cognee 0.3.7.dev2__py3-none-any.whl → 0.3.8__py3-none-any.whl

cognee/base_config.py

@@ -1,4 +1,5 @@
 import os
+from pathlib import Path
 from typing import Optional
 from functools import lru_cache
 from cognee.root_dir import get_absolute_path, ensure_absolute_path
@@ -11,6 +12,9 @@ class BaseConfig(BaseSettings):
     data_root_directory: str = get_absolute_path(".data_storage")
     system_root_directory: str = get_absolute_path(".cognee_system")
     cache_root_directory: str = get_absolute_path(".cognee_cache")
+    logs_root_directory: str = os.getenv(
+        "COGNEE_LOGS_DIR", str(os.path.join(os.path.dirname(os.path.dirname(__file__)), "logs"))
+    )
     monitoring_tool: object = Observer.NONE
 
     @pydantic.model_validator(mode="after")
@@ -30,6 +34,8 @@ class BaseConfig(BaseSettings):
         # Require absolute paths for root directories
         self.data_root_directory = ensure_absolute_path(self.data_root_directory)
         self.system_root_directory = ensure_absolute_path(self.system_root_directory)
+        self.logs_root_directory = ensure_absolute_path(self.logs_root_directory)
+
         # Set monitoring tool based on available keys
         if self.langfuse_public_key and self.langfuse_secret_key:
             self.monitoring_tool = Observer.LANGFUSE
@@ -49,6 +55,7 @@ class BaseConfig(BaseSettings):
             "system_root_directory": self.system_root_directory,
             "monitoring_tool": self.monitoring_tool,
             "cache_root_directory": self.cache_root_directory,
+            "logs_root_directory": self.logs_root_directory,
         }
 
 

cognee/infrastructure/databases/vector/create_vector_engine.py

@@ -47,7 +47,7 @@ def create_vector_engine(
             embedding_engine=embedding_engine,
         )
 
-    if vector_db_provider == "pgvector":
+    if vector_db_provider.lower() == "pgvector":
         from cognee.infrastructure.databases.relational import get_relational_config
 
         # Get configuration for postgres database
@@ -78,7 +78,7 @@ def create_vector_engine(
             embedding_engine,
         )
 
-    elif vector_db_provider == "chromadb":
+    elif vector_db_provider.lower() == "chromadb":
         try:
             import chromadb
         except ImportError:
@@ -94,7 +94,7 @@ def create_vector_engine(
             embedding_engine=embedding_engine,
         )
 
-    elif vector_db_provider == "neptune_analytics":
+    elif vector_db_provider.lower() == "neptune_analytics":
         try:
             from langchain_aws import NeptuneAnalyticsGraph
         except ImportError:
@@ -122,7 +122,7 @@ def create_vector_engine(
             embedding_engine=embedding_engine,
         )
 
-    else:
+    elif vector_db_provider.lower() == "lancedb":
         from .lancedb.LanceDBAdapter import LanceDBAdapter
 
         return LanceDBAdapter(
@@ -130,3 +130,9 @@ def create_vector_engine(
             api_key=vector_db_key,
             embedding_engine=embedding_engine,
         )
+
+    else:
+        raise EnvironmentError(
+            f"Unsupported graph database provider: {vector_db_provider}. "
+            f"Supported providers are: {', '.join(list(supported_databases.keys()) + ['LanceDB', 'PGVector', 'neptune_analytics', 'ChromaDB'])}"
+        )

cognee/infrastructure/files/utils/guess_file_type.py

@@ -22,89 +22,6 @@ class FileTypeException(Exception):
         self.message = message
 
 
-class TxtFileType(filetype.Type):
-    """
-    Represents a text file type with specific MIME and extension properties.
-
-    Public methods:
-    - match: Determines whether a given buffer matches the text file type.
-    """
-
-    MIME = "text/plain"
-    EXTENSION = "txt"
-
-    def __init__(self):
-        super(TxtFileType, self).__init__(mime=TxtFileType.MIME, extension=TxtFileType.EXTENSION)
-
-    def match(self, buf):
-        """
-        Determine if the given buffer contains text content.
-
-        Parameters:
-        -----------
-
-            - buf: The buffer to check for text content.
-
-        Returns:
-        --------
-
-            Returns True if the buffer is identified as text content, otherwise False.
-        """
-        return is_text_content(buf)
-
-
-txt_file_type = TxtFileType()
-
-filetype.add_type(txt_file_type)
-
-
-class CustomPdfMatcher(filetype.Type):
-    """
-    Match PDF file types based on MIME type and extension.
-
-    Public methods:
-    - match
-
-    Instance variables:
-    - MIME: The MIME type of the PDF.
-    - EXTENSION: The file extension of the PDF.
-    """
-
-    MIME = "application/pdf"
-    EXTENSION = "pdf"
-
-    def __init__(self):
-        super(CustomPdfMatcher, self).__init__(
-            mime=CustomPdfMatcher.MIME, extension=CustomPdfMatcher.EXTENSION
-        )
-
-    def match(self, buf):
-        """
-        Determine if the provided buffer is a PDF file.
-
-        This method checks for the presence of the PDF signature in the buffer.
-
-        Raises:
-        - TypeError: If the buffer is not of bytes type.
-
-        Parameters:
-        -----------
-
-            - buf: The buffer containing the data to be checked.
-
-        Returns:
-        --------
-
-            Returns True if the buffer contains a PDF signature, otherwise returns False.
-        """
-        return b"PDF-" in buf
-
-
-custom_pdf_matcher = CustomPdfMatcher()
-
-filetype.add_type(custom_pdf_matcher)
-
-
 def guess_file_type(file: BinaryIO) -> filetype.Type:
     """
     Guess the file type from the given binary file stream.

cognee/infrastructure/llm/prompts/extract_query_time.txt

@@ -1,15 +1,13 @@
-For the purposes of identifying timestamps in a query, you are tasked with extracting relevant timestamps from the query.
-## Timestamp requirements
-- If the query contains interval extrack both starts_at and ends_at  properties
-- If the query contains an instantaneous timestamp, starts_at and ends_at should be the same
-- If the query its open-ended (before 2009 or after 2009), the corresponding non defined end of the time should be none
-    -For example: "before 2009" -- starts_at: None, ends_at: 2009 or  "after 2009" -- starts_at: 2009, ends_at: None
-- Put always the data that comes first in time as starts_at and the timestamps that comes second in time as ends_at
-- If starts_at or ends_at cannot be extracted both of them has to be None
-## Output Format
-Your reply should be a JSON: list of dictionaries with the following structure:
-```python
-class QueryInterval(BaseModel):
-    starts_at: Optional[Timestamp] = None
-    ends_at: Optional[Timestamp] = None
-```
+You are tasked with identifying relevant time periods where the answer to a given query should be searched.
+Current date is:  `{{ time_now }}`. Determine relevant period(s) and return structured intervals.
+
+Extraction rules:
+
+1. Query without specific timestamp: use the time period with starts_at set to None and ends_at set to now.
+2. Explicit time intervals: If the query specifies a range (e.g., from 2010 to 2020, between January and March 2023), extract both start and end dates. Always assign the earlier date to starts_at and the later date to ends_at.
+3. Single timestamp: If the query refers to one specific moment (e.g., in 2015, on March 5, 2022), set starts_at and ends_at to that same timestamp.
+4. Open-ended time references: For phrases such as "before X" or "after X", represent the unspecified side as None. For example: before 2009 → starts_at: None, ends_at: 2009; after 2009 → starts_at: 2009, ends_at: None.
+5. Current-time references ("now", "current", "today"): If the query explicitly refers to the present, set both starts_at and ends_at to now (the ingestion timestamp).
+6. "Who is" and "Who was" questions: These imply a general identity or biographical inquiry without a specific temporal scope. Set both starts_at and ends_at to None.
+7. Ordering rule: Always ensure the earlier date is assigned to starts_at and the later date to ends_at.
+8. No temporal information: If no valid or inferable time reference is found, set both starts_at and ends_at to None.

cognee/infrastructure/loaders/LoaderEngine.py

@@ -1,6 +1,7 @@
 import filetype
 from typing import Dict, List, Optional, Any
 from .LoaderInterface import LoaderInterface
+from cognee.infrastructure.files.utils.guess_file_type import guess_file_type
 from cognee.shared.logging_utils import get_logger
 
 logger = get_logger(__name__)
@@ -80,7 +81,7 @@ class LoaderEngine:
         """
         from pathlib import Path
 
-        file_info = filetype.guess(file_path)
+        file_info = guess_file_type(file_path)
 
         path_extension = Path(file_path).suffix.lstrip(".")
 

cognee/modules/ontology/get_default_ontology_resolver.py

@@ -21,7 +21,8 @@ def get_ontology_resolver_from_env(
             Supported value: "rdflib".
         matching_strategy (str): The matching strategy to apply.
             Supported value: "fuzzy".
-        ontology_file_path (str): Path to the ontology file required for the resolver.
+        ontology_file_path (str): Path to the ontology file(s) required for the resolver.
+            Can be a single path or comma-separated paths for multiple files.
 
     Returns:
         BaseOntologyResolver: An instance of the requested ontology resolver.
@@ -31,8 +32,13 @@ def get_ontology_resolver_from_env(
             or if required parameters are missing.
     """
     if ontology_resolver == "rdflib" and matching_strategy == "fuzzy" and ontology_file_path:
+        if "," in ontology_file_path:
+            file_paths = [path.strip() for path in ontology_file_path.split(",")]
+        else:
+            file_paths = ontology_file_path
+
         return RDFLibOntologyResolver(
-            matching_strategy=FuzzyMatchingStrategy(), ontology_file=ontology_file_path
+            matching_strategy=FuzzyMatchingStrategy(), ontology_file=file_paths
         )
     else:
         raise EnvironmentError(

cognee/modules/ontology/rdf_xml/RDFLibOntologyResolver.py

@@ -2,7 +2,7 @@ import os
 import difflib
 from cognee.shared.logging_utils import get_logger
 from collections import deque
-from typing import List, Tuple, Dict, Optional, Any
+from typing import List, Tuple, Dict, Optional, Any, Union
 from rdflib import Graph, URIRef, RDF, RDFS, OWL
 
 from cognee.modules.ontology.exceptions import (
@@ -26,22 +26,50 @@ class RDFLibOntologyResolver(BaseOntologyResolver):
 
     def __init__(
         self,
-        ontology_file: Optional[str] = None,
+        ontology_file: Optional[Union[str, List[str]]] = None,
         matching_strategy: Optional[MatchingStrategy] = None,
     ) -> None:
         super().__init__(matching_strategy)
         self.ontology_file = ontology_file
         try:
-            if ontology_file and os.path.exists(ontology_file):
+            files_to_load = []
+            if ontology_file is not None:
+                if isinstance(ontology_file, str):
+                    files_to_load = [ontology_file]
+                elif isinstance(ontology_file, list):
+                    files_to_load = ontology_file
+                else:
+                    raise ValueError(
+                        f"ontology_file must be a string, list of strings, or None. Got: {type(ontology_file)}"
+                    )
+
+            if files_to_load:
                 self.graph = Graph()
-                self.graph.parse(ontology_file)
-                logger.info("Ontology loaded successfully from file: %s", ontology_file)
+                loaded_files = []
+                for file_path in files_to_load:
+                    if os.path.exists(file_path):
+                        self.graph.parse(file_path)
+                        loaded_files.append(file_path)
+                        logger.info("Ontology loaded successfully from file: %s", file_path)
+                    else:
+                        logger.warning(
+                            "Ontology file '%s' not found. Skipping this file.",
+                            file_path,
+                        )
+
+                if not loaded_files:
+                    logger.info(
+                        "No valid ontology files found. No owl ontology will be attached to the graph."
+                    )
+                    self.graph = None
+                else:
+                    logger.info("Total ontology files loaded: %d", len(loaded_files))
             else:
                 logger.info(
-                    "Ontology file '%s' not found. No owl ontology will be attached to the graph.",
-                    ontology_file,
+                    "No ontology file provided. No owl ontology will be attached to the graph."
                 )
                 self.graph = None
+
             self.build_lookup()
         except Exception as e:
             logger.error("Failed to load ontology", exc_info=e)

cognee/modules/retrieval/temporal_retriever.py

@@ -1,7 +1,7 @@
 import os
 import asyncio
 from typing import Any, Optional, List, Type
-
+from datetime import datetime
 
 from operator import itemgetter
 from cognee.infrastructure.databases.vector import get_vector_engine
@@ -79,7 +79,11 @@ class TemporalRetriever(GraphCompletionRetriever):
         else:
             base_directory = None
 
-        system_prompt = render_prompt(prompt_path, {}, base_directory=base_directory)
+        time_now = datetime.now().strftime("%d-%m-%Y")
+
+        system_prompt = render_prompt(
+            prompt_path, {"time_now": time_now}, base_directory=base_directory
+        )
 
         interval = await LLMGateway.acreate_structured_output(query, system_prompt, QueryInterval)
 
@@ -108,8 +112,6 @@ class TemporalRetriever(GraphCompletionRetriever):
 
         graph_engine = await get_graph_engine()
 
-        triplets = []
-
         if time_from and time_to:
             ids = await graph_engine.collect_time_ids(time_from=time_from, time_to=time_to)
         elif time_from: