cognee-agensgraph 0.2.0__tar.gz

cognee_agensgraph-0.2.0/.gitignore

@@ -0,0 +1,59 @@
+# Build
+.pants.d/
+dist/
+migration_scripts/
+
+# IDEs
+.idea
+.vscode
+.zed
+
+# Local development
+venv/
+*/.venv/
+.venv/
+.ipynb_checkpoints
+.__pycache__
+__pycache__
+dev_notebooks/
+.pytest_cache/
+
+# Other
+llamaindex_registry.txt
+packages_to_bump_deduped.txt
+.env
+credentials.json
+token.json
+.python-version
+.DS_Store
+/storage/
+
+# Data & Storage
+inputs/
+rag_storage/
+examples/input/
+examples/output/
+output*/
+custom_kg/
+data/
+
+# Miscellaneous
+.DS_Store
+TODO.md
+ignore_this.txt
+*.ignore.*
+
+# Project-specific files
+dickens*/
+book.txt
+LightRAG.pdf
+download_models_hf.py
+lightrag-dev/
+gui/
+
+# cognee
+.cognee_system/
+.data_storage/
+
+# Demo run output
+**/examples/demos/.data/

cognee_agensgraph-0.2.0/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright (c) 2025 SKAI Worldwide Co., Ltd.
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

cognee_agensgraph-0.2.0/PKG-INFO

@@ -0,0 +1,260 @@
+Metadata-Version: 2.4
+Name: cognee-agensgraph
+Version: 0.2.0
+Summary: AgensGraph graph + vector adapters for Cognee.
+Project-URL: Homepage, https://github.com/skaiworldwide-oss/agensgraph-ai/tree/main/cognee
+Project-URL: Repository, https://github.com/skaiworldwide-oss/agensgraph-ai
+Project-URL: Issues, https://github.com/skaiworldwide-oss/agensgraph-ai/issues
+Author-email: Muhammad Taha Naveed <skaisw@skaiworldwide.com>
+License-Expression: Apache-2.0
+License-File: LICENSE
+Keywords: agensgraph,cognee,graph store,knowledge graph,rag,vector store
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Database
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: <3.14,>=3.10
+Requires-Dist: cognee<1.0.0,>=0.2.1
+Requires-Dist: numpy>=1.24
+Requires-Dist: pgvector>=0.2.5
+Requires-Dist: psycopg[binary,pool]>=3.1.0
+Description-Content-Type: text/markdown
+
+# Cognee AgensGraph adapters
+
+[Cognee](https://github.com/topoteretes/cognee) is an **AI-memory** framework: you
+`add` your data, `cognify` it into a **knowledge graph + embeddings**, then
+`search` that memory many ways. This package lets **one AgensGraph database back
+both** of cognee's stores at once.
+
+AgensGraph is PostgreSQL + Cypher + `pgvector`, so a single database can be cognee's
+**graph store** *and* its **vector store**:
+
+- **Graph adapter** (`GRAPH_DATABASE_PROVIDER=agensgraph`) — the knowledge graph
+  (entities + relationships) as a Cypher property graph.
+- **Vector adapter** (`VECTOR_DB_PROVIDER=agensgraph`) — the embeddings as
+  `pgvector` HNSW tables.
+
+Use both for one-database simplicity, or use just the graph adapter and keep your
+vectors elsewhere. (cognee's small bookkeeping — datasets, users — stays in a local
+SQLite file by default.)
+
+## Try the demos
+
+The fastest way to see what this enables is the runnable demo suite in
+[`examples/demos/`](./examples/demos) — five focused examples on real public
+datasets (Wikipedia, CC-News, a Python repo), each with its own README and a
+**pre-executed notebook** you can read without running anything:
+
+| Demo | What it shows |
+|---|---|
+| [01 · Search modes](./examples/demos/01_search_modes) | Build a knowledge graph from Wikipedia, then query it ten ways — `GRAPH_COMPLETION` (+ summary / chain-of-thought / context-extension variants), `RAG_COMPLETION`, `INSIGHTS`, `CHUNKS`, `SUMMARIES`, `NATURAL_LANGUAGE`, and raw `CYPHER` |
+| [02 · Typed](./examples/demos/02_typed) | Ontology-guided extraction — make the graph follow *your* domain vocabulary |
+| [03 · Memory](./examples/demos/03_memory) | A multi-dataset memory layer — named datasets, `node_set` tags, incremental builds |
+| [04 · Code graph](./examples/demos/04_code_graph) | Turn a Python repo into a code knowledge graph; `SearchType.CODE` + visualize |
+| [05 · Explore](./examples/demos/05_explore) | Inspect the AgensGraph-backed graph — metrics, traversal, raw Cypher, HTML visualization |
+
+Start at [`examples/demos/README.md`](./examples/demos/README.md).
+
+## Installation
+
+```bash
+# from the cognee/ directory of this repo
+pip install -e .          # installs cognee-agensgraph + the cognee core it requires
+# (uv: uv pip install -e .)
+```
+
+Then activate the adapters by importing the package once at startup:
+
+```python
+import cognee_agensgraph   # registers the agensgraph graph + vector providers
+```
+
+## Quickstart
+
+```python
+import asyncio
+import cognee
+from cognee.infrastructure.databases.graph import get_graph_engine
+import pathlib
+import os
+import pprint
+import cognee_agensgraph
+
+async def main():
+    # Set up agensgraph credentials in .env file and get the values from environment variables
+    agensgraph_url = os.getenv("GRAPH_DATABASE_URL")
+
+    # Configure agensgraph as the graph database provider
+    cognee.config.set_graph_db_config(
+        {
+            "graph_database_url": agensgraph_url,  # agensgraph connection DSN
+            "graph_database_provider": "agensgraph",  # Specify agensgraph as provider
+        }
+    )
+    
+    # Optional: Set custom data and system directories
+    system_path = pathlib.Path(__file__).parent
+    cognee.config.system_root_directory(os.path.join(system_path, ".cognee_system"))
+    cognee.config.data_root_directory(os.path.join(system_path, ".data_storage"))
+    
+    # Sample data to add to the knowledge graph
+    sample_data = [
+        "Artificial intelligence is a branch of computer science that aims to create intelligent machines.",
+        "Machine learning is a subset of AI that focuses on algorithms that can learn from data.",
+        "Deep learning is a subset of machine learning that uses neural networks with many layers.",
+        "Natural language processing enables computers to understand and process human language.",
+        "Computer vision allows machines to interpret and make decisions based on visual information."
+    ]
+    
+    try:
+        print("Adding data to Cognee...")
+        await cognee.add(sample_data, "ai_knowledge")
+        
+        print("Processing data with Cognee...")
+        await cognee.cognify(["ai_knowledge"])
+        
+        print("Searching for insights...")
+        search_results = await cognee.search(
+            query_type=cognee.SearchType.GRAPH_COMPLETION,
+            query_text="artificial intelligence"
+        )
+        
+        print(f"Found {len(search_results)} insights:")
+        for i, result in enumerate(search_results, 1):
+            print(f"{i}. {result}")
+            
+        print("\nSearching with Chain of Thought reasoning...")
+        await cognee.search(
+            query_type=cognee.SearchType.GRAPH_COMPLETION_COT,
+            query_text="How does machine learning relate to artificial intelligence and what are its applications?"
+        )
+
+        print("\nYou can get the graph data directly, or visualize it in an HTML file like below:")
+        
+        # Get graph data directly
+        graph_engine = await get_graph_engine()
+        graph_data = await graph_engine.get_graph_data()
+        
+        print("\nDirect graph data:")
+        pprint.pprint(graph_data)
+
+        # Or visualize it in HTML
+        print("\nVisualizing the graph...")
+        await cognee.visualize_graph(system_path / "graph.html")
+        print(f"Graph visualization saved to {system_path / 'graph.html'}")
+
+    except Exception as e:
+        print(f"Error: {e}")
+        print("Make sure AgensGraph is running and your DSN is correct.")
+
+if __name__ == "__main__":
+    asyncio.run(main())
+```
+
+## Requirements
+
+- Python >= 3.10, <= 3.13
+- AgensGraph database instance
+- psycopg >= 3.1.0 with extras(binary and pool)
+
+## Configuration
+
+The adapter requires the following configuration using the `set_graph_db_config()` method:
+
+```python
+cognee.config.set_graph_db_config({
+    "graph_database_url": "postgresql://username:password@host:port/dbname",
+    "graph_database_provider": "agensgraph",
+})
+```
+
+To use AgensGraph as the **vector store** as well (pgvector HNSW), point the
+vector config at the same database:
+
+```python
+cognee.config.set_vector_db_config({
+    "vector_db_url": "postgresql://username:password@host:port/dbname",
+    "vector_db_provider": "agensgraph",
+})
+```
+
+### Environment Variables
+
+Set the following environment variables or pass them directly in the config:
+
+```bash
+export GRAPH_DATABASE_URL="postgresql://username:password@host:port/dbname"
+export GRAPH_DATABASE_PROVIDER="agensgraph"
+# Optional: AgensGraph as the vector store too
+export VECTOR_DB_URL="postgresql://username:password@host:port/dbname"
+export VECTOR_DB_PROVIDER="agensgraph"
+```
+
+**Alternative:** You can also use the [`.env.template`](https://github.com/topoteretes/cognee/blob/main/.env.template) file from the main cognee repository. Copy it to your project directory, rename it to `.env`, and fill in your AgensGraph configuration values.
+
+### Optional Configuration
+
+You can also set custom directories for system and data storage:
+
+```python
+cognee.config.system_root_directory("/path/to/system")
+cognee.config.data_root_directory("/path/to/data")
+```
+
+## Features
+
+- **Graph adapter** (`GRAPH_DATABASE_PROVIDER=agensgraph`): full GraphDBInterface
+  support over AgensGraph's Cypher, async, with graph-completion and
+  Chain-of-Thought search, direct `get_graph_engine()` access, and HTML
+  visualization.
+- **Vector adapter** (`VECTOR_DB_PROVIDER=agensgraph`): cognee VectorDBInterface
+  over pgvector with an HNSW cosine index.
+
+## Performance & indexing
+
+- A **single async connection pool** is shared (refcounted) across the graph and
+  vector adapters and opened once per process; `graph_path` is reapplied per
+  checkout, not per query.
+- **Graph ingest and lookups are index-backed**: nodes MERGE/lookup on an
+  indexed `id` (the previous build indexed the wrong property, making ingest
+  O(N²) and every lookup a sequential scan); `add_edges` is UNWIND-batched per
+  relationship type.
+- **Vector search** uses an HNSW (`vector_cosine_ops`) index; the column is typed
+  `vector(dim)` so the query's `<=>` cast matches the index and it is used at
+  scale.
+
+> The vector embedding dimension is fixed when a collection's table is first
+> created; to change embedding models, drop the affected collection tables.
+
+## What's new in 0.2.0
+
+- **A working, dedicated vector adapter.** `AgensgraphVectorAdapter` implements
+  cognee's `VectorDBInterface` over `pgvector` (HNSW cosine), selectable with
+  `VECTOR_DB_PROVIDER=agensgraph`, so AgensGraph can be cognee's vector store too.
+- **End-to-end `cognify` with AgensGraph vectors.** The vector adapter implements
+  cognee's indexing hooks (`create_vector_index` / `index_data_points`), so a full
+  `add → cognify → search` runs with `VECTOR_DB_PROVIDER=agensgraph` (previously
+  `cognify` raised `AttributeError` on the missing methods).
+- **Fixed an O(N²) ingest bug.** Node lookups and MERGE key on the `id` property,
+  but the only index was on a different label/property — so ingest was quadratic
+  and every lookup did a sequential scan. Ingest and id lookups are now backed by a
+  `base_id_idx ON "__Node__" (id)` index (≈5000 nodes + 5000 edges in ~1.2s).
+- **Batched `add_edges`.** Edges are UNWIND-batched per relationship type instead
+  of one query per edge; `name` is indexed and used by nodeset retrieval (was a
+  sequential scan).
+- **Shared async connection pool.** One refcounted pool is opened once per process
+  and reused by both adapters; `graph_path` is reapplied per checkout, not per query.
+- **Correctness fixes.** `add_node`, `has_node`, `has_edge`, `get_neighbors`, and
+  `get_disconnected_nodes` were broken (bad parameter binding / never awaited /
+  undefined variables / non-existent method calls / invalid Cypher) and now work.
+- **Modernized packaging.** Poetry → hatchling, Python ≥3.10.
+
+## Contributing
+
+Contributions are welcome! Please open an issue or submit a Pull Request.