         content += "<strong>Weights:</strong><br/>";
@@ -176,23 +180,23 @@ async def cognee_network_visualization(graph_data, destination_file_path: str =
                     } else if (d.weight !== null && d.weight !== undefined) {
                         content += "Weight: " + d.weight + "<br/>";
                     }
-                    
+
                     if (d.relationship_type) {
                         content += "Type: " + d.relationship_type + "<br/>";
                     }
-                    
+
                     // Add other edge properties
                     if (d.edge_info) {
                         Object.keys(d.edge_info).forEach(function(key) {
-                            if (key !== 'weight' && key !== 'weights' && key !== 'relationship_type' && 
-                                key !== 'source_node_id' && key !== 'target_node_id' && 
-                                key !== 'relationship_name' && key !== 'updated_at' && 
+                            if (key !== 'weight' && key !== 'weights' && key !== 'relationship_type' &&
+                                key !== 'source_node_id' && key !== 'target_node_id' &&
+                                key !== 'relationship_name' && key !== 'updated_at' &&
                                 !key.startsWith('weight_')) {
                                 content += key + ": " + d.edge_info[key] + "<br/>";
                             }
                         });
                     }
-                    
+
                     tooltip.html(content)
                         .style("left", (d3.event.pageX + 10) + "px")
                         .style("top", (d3.event.pageY - 10) + "px")

cognee/shared/data_models.py

@@ -288,7 +288,6 @@ class SummarizedCode(BaseModel):
 class GraphDBType(Enum):
     NETWORKX = auto()
     NEO4J = auto()
-    FALKORDB = auto()
     KUZU = auto()
 
 

cognee/shared/utils.py

@@ -4,7 +4,6 @@ import os
 import ssl
 import requests
 from datetime import datetime, timezone
-import matplotlib.pyplot as plt
 import http.server
 import socketserver
 from threading import Thread
@@ -30,37 +29,6 @@ def create_secure_ssl_context() -> ssl.SSLContext:
     return ssl.create_default_context()
 
 
-def get_entities(tagged_tokens):
-    import nltk
-
-    nltk.download("maxent_ne_chunker", quiet=True)
-
-    from nltk.chunk import ne_chunk
-
-    return ne_chunk(tagged_tokens)
-
-
-def extract_pos_tags(sentence):
-    """Extract Part-of-Speech (POS) tags for words in a sentence."""
-    import nltk
-
-    # Ensure that the necessary NLTK resources are downloaded
-    nltk.download("words", quiet=True)
-    nltk.download("punkt", quiet=True)
-    nltk.download("averaged_perceptron_tagger", quiet=True)
-
-    from nltk.tag import pos_tag
-    from nltk.tokenize import word_tokenize
-
-    # Tokenize the sentence into words
-    tokens = word_tokenize(sentence)
-
-    # Tag each word with its corresponding POS tag
-    pos_tags = pos_tag(tokens)
-
-    return pos_tags
-
-
 def get_anonymous_id():
     """Creates or reads a anonymous user id"""
     tracking_id = os.getenv("TRACKING_ID", None)

cognee/tasks/chunk_naive_llm_classifier/chunk_naive_llm_classifier.py

@@ -7,7 +7,7 @@ from pydantic import BaseModel
 from cognee.infrastructure.databases.graph import get_graph_engine
 from cognee.infrastructure.databases.vector import get_vector_engine
 from cognee.infrastructure.engine.models import DataPoint
-from cognee.infrastructure.llm.LLMGateway import LLMGateway
+from cognee.infrastructure.llm.extraction import extract_categories
 from cognee.modules.chunking.models.DocumentChunk import DocumentChunk
 
 
@@ -40,7 +40,7 @@ async def chunk_naive_llm_classifier(
         return data_chunks
 
     chunk_classifications = await asyncio.gather(
-        *[LLMGateway.extract_categories(chunk.text, classification_model) for chunk in data_chunks],
+        *[extract_categories(chunk.text, classification_model) for chunk in data_chunks],
     )
 
     classification_data_points = []