cognee 0.3.7.dev2__tar.gz → 0.3.9__tar.gz

{cognee-0.3.7.dev2 → cognee-0.3.9}/.env.template

@@ -242,13 +242,14 @@ LITELLM_LOG="ERROR"
 
 ########## Local LLM via Ollama ###############################################
 
+
 #LLM_API_KEY ="ollama"
 #LLM_MODEL="llama3.1:8b"
 #LLM_PROVIDER="ollama"
 #LLM_ENDPOINT="http://localhost:11434/v1"
 #EMBEDDING_PROVIDER="ollama"
 #EMBEDDING_MODEL="nomic-embed-text:latest"
-#EMBEDDING_ENDPOINT="http://localhost:11434/api/embeddings"
+#EMBEDDING_ENDPOINT="http://localhost:11434/api/embed"
 #EMBEDDING_DIMENSIONS=768
 #HUGGINGFACE_TOKENIZER="nomic-ai/nomic-embed-text-v1.5"
 

cognee-0.3.9/AGENTS.md

@@ -0,0 +1,132 @@
+## Repository Guidelines
+
+This document summarizes how to work with the cognee repository: how it’s organized, how to build, test, lint, and contribute. It mirrors our actual tooling and CI while providing quick commands for local development.
+
+## Project Structure & Module Organization
+
+- `cognee/`: Core Python library and API.
+  - `api/`: FastAPI application and versioned routers (add, cognify, memify, search, delete, users, datasets, responses, visualize, settings, sync, update, checks).
+  - `cli/`: CLI entry points and subcommands invoked via `cognee` / `cognee-cli`.
+  - `infrastructure/`: Databases, LLM providers, embeddings, loaders, and storage adapters.
+  - `modules/`: Domain logic (graph, retrieval, ontology, users, processing, observability, etc.).
+  - `tasks/`: Reusable tasks (e.g., code graph, web scraping, storage). Extend with new tasks here.
+  - `eval_framework/`: Evaluation utilities and adapters.
+  - `shared/`: Cross-cutting helpers (logging, settings, utils).
+  - `tests/`: Unit, integration, CLI, and end-to-end tests organized by feature.
+  - `__main__.py`: Entrypoint to route to CLI.
+- `cognee-mcp/`: Model Context Protocol server exposing cognee as MCP tools (SSE/HTTP/stdio). Contains its own README and Dockerfile.
+- `cognee-frontend/`: Next.js UI for local development and demos.
+- `distributed/`: Utilities for distributed execution (Modal, workers, queues).
+- `examples/`: Example scripts demonstrating the public APIs and features (graph, code graph, multimodal, permissions, etc.).
+- `notebooks/`: Jupyter notebooks for demos and tutorials.
+- `alembic/`: Database migrations for relational backends.
+
+Notes:
+- Co-locate feature-specific helpers under their respective package (`modules/`, `infrastructure/`, or `tasks/`).
+- Extend the system by adding new tasks, loaders, or retrievers rather than modifying core pipeline mechanisms.
+
+## Build, Test, and Development Commands
+
+Python (root) – requires Python >= 3.10 and < 3.14. We recommend `uv` for speed and reproducibility.
+
+- Create/refresh env and install dev deps:
+```bash
+uv sync --dev --all-extras --reinstall
+```
+
+- Run the CLI (examples):
+```bash
+uv run cognee-cli add "Cognee turns documents into AI memory."
+uv run cognee-cli cognify
+uv run cognee-cli search "What does cognee do?"
+uv run cognee-cli -ui   # Launches UI, backend API, and MCP server together
+```
+
+- Start the FastAPI server directly:
+```bash
+uv run python -m cognee.api.client
+```
+
+- Run tests (CI mirrors these commands):
+```bash
+uv run pytest cognee/tests/unit/ -v
+uv run pytest cognee/tests/integration/ -v
+```
+
+- Lint and format (ruff):
+```bash
+uv run ruff check .
+uv run ruff format .
+```
+
+- Optional static type checks (mypy):
+```bash
+uv run mypy cognee/
+```
+
+MCP Server (`cognee-mcp/`):
+
+- Install and run locally:
+```bash
+cd cognee-mcp
+uv sync --dev --all-extras --reinstall
+uv run python src/server.py               # stdio (default)
+uv run python src/server.py --transport sse
+uv run python src/server.py --transport http --host 127.0.0.1 --port 8000 --path /mcp
+```
+
+- API Mode (connect to a running Cognee API):
+```bash
+uv run python src/server.py --transport sse --api-url http://localhost:8000 --api-token YOUR_TOKEN
+```
+
+- Docker quickstart (examples): see `cognee-mcp/README.md` for full details
+```bash
+docker run -e TRANSPORT_MODE=http --env-file ./.env -p 8000:8000 --rm -it cognee/cognee-mcp:main
+```
+
+Frontend (`cognee-frontend/`):
+```bash
+cd cognee-frontend
+npm install
+npm run dev     # Next.js dev server
+npm run lint    # ESLint
+npm run build && npm start
+```
+
+## Coding Style & Naming Conventions
+
+Python:
+- 4-space indentation, modules and functions in `snake_case`, classes in `PascalCase`.
+- Public APIs should be type-annotated where practical.
+- Use `ruff format` before committing; `ruff check` enforces import hygiene and style (line-length 100 configured in `pyproject.toml`).
+- Prefer explicit, structured error handling. Use shared logging utilities in `cognee.shared.logging_utils`.
+
+MCP server and Frontend:
+- Follow the local `README.md` and ESLint/TypeScript configuration in `cognee-frontend/`.
+
+## Testing Guidelines
+
+- Place Python tests under `cognee/tests/`.
+  - Unit tests: `cognee/tests/unit/`
+  - Integration tests: `cognee/tests/integration/`
+  - CLI tests: `cognee/tests/cli_tests/`
+- Name test files `test_*.py`. Use `pytest.mark.asyncio` for async tests.
+- Avoid external state; rely on test fixtures and the CI-provided env vars when LLM/embedding providers are required. See CI workflows under `.github/workflows/` for expected environment variables.
+- When adding public APIs, provide/update targeted examples under `examples/python/`.
+
+## Commit & Pull Request Guidelines
+
+- Use clear, imperative subjects (≤ 72 chars) and conventional commit styling in PR titles. Our CI validates semantic PR titles (see `.github/workflows/pr_lint`). Examples:
+  - `feat(graph): add temporal edge weighting`
+  - `fix(api): handle missing auth cookie`
+  - `docs: update installation instructions`
+- Reference related issues/discussions in the PR body and provide brief context.
+- PRs should describe scope, list local test commands run, and mention any impacts on MCP server or UI if applicable.
+- Sign commits and affirm the DCO (see `CONTRIBUTING.md`).
+
+## CI Mirrors Local Commands
+
+Our GitHub Actions run the same ruff checks and pytest suites shown above (`.github/workflows/basic_tests.yml` and related workflows). Use the commands in this document locally to minimize CI surprises.
+
+

{cognee-0.3.7.dev2 → cognee-0.3.9}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cognee
-Version: 0.3.7.dev2
+Version: 0.3.9
 Summary: Cognee - is a library for enriching LLM context with a semantic layer for better understanding and reasoning.
 Project-URL: Homepage, https://www.cognee.ai
 Project-URL: Repository, https://github.com/topoteretes/cognee
@@ -248,7 +248,7 @@ Hosted platform:
 
 ### 📦 Installation
 
-You can install Cognee using either **pip**, **poetry**, **uv** or any other python package manager.
+You can install Cognee using either **pip**, **poetry**, **uv** or any other python package manager..
 
 Cognee supports Python 3.10 to 3.12
 

{cognee-0.3.7.dev2 → cognee-0.3.9}/README.md

@@ -97,7 +97,7 @@ Hosted platform:
 
 ### 📦 Installation
 
-You can install Cognee using either **pip**, **poetry**, **uv** or any other python package manager.
+You can install Cognee using either **pip**, **poetry**, **uv** or any other python package manager..
 
 Cognee supports Python 3.10 to 3.12
 

{cognee-0.3.7.dev2 → cognee-0.3.9}/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-0.3.7.dev2 → cognee-0.3.9}/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-0.3.7.dev2 → cognee-0.3.9}/cognee/infrastructure/files/utils/get_file_metadata.py

@@ -1,6 +1,6 @@
 import io
 import os.path
-from typing import BinaryIO, TypedDict
+from typing import BinaryIO, TypedDict, Optional
 from pathlib import Path
 
 from cognee.shared.logging_utils import get_logger
@@ -27,7 +27,7 @@ class FileMetadata(TypedDict):
     file_size: int
 
 
-async def get_file_metadata(file: BinaryIO) -> FileMetadata:
+async def get_file_metadata(file: BinaryIO, name: Optional[str] = None) -> FileMetadata:
     """
     Retrieve metadata from a file object.
 
@@ -53,7 +53,7 @@ async def get_file_metadata(file: BinaryIO) -> FileMetadata:
     except io.UnsupportedOperation as error:
         logger.error(f"Error retrieving content hash for file: {file.name} \n{str(error)}\n\n")
 
-    file_type = guess_file_type(file)
+    file_type = guess_file_type(file, name)
 
     file_path = getattr(file, "name", None) or getattr(file, "full_name", None)
 

cognee-0.3.9/cognee/infrastructure/files/utils/guess_file_type.py

@@ -0,0 +1,67 @@
+import io
+from pathlib import Path
+from typing import BinaryIO, Optional, Any
+import filetype
+from tempfile import SpooledTemporaryFile
+from filetype.types.base import Type
+
+
+class FileTypeException(Exception):
+    """
+    Represents an exception for file type errors.
+
+    This exception is raised when an invalid file type is encountered. It includes a custom
+    message to describe the error.
+
+    Parameters:
+    -----------
+
+        - message (str): The message describing the exception error.
+    """
+
+    message: str
+
+    def __init__(self, message: str):
+        self.message = message
+
+
+def guess_file_type(file: BinaryIO, name: Optional[str] = None) -> filetype.Type:
+    """
+    Guess the file type from the given binary file stream.
+
+    If the file type cannot be determined from content, attempts to infer from extension.
+    If still unable to determine, raise a FileTypeException with an appropriate message.
+
+    Parameters:
+    -----------
+
+        - file (BinaryIO): A binary file stream to analyze for determining the file type.
+
+    Returns:
+    --------
+
+        - filetype.Type: The guessed file type, represented as filetype.Type.
+    """
+
+    # Note: If file has .txt or .text extension, consider it a plain text file as filetype.guess may not detect it properly
+    # as it contains no magic number encoding
+    ext = None
+    if isinstance(file, str):
+        ext = Path(file).suffix
+    elif name is not None:
+        ext = Path(name).suffix
+
+    if ext in [".txt", ".text"]:
+        file_type = Type("text/plain", "txt")
+        return file_type
+
+    file_type = filetype.guess(file)
+
+    # If file type could not be determined consider it a plain text file as they don't have magic number encoding
+    if file_type is None:
+        file_type = Type("text/plain", "txt")
+
+    if file_type is None:
+        raise FileTypeException(f"Unknown file detected: {file.name}.")
+
+    return file_type

cognee-0.3.9/cognee/infrastructure/llm/prompts/extract_query_time.txt

@@ -0,0 +1,13 @@
+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-0.3.7.dev2 → cognee-0.3.9}/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-0.3.7.dev2 → cognee-0.3.9}/cognee/infrastructure/loaders/core/audio_loader.py

@@ -42,6 +42,7 @@ class AudioLoader(LoaderInterface):
             "audio/wav",
             "audio/amr",
             "audio/aiff",
+            "audio/x-wav",
         ]
 
     @property

{cognee-0.3.7.dev2 → cognee-0.3.9}/cognee/modules/ingestion/data_types/BinaryData.py

@@ -30,7 +30,7 @@ class BinaryData(IngestionData):
 
     async def ensure_metadata(self):
         if self.metadata is None:
-            self.metadata = await get_file_metadata(self.data)
+            self.metadata = await get_file_metadata(self.data, name=self.name)
 
             if self.metadata["name"] is None:
                 self.metadata["name"] = self.name

{cognee-0.3.7.dev2 → cognee-0.3.9}/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-0.3.7.dev2 → cognee-0.3.9}/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-0.3.7.dev2 → cognee-0.3.9}/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: