9004 Commits (67428c4052bb63c211cae9f55f94762adbfc6019)

 

All Branches   

Search

Author	SHA1	Message	Date
Tomaz Bratanic	67428c4052	community[patch]: Neo4j enhanced schema (#20983) ... Scan the database for example values and provide them to an LLM for better inference of Text2cypher	2 months ago
Leonid Kuligin	dc70c23a11	docs: switched GCSLoaders docs to langchain-google-community (#20985) ... Thank you for contributing to LangChain! - [ ] **PR title**: "docs: switched GCSLoaders docs to langchain-google-community" - [ ] **PR message**: ***Delete this entire checklist*** and replace with - **Description:** switched GCSLoaders docs to langchain-google-community	2 months ago
aditya thomas	8b59bddc03	anthropic[patch]: add tests for secret_str for api key (#20986) ... **Description:** Add tests to check API keys are masked **Issue:** Resolves https://github.com/langchain-ai/langchain/issues/12165 for Anthropic models **Dependencies:** None	2 months ago
Pengcheng Liu	1fad39be1c	community[minor]: Add LarkSuite wiki document loader. (#21016) ... **Description:** Add LarkSuite wiki document loader. Refer to [LarkSuite api document ](https://open.feishu.cn/document/server-docs/docs/wiki-v2/space-node/list)for details. **Issue:** None **Dependencies:** None **Twitter handle:** None	2 months ago
Tomaz Bratanic	d36332476c	docs: Add neo4j relationship vector index docs (#20990) ... Co-authored-by: Bagatur <baskaryan@gmail.com>	2 months ago
Leonid Ganeline	dc7c06bc07	community[minor]: import fix (#20995) ... Issue: When the third-party package is not installed, whenever we need to `pip install <package>` the ImportError is raised. But sometimes, the `ValueError` or `ModuleNotFoundError` is raised. It is bad for consistency. Change: replaced the `ValueError` or `ModuleNotFoundError` with `ImportError` when we raise an error with the `pip install <package>` message. Note: Ideally, we replace all `try: import... except... raise ... `with helper functions like `import_aim` or just use the existing [langchain_core.utils.utils.guard_import](https://api.python.langchain.com/en/latest/utils/langchain_core.utils.utils.guard_import.html#langchain_core.utils.utils.guard_import) But it would be much bigger refactoring. @baskaryan Please, advice on this.	2 months ago
Karim Lalani	2ddac9a7c3	experimental[minor]: Add bind_tools and with_structured_output functions to OllamaFunctions (#20881) ... Implemented bind_tools for OllamaFunctions. Made OllamaFunctions sub class of ChatOllama. Implemented with_structured_output for OllamaFunctions. integration unit test has been updated. notebook has been updated. --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	2 months ago
Eugene Yurtsev	d781560722	cli[minor]: Add ipynb support, add text_splitters (#20963)	2 months ago
Vadym Barda	5e0b6b3e75	docs: update langserve link in LCEL docs (#20992)	2 months ago
Aditya	07ce39bfe7	docs: updated tutorials for Image generation and Vector Search (#21000) ... Description: docs: updated tutorials for Image generation and Vector Search @lkuligin for review --------- Co-authored-by: adityarane@google.com <adityarane@google.com>	2 months ago
Aditya	17bbb7d2a5	docs: updated tutorial for Gemini versions, included safety attribute updates (#21006) ... Description:updated tutorial for Gemini versions, included safety attribute updates @lkuligin For review --------- Co-authored-by: adityarane@google.com <adityarane@google.com>	2 months ago
WilliamEspegren	804390ba4b	community: Spider integration (#20937) ... Added the [Spider.cloud](https://spider.cloud) document loader. [Spider](https://github.com/spider-rs/spider) is the [fastest](https://github.com/spider-rs/spider/blob/main/benches/BENCHMARKS.md) and cheapest crawler that returns LLM-ready data. ``` - **Description:** Adds Spider data loader - **Dependencies:** spider-client - **Twitter handle:** @WilliamEspegren ``` --------- Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com> Co-authored-by: Bagatur <baskaryan@gmail.com> Co-authored-by: = <=> Co-authored-by: Chester Curme <chester.curme@gmail.com>	2 months ago
Jamie Lemon	6342217b93	docs: Moves "Using PyMuPDF" to higher up the page. (#20832) ... **Description:** This PR moves the **PyMuPDF** PDF loader solution to be underneath **PyPDF**. This is because it is the the 2nd most popular PyPI package after **PyPDF**. Please refer to these numbers, at the time of writing as follows: PyPDF https://www.pepy.tech/projects/PyPDF2 160 million PyMuPDF https://www.pepy.tech/projects/pymupdf 60 million PDFPlumber https://www.pepy.tech/projects/pdfplumber 23 million PDFMiner https://www.pepy.tech/projects/pdfminer 16 million PyPDFium2 https://www.pepy.tech/projects/pypdfium2 8 million Unstructured https://www.pepy.tech/projects/unstructured 8 million Please note I am an active contributor to https://github.com/pymupdf/PyMuPDF Many thanks! ---- **Twitter handle:** @artifex	2 months ago
Chouaieb Nemri	8097bec472	Added LogEntry, Any, Dict, List, Optional, TypedDict imports (#20970) ... Thank you for contributing to LangChain! - [ ] **PR title**: "package: docs" - [ ] **PR message**: - **Description:** Uptaded docs: Rag streaming use-cases notebook with LogEntry, Any, Dict, List, Optional, TypedDict imports - **Twitter handle:** c_nemri --------- Co-authored-by: Chester Curme <chester.curme@gmail.com>	2 months ago
ccurme	9ec7151317	fireworks: fix integration tests (#20973)	2 months ago
William FH	9fa9f05e5d	Catch System Error in ast parse (#20961) ... I can't seem to reproduce, but i got this: ``` SystemError: AST constructor recursion depth mismatch (before=102, after=37) ``` And the operation isn't critical for the actual forward pass so seems preferable to expand our caught exceptions	2 months ago
YH	2aca7fcdcf	core[patch]: Enhance link extraction with query parameters (#20259) ... **Description**: This update enhances the `extract_sub_links` function within the `langchain_core/utils/html.py` module to include query parameters in the extracted URLs. **Issue**: N/A **Dependencies**: No additional dependencies required for this change. **Twitter handle**: N/A Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	2 months ago
CT	0e917e319b	docs: Add langchainhub to pip install (#20185) ... Added langchainhub package in import statement which is required for "from langchain import hub" to work. Added sample code to add OpenAI key Co-authored-by: Chi Yan Tang <100466443+poochiekittie@users.noreply.github.com> Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	2 months ago
Pamela Fox	45092a36a2	docs: Fix langgraph link (#20244) ... Just a simple PR to fix a broken link. Apparently having backticks outside a link makes it render as code. Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	2 months ago
Chip Davis	e818c75f8a	infra: test directory loader multithreaded (#20281) ... This is a unit test for #20230 which was a fix for using multithreaded mode with directory loader @eyurtsev	2 months ago
Guilherme Zanotelli	f931a9ce60	community[patch]: Pass kwargs to SPARQLStore from RdfGraph (#20385) ... This introduces `store_kwargs` which behaves similarly to `graph_kwargs` on the `RdfGraph` object, which will enable users to pass `headers` and other arguments to the underlying `SPARQLStore` object. I have also made a [PR in `rdflib` to support passing `default_graph`](https://github.com/RDFLib/rdflib/pull/2761). Example usage: ```python from langchain_community.graphs import RdfGraph graph = RdfGraph( query_endpoint="http://localhost/sparql", standard="rdf", store_kwargs=dict( default_graph="http://example.com/mygraph" ) ) ``` <!--If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, hwchase17.--> --------- Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com> Co-authored-by: Bagatur <baskaryan@gmail.com>	2 months ago
Chandre Van Der Westhuizen	e57cf73cf5	docs: Added MindsDB provider (#20322) ... MindsDB integrates with LangChain, enabling users to deploy, serve, and fine-tune models available via LangChain within MindsDB, making them accessible to numerous data sources. --------- Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com> Co-authored-by: Bagatur <baskaryan@gmail.com>	2 months ago
Jorge Piedrahita Ortiz	40b2e2916b	community[minor]: Sambanova llm integration (#20955) ... - **Description:** Added [Sambanova systems](https://sambanova.ai/) integration, including sambaverse and sambastudio LLMs - **Dependencies:** sseclient-py (optional) --------- Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com> Co-authored-by: Bagatur <baskaryan@gmail.com>	2 months ago
Rahul Triptahi	955cf186d2	community[patch]: Ingest source, owner and full_path if present in Document's metadata. (#20949) ... Description: The PebbloSafeLoader should first check for owner, full_path and size in metadata before implementing its own logic. Dependencies: None Documentation: NA. Signed-off-by: Rahul Tripathi <rauhl.psit.ec@gmail.com> Co-authored-by: Rahul Tripathi <rauhl.psit.ec@gmail.com>	2 months ago
Amine Djeghri	790ea75cf7	community[minor]: add exllamav2 library for GPTQ & EXL2 models (#17817) ... Added 3 files : - Library : ExLlamaV2 - Test integration - Notebook --------- Co-authored-by: Bagatur <baskaryan@gmail.com> Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	2 months ago
Naveen Tatikonda	8bbdb4f6a0	community[patch]: Add OpenSearch as semantic cache (#20254) ... ### Description Use OpenSearch vector store as Semantic Cache. ### Twitter Handle **@OpenSearchProj** --------- Signed-off-by: Naveen Tatikonda <navtat@amazon.com> Co-authored-by: Harish Tatikonda <harishtatikonda@Harishs-MacBook-Air.local> Co-authored-by: EC2 Default User <ec2-user@ip-172-31-31-155.ec2.internal> Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com> Co-authored-by: Bagatur <baskaryan@gmail.com>	2 months ago
Giacomo Berardi	61f14f00d7	docs: `ElasticsearchCache` in cache integrations documentation (#20790) ... The package for LangChain integrations with Elasticsearch https://github.com/langchain-ai/langchain-elastic is going to contain a LLM cache integration in the next release (see https://github.com/langchain-ai/langchain-elastic/pull/14). This is the documentation contribution on the page dedicated to cache integrations	2 months ago
Mayank Solanki	8c085fc697	community[patch]: Added a function `from_existing_collection` in `Qdrant` vector database. (#20779) ... Issue: #20514 The current implementation of `construct_instance` expects a `texts: List[str]` that will call the embedding function. This might not be needed when we already have a client with collection and `path, you don't want to add any text. This PR adds a class method that returns a qdrant instance with an existing client. Here everytime cb6e5e56c2/libs/community/langchain_community/vectorstores/qdrant.py (L1592) `construct_instance` is called, this line sends some text for embedding generation. --------- Co-authored-by: Anush <anushshetty90@gmail.com>	2 months ago
Leonid Kuligin	893a924b90	core[minor], community[patch], langchain[patch]: move BaseChatLoader to core (#19607) ... Thank you for contributing to LangChain! - [ ] **PR title**: "core: move BaseChatLoader and BaseToolkit from community" - [ ] **PR message**: move BaseChatLoader and BaseToolkit --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	2 months ago
Erick Friis	d4befd0cfb	core: fix batch ordering test (#20952)	2 months ago
Eugene Yurtsev	8ed150b2fe	cli[minor]: Fix bug to account for name changes (#20948) ... * Fix bug to account for name changes / aliases * Generate migration list from langchain to langchain_core	2 months ago
ccurme	989e4a92c2	(infra) pass input to test-release (#20947)	2 months ago
Eugene Yurtsev	2fa0ff1a2d	cli[minor]: update code to generate migrations from langchain to community (#20946) ... Updates code that generates migrations from langchain to community	2 months ago
Erick Friis	078c5d9bc6	infra: nonmaster release checkbox (#20945) ... Co-authored-by: ccurme <chester.curme@gmail.com>	2 months ago
Leonid Kuligin	d4aec8fc8f	docs: adding langchain_google_community to the docs (#20665) ... Thank you for contributing to LangChain! - [ ] **PR title**: "docs: step1. adjusting langchain_community -> langchain_google_community" - [ ] - **Description:** step1. adjusting langchain_community -> langchain_google_community	2 months ago
ccurme	bf16cefd18	langchain: deprecate create_structured_output_runnable (#20933)	2 months ago
Erick Friis	38eccab3ae	upstage: release 0.1.3 (#20941)	2 months ago
Sean	e1c2e2fdfa	upstage: Upstage Groundedness Check parameter update (#20914) ... * Groundedness Check takes `str` or `list[Document]` as input. * Deprecate `GroundednessCheck` due to its naming. * Added `UpstageGroundednessCheck`. * Hotfix for Groundedness Check parameter. The name `query` was misleading and it should be `answer` instead. --------- Co-authored-by: Erick Friis <erick@langchain.dev>	2 months ago
ccurme	84b8e67c9c	mistral: release 0.1.4 (#20940)	2 months ago
ccurme	465fbaa30b	openai: release 0.1.4 (#20939)	2 months ago
Eugene Yurtsev	12c906f6ce	cli[minor]: Improve partner migrations (#20938) ... This auto generates partner migrations. At the moment the migration is from community -> partner. So one would need to run the migration script twice to go from langchain to partner.	2 months ago
Eugene Yurtsev	5653f36adc	cli[minor]: Add script to generate migrations for partner packages (#20932) ... Add script to help generate migrations. This works well for partner packages. Migrations are generated based on run time rather than static analysis (much simpler to get the correct migrations implemented). The script for generating migrations from langchain to community still needs work.	2 months ago
ccurme	fe1304afc4	openai: add unit test (#20931) ... Test a helper function that was added earlier.	2 months ago
Eugene Yurtsev	6598757037	cli[minor]: Add first version of migrate (#20902) ... Adds a first version of the migrate script.	2 months ago
Pengcheng Liu	d95e9fb67f	docs: add tool calling example in Tongyi chat model integration. (#20925) ... **Description:** add tool calling example in Tongyi chat model integration. **Issue:** None **Dependencies:** None	2 months ago
Lei Zhang	9281841cfe	community[patch]: fix integrated test case test_recursive_url_loader.py assertions (issue-20919) (#20920) ... **Description:** Fix integrated test case test_recursive_url_loader.py Local testing successful ```shell (venv) lei@LeideMacBook-Pro community % poetry run pytest tests/integration_tests/document_loaders/test_recursive_url_loader.py ================================================================================ test session starts ================================================================================ platform darwin -- Python 3.11.4, pytest-7.4.4, pluggy-1.4.0 -- /Users/zhanglei/Work/github/langchain/venv/bin/python cachedir: .pytest_cache rootdir: /Users/zhanglei/Work/github/langchain/libs/community configfile: pyproject.toml plugins: syrupy-4.6.1, asyncio-0.20.3, cov-4.1.0, vcr-1.0.2, mock-3.12.0, anyio-3.7.1, dotenv-0.5.2, requests-mock-1.11.0, socket-0.6.0 asyncio: mode=Mode.AUTO collected 6 items tests/integration_tests/document_loaders/test_recursive_url_loader.py::test_async_recursive_url_loader PASSED [ 16%] tests/integration_tests/document_loaders/test_recursive_url_loader.py::test_async_recursive_url_loader_deterministic PASSED [ 33%] tests/integration_tests/document_loaders/test_recursive_url_loader.py::test_sync_recursive_url_loader FAILED [ 50%] tests/integration_tests/document_loaders/test_recursive_url_loader.py::test_sync_async_equivalent PASSED [ 66%] tests/integration_tests/document_loaders/test_recursive_url_loader.py::test_loading_invalid_url PASSED [ 83%] tests/integration_tests/document_loaders/test_recursive_url_loader.py::test_sync_async_metadata_necessary_properties PASSED [100%] ===================================================================================== FAILURES ====================================================================================== __________________________________________________________________________ test_sync_recursive_url_loader ___________________________________________________________________________ def test_sync_recursive_url_loader() -> None: url = "https://docs.python.org/3.9/" loader = RecursiveUrlLoader( url, extractor=lambda _: "placeholder", use_async=False, max_depth=2 ) docs = loader.load() > assert len(docs) == 23 E AssertionError: assert 24 == 23 E + where 24 = len([Document(page_content='placeholder', metadata={'source': 'https://docs.python.org/3.9/', 'content_type': 'text/html', 'title': '3.9.18 Documentation', 'language': None}), Document(page_content='placeholder', metadata={'source': 'https://docs.python.org/3.9/py-modindex.html', 'content_type': 'text/html', 'title': 'Python Module Index — Python 3.9.18 documentation', 'language': None}), Document(page_content='placeholder', metadata={'source': 'https://docs.python.org/3.9/download.html', 'content_type': 'text/html', 'title': 'Download — Python 3.9.18 documentation', 'language': None}), Document(page_content='placeholder', metadata={'source': 'https://docs.python.org/3.9/howto/index.html', 'content_type': 'text/html', 'title': 'Python HOWTOs — Python 3.9.18 documentation', 'language': None}), Document(page_content='placeholder', metadata={'source': 'https://docs.python.org/3.9/whatsnew/index.html', 'content_type': 'text/html', 'title': 'Whatâ\x80\x99s New in Python — Python 3.9.18 documentation', 'language': None}), Document(page_content='placeholder', metadata={'source': 'https://docs.python.org/3.9/c-api/index.html', 'content_type': 'text/html', 'title': 'Python/C API Reference Manual — Python 3.9.18 documentation', 'language': None}), ...]) tests/integration_tests/document_loaders/test_recursive_url_loader.py:38: AssertionError ================================================================================= warnings summary ================================================================================== tests/integration_tests/document_loaders/test_recursive_url_loader.py::test_async_recursive_url_loader tests/integration_tests/document_loaders/test_recursive_url_loader.py::test_async_recursive_url_loader_deterministic tests/integration_tests/document_loaders/test_recursive_url_loader.py::test_sync_recursive_url_loader tests/integration_tests/document_loaders/test_recursive_url_loader.py::test_sync_async_equivalent tests/integration_tests/document_loaders/test_recursive_url_loader.py::test_sync_async_metadata_necessary_properties /Users/zhanglei/.pyenv/versions/3.11.4/lib/python3.11/html/parser.py:170: XMLParsedAsHTMLWarning: It looks like you're parsing an XML document using an HTML parser. If this really is an HTML document (maybe it's XHTML?), you can ignore or filter this warning. If it's XML, you should know that using an XML parser will be more reliable. To parse this document as XML, make sure you have the lxml package installed, and pass the keyword argument `features="xml"` into the BeautifulSoup constructor. k = self.parse_starttag(i) -- Docs: https://docs.pytest.org/en/stable/how-to/capture-warnings.html ================================================================================ slowest 5 durations ================================================================================ 56.75s call tests/integration_tests/document_loaders/test_recursive_url_loader.py::test_async_recursive_url_loader_deterministic 38.99s call tests/integration_tests/document_loaders/test_recursive_url_loader.py::test_async_recursive_url_loader 31.20s call tests/integration_tests/document_loaders/test_recursive_url_loader.py::test_sync_async_metadata_necessary_properties 30.37s call tests/integration_tests/document_loaders/test_recursive_url_loader.py::test_sync_async_equivalent 15.44s call tests/integration_tests/document_loaders/test_recursive_url_loader.py::test_sync_recursive_url_loader ============================================================================== short test summary info ============================================================================== FAILED tests/integration_tests/document_loaders/test_recursive_url_loader.py::test_sync_recursive_url_loader - AssertionError: assert 24 == 23 ================================================================ 1 failed, 5 passed, 5 warnings in 172.97s (0:02:52) ================================================================ (venv) zhanglei@LeideMacBook-Pro community % poetry run pytest tests/integration_tests/document_loaders/test_recursive_url_loader.py ================================================================================ test session starts ================================================================================ platform darwin -- Python 3.11.4, pytest-7.4.4, pluggy-1.4.0 -- /Users/zhanglei/Work/github/langchain/venv/bin/python cachedir: .pytest_cache rootdir: /Users/zhanglei/Work/github/langchain/libs/community configfile: pyproject.toml plugins: syrupy-4.6.1, asyncio-0.20.3, cov-4.1.0, vcr-1.0.2, mock-3.12.0, anyio-3.7.1, dotenv-0.5.2, requests-mock-1.11.0, socket-0.6.0 asyncio: mode=Mode.AUTO collected 6 items tests/integration_tests/document_loaders/test_recursive_url_loader.py::test_async_recursive_url_loader PASSED [ 16%] tests/integration_tests/document_loaders/test_recursive_url_loader.py::test_async_recursive_url_loader_deterministic PASSED [ 33%] tests/integration_tests/document_loaders/test_recursive_url_loader.py::test_sync_recursive_url_loader PASSED [ 50%] tests/integration_tests/document_loaders/test_recursive_url_loader.py::test_sync_async_equivalent PASSED [ 66%] tests/integration_tests/document_loaders/test_recursive_url_loader.py::test_loading_invalid_url PASSED [ 83%] tests/integration_tests/document_loaders/test_recursive_url_loader.py::test_sync_async_metadata_necessary_properties PASSED [100%] ================================================================================= warnings summary ================================================================================== tests/integration_tests/document_loaders/test_recursive_url_loader.py::test_async_recursive_url_loader tests/integration_tests/document_loaders/test_recursive_url_loader.py::test_async_recursive_url_loader_deterministic tests/integration_tests/document_loaders/test_recursive_url_loader.py::test_sync_recursive_url_loader tests/integration_tests/document_loaders/test_recursive_url_loader.py::test_sync_async_equivalent tests/integration_tests/document_loaders/test_recursive_url_loader.py::test_sync_async_metadata_necessary_properties /Users/zhanglei/.pyenv/versions/3.11.4/lib/python3.11/html/parser.py:170: XMLParsedAsHTMLWarning: It looks like you're parsing an XML document using an HTML parser. If this really is an HTML document (maybe it's XHTML?), you can ignore or filter this warning. If it's XML, you should know that using an XML parser will be more reliable. To parse this document as XML, make sure you have the lxml package installed, and pass the keyword argument `features="xml"` into the BeautifulSoup constructor. k = self.parse_starttag(i) -- Docs: https://docs.pytest.org/en/stable/how-to/capture-warnings.html ================================================================================ slowest 5 durations ================================================================================ 46.99s call tests/integration_tests/document_loaders/test_recursive_url_loader.py::test_async_recursive_url_loader_deterministic 32.43s call tests/integration_tests/document_loaders/test_recursive_url_loader.py::test_async_recursive_url_loader 31.23s call tests/integration_tests/document_loaders/test_recursive_url_loader.py::test_sync_async_equivalent 30.75s call tests/integration_tests/document_loaders/test_recursive_url_loader.py::test_sync_async_metadata_necessary_properties 15.89s call tests/integration_tests/document_loaders/test_recursive_url_loader.py::test_sync_recursive_url_loader ===================================================================== 6 passed, 5 warnings in 157.42s (0:02:37) ===================================================================== (venv) lei@LeideMacBook-Pro community % ``` **Issue:** https://github.com/langchain-ai/langchain/issues/20919 **Twitter handle:** @coolbeevip	2 months ago
ccurme	7d8d0229fa	remove placeholder error message (#20340)	2 months ago
William FH	4c437ebb9c	Use lstv2 (#20747)	2 months ago
ccurme	891ae37437	langchain: support PineconeVectorStore in self query retriever (#20905) ... `langchain_pinecone.Pinecone` is deprecated in favor of `PineconeVectorStore`, and is currently a subclass of `PineconeVectorStore`. ```python @deprecated(since="0.0.3", removal="0.2.0", alternative="PineconeVectorStore") class Pinecone(PineconeVectorStore): """Deprecated. Use PineconeVectorStore instead.""" pass ```	2 months ago
Matt	28df4750ef	community[patch]: Add initial tests for AzureSearch vector store (#17663) ... **Description:** AzureSearch vector store has no tests. This PR adds initial tests to validate the code can be imported and used. **Issue:** N/A **Dependencies:** azure-search-documents and azure-identity are added as optional dependencies for testing --------- Co-authored-by: Matt Gotteiner <[email protected]> Co-authored-by: Bagatur <baskaryan@gmail.com>	2 months ago