langchain

Commit Graph

Author	SHA1	Message	Date
Erick Friis	3405dbbc64	dash not underscore (#12716 ) template names are auto-populating with the wrong convention (with underscores)	11 months ago
123-fake-st	8bd3ce59cd	PyPDFLoader use url in metadata source if file is a web path (#12092 ) Description: Update `langchain.document_loaders.pdf.PyPDFLoader` to store url in metadata (instead of a temporary file path) if user provides a web path to a pdf - Issue: Related to #7034; the reporter on that issue submitted a PR updating `PyMuPDFParser` for this behavior, but it has unresolved merge issues as of 20 Oct 2023 #7077 - In addition to `PyPDFLoader` and `PyMuPDFParser`, these other classes in `langchain.document_loaders.pdf` exhibit similar behavior and could benefit from an update: `PyPDFium2Loader`, `PDFMinerLoader`, `PDFMinerPDFasHTMLLoader`, `PDFPlumberLoader` (I'm happy to contribute to some/all of that, including assisting with `PyMuPDFParser`, if my work is agreeable) - The root cause is that the underlying pdf parser classes, e.g. `langchain.document_loaders.parsers.pdf.PyPDFParser`, never receive information about the url; the parsers receive a `langchain.document_loaders.blob_loaders.blob`, which contains the pdf contents and local file path, but not the url - This update passes the web path directly to the parser since it's minimally invasive and doesn't require further changes to maintain existing behavior for local files... bigger picture, I'd consider extending `blob` so that extra information like this can be communicated, but that has much bigger implications on the codebase which I think warrants maintainer input - Dependencies: None ```python # old behavior >>> from langchain.document_loaders import PyPDFLoader >>> loader = PyPDFLoader('https://arxiv.org/pdf/1706.03762.pdf') >>> docs = loader.load() >>> docs[0].metadata {'source': '/var/folders/w2/zx77z1cs01s1thx5dhshkd58h3jtrv/T/tmpfgrorsi5/tmp.pdf', 'page': 0} # new behavior >>> from langchain.document_loaders import PyPDFLoader >>> loader = PyPDFLoader('https://arxiv.org/pdf/1706.03762.pdf') >>> docs = loader.load() >>> docs[0].metadata {'source': 'https://arxiv.org/pdf/1706.03762.pdf', 'page': 0} ```	11 months ago
Dave Kwon	b1954aab13	feat: Add page metadata on PDFMinerLoader (#12277 ) - Description: #12273 's suggestion PR Like other PDFLoader, loading pdf per each page and giving page metadata. - Issue: #12273 - Twitter handle: @blue0_0hope --------- Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>	11 months ago
Duda Nogueira	7148f3e1fe	Weaviate - Fix schema existence check (#12711 ) This will allow you create the schema beforehand. The check was failing and preventing importing into existing classes. <!-- Thank you for contributing to LangChain! Replace this entire comment with: - Description: a description of the change, - Issue: the issue # it fixes (if applicable), - Dependencies: any dependencies required for this change, - Tag maintainer: for a quicker response, tag the relevant maintainer (see below), - Twitter handle: we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md If you're adding a new integration, please include: 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/extras` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. -->	11 months ago
Sayandip	8dbbcf0b6c	Adding a template for Solo Performance Prompting Agent (#12627 ) Description: This template creates an agent that transforms a single LLM into a cognitive synergist by engaging in multi-turn self-collaboration with multiple personas. Tag maintainer: @hwchase17 --------- Co-authored-by: Sayandip Sarkar <sayandip.sarkar@skypointcloud.com> Co-authored-by: Erick Friis <erick@langchain.dev>	11 months ago
Aidos Kanapyanov	ae63c186af	Mask API key for Anyscale LLM (#12406 ) Description: Add masking of API Key for Anyscale LLM when printed. Issue: #12165 Dependencies: None Tag maintainer: @eyurtsev --------- Co-authored-by: Bagatur <baskaryan@gmail.com> Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>	11 months ago
Predrag Gruevski	5ae51a8a85	Fix typo highlighted by `ruff` autoformatter. (#12691 ) H/t @MichaReiser for spotting it: https://github.com/langchain-ai/langchain/pull/12585/files#r1378253045	11 months ago
Predrag Gruevski	724b92231d	Remove `black` caching config from CI lint workflow. (#12594 ) To merge after #12585 is merged.	11 months ago
Predrag Gruevski	0ea837404a	Only publish to test PyPI from the `_test_release.yml` workflow. (#12668 ) PyPI trusted publishing wants to know which workflow is expected to do the publish. We always want to publish from the same workflow, so we're making `_test_release.yml` the only workflow that publishes to Test PyPI.	11 months ago
Predrag Gruevski	321cd44f13	Use separate jobs for building and publishing test releases. (#12671 ) This follows the principle of least privilege. Our `poetry build` step doesn't need, and shouldn't get, access to our GitHub OIDC capability. This is the same structure as I used in the already-merged PR for refactoring the regular PyPI release workflow: #12578.	11 months ago
Erick Friis	44c8b159b9	properly increment version in cli (#12685 ) Went from 0.0.9 -> 0.0.11 without releasing. Back to 10, then release.	11 months ago
Erick Friis	b825dddf95	fix elastic rag template in playground (#12682 ) - a few instructions in the readme (load_documents -> ingest.py) - added docker run command for local elastic - adds input type definition to render playground properly	11 months ago
Lance Martin	f0eba1ac63	Add RAG input types (#12684 ) Co-authored-by: Erick Friis <erick@langchain.dev>	11 months ago
Erick Friis	392cfbee24	link to templates (#12680 )	11 months ago
Leonid Ganeline	ddcec005bc	fix for `YahooFinanceNewsTool` (#12665 ) Added YahooFinanceNewsTool to the __init__.py It was missed here.	11 months ago
Predrag Gruevski	09711ad5a1	Both lint and format `templates` with ruff v0.1.3. (#12676 ) - Both lint and format code in `templates`. - Upgrade to ruff v0.1.3.	11 months ago
Predrag Gruevski	01a3c9b94e	Use an in-project virtualenv in the CLI package. (#12678 ) Keeping it in sync with how our other packages are configured.	11 months ago
Predrag Gruevski	f7f35a9102	Use black to lint notebooks and docs for now. (#12679 ) Due to #12677 having lots of errors for the time being.	11 months ago
Jacob Lee	bd668fcea1	Adds version CLI command (#12619 ) Will be automatically bumped with `poetry version patch`. @efriis @hwchase17 --------- Co-authored-by: Erick Friis <erick@langchain.dev>	11 months ago
Frank	bf5805bb32	Add quip loader (#12259 ) - Description: implement [quip](https://quip.com) loader - Issue: https://github.com/langchain-ai/langchain/issues/10352 - Dependencies: No - pass make format, make lint, make test --------- Co-authored-by: Hao Fan <h_fan@apple.com> Co-authored-by: Bagatur <baskaryan@gmail.com>	11 months ago
Roman Vasilyev	c9a6940d58	PGVector fix (#12592 ) latest release broken, this fixes it --------- Co-authored-by: Roman Vasilyev <rvasilyev@mozilla.com> Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>	11 months ago
Lance Martin	9e17d1a225	Update Vertex template (#12644 ) Co-authored-by: Erick Friis <erick@langchain.dev>	11 months ago
Predrag Gruevski	aa3f4a9bc8	Remove the CLI package's pydantic compatibility tests. (#12675 ) They aren't necessary, since the CLI package doesn't have a direct dependency on pydantic.	11 months ago
Predrag Gruevski	e8b99364b3	Use `ruff` for both linting and formatting in `langchain-cli`. (#12672 ) Prior to this PR, `ruff` was used only for linting and not for formatting, despite the names of the commands. This PR makes it be used for both linting code and autoformatting it.	11 months ago
Harrison Chase	9a10b2b047	fix plate chain (#12673 )	11 months ago
Margaret Qian	acfc485808	Update MosaicML Embedding Input Key (#12657 ) This input key was missed in the last update PR: https://github.com/langchain-ai/langchain/pull/7391 The input/output formats are intended to be like this: ``` {"inputs": [<prompt>]} {"outputs": [<output_text>]} ```	11 months ago
Erika Cardenas	d26ac5f999	Update README for Hybrid Search Weaviate (#12661 ) - Description: Updated the README for Hybrid Search Weaviate	11 months ago
Predrag Gruevski	c871cc5055	Remove `print()` statements which seemed leftover from debugging. (#12648 ) Added in #12159 presumably during debugging. Right now they cause a bit of visual noise.	11 months ago
Erick Friis	2a7e0a27cb	update lc version (#12655 ) also updated py version in `csv-agent` and `rag-codellama-fireworks` because they have stricter python requirements	11 months ago
Predrag Gruevski	360cff81a3	Overwrite existing distributions when uploading to test PyPI. (#12658 )	11 months ago
Lance Martin	da94c750c5	Add RAG template for Timescale Vector (#12651 ) <!-- Thank you for contributing to LangChain! Replace this entire comment with: - Description: a description of the change, - Issue: the issue # it fixes (if applicable), - Dependencies: any dependencies required for this change, - Tag maintainer: for a quicker response, tag the relevant maintainer (see below), - Twitter handle: we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md If you're adding a new integration, please include: 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/extras` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. --> --------- Co-authored-by: Matvey Arye <mat@timescale.com>	11 months ago
Noam Gat	14e8c74736	LM Format Enforcer Integration + Sample Notebook (#12625 ) ## Description This PR adds support for [lm-format-enforcer](https://github.com/noamgat/lm-format-enforcer) to LangChain. ![image](https://raw.githubusercontent.com/noamgat/lm-format-enforcer/main/docs/Intro.webp) The library is similar to jsonformer / RELLM which are supported in Langchain, but has several advantages such as - Batching and Beam search support - More complete JSON Schema support - LLM has control over whitespace, improving quality - Better runtime performance due to only calling the LLM's generate() function once per generate() call. The integration is loosely based on the jsonformer integration in terms of project structure. ## Dependencies No compile-time dependency was added, but if `lm-format-enforcer` is not installed, a runtime error will occur if it is trying to be used. ## Tests Due to the integration modifying the internal parameters of the underlying huggingface transformer LLM, it is not possible to test without building a real LM, which requires internet access. So, similar to the jsonformer and RELLM integrations, the testing is via the notebook. ## Twitter Handle [@noamgat](https://twitter.com/noamgat) Looking forward to hearing feedback! --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	11 months ago
Stefano Lottini	a4e4b5a86f	Relax python version and remove need for explicit setup step (#12637 ) This PR addresses what seems like a unnecessary Python version restriction in the pyroject.toml specs within both Cassandra (/Astra DB) templates. With "^3.11" I got some version incompatibilities with the latest "langchain add [...]" commands, so these are now relaxed in line with the other templates I could inspect. Incidentally, in the "entomology" template, the need for an explicit "setup" step for the user to carry on has been removed, replaced by a check-and-execute-if-necessary instruction on app startup. Thank you for your attention!	11 months ago
Predrag Gruevski	5308b836c7	Upgrade to `actions/checkout@v4` in the docs lint job. (#12581 )	11 months ago
Predrag Gruevski	94f018f1ba	Support release-testing packages with dashes in their names. (#12654 )	11 months ago
Erick Friis	912ace18e9	fix template py verisons (#12650 )	11 months ago
Brian McBrayer	b74468f399	Fix small typo on Founcational -> Router notebook (#12634 ) - Description: Fix small typo on Founcational -> Router notebook	11 months ago
Predrag Gruevski	72fa5a463d	Show ruff output inline in GitHub PRs. (#12647 )	11 months ago
William FH	17c2e3b87e	Rename Template (#12649 ) To chatbot feedback. Update import	11 months ago
Erick Friis	7f6e751a3d	template updates (#12646 )	11 months ago
Leonid Kuligin	a53cac4508	added template to use Vertex Vector Search for q&a (#12622 ) added template to use Vertex Vector Search for q&a	11 months ago
Lance Martin	944cb552bb	Minor updates to READMEs (#12642 )	11 months ago
William FH	88f0f1e73b	Conversational Feedback (#12590 ) Context in the README. Show how score chat responses based on a followup from the user and then log that as feedback in LangSmith	11 months ago
Predrag Gruevski	f94e24dfd7	Install and use `ruff format` instead of black for code formatting. (#12585 ) Best to review one commit at a time, since two of the commits are 100% autogenerated changes from running `ruff format`: - Install and use `ruff format` instead of black for code formatting. - Output of `ruff format .` in the `langchain` package. - Use `ruff format` in experimental package. - Format changes in experimental package by `ruff format`. - Manual formatting fixes to make `ruff .` pass.	11 months ago
William FH	bfd719f9d8	bind_functions convenience method (#12518 ) I always take 20-30 seconds to re-discover where the `convert_to_openai_function` wrapper lives in our codebase. Chat langchain [has no clue](https://smith.langchain.com/public/3989d687-18c7-4108-958e-96e88803da86/r) what to do either. There's the older `create_openai_fn_chain` , but we haven't been recommending it in LCEL. The example we show in the [cookbook](https://python.langchain.com/docs/expression_language/how_to/binding#attaching-openai-functions) is really verbose. General function calling should be as simple as possible to do, so this seems a bit more ergonomic to me (feel free to disagree). Another option would be to directly coerce directly in the class's init (or when calling invoke), if provided. I'm not 100% set against that. That approach may be too easy but not simple. This PR feels like a decent compromise between simple and easy. ``` from enum import Enum from typing import Optional from pydantic import BaseModel, Field class Category(str, Enum): """The category of the issue.""" bug = "bug" nit = "nit" improvement = "improvement" other = "other" class IssueClassification(BaseModel): """Classify an issue.""" category: Category other_description: Optional[str] = Field( description="If classified as 'other', the suggested other category" ) from langchain.chat_models import ChatOpenAI llm = ChatOpenAI().bind_functions([IssueClassification]) llm.invoke("This PR adds a convenience wrapper to the bind argument") # AIMessage(content='', additional_kwargs={'function_call': {'name': 'IssueClassification', 'arguments': '{\n "category": "improvement"\n}'}}) ```	11 months ago
Nuno Campos	3143324984	Improve Runnable type inference for input_schemas (#12630 ) - Prefer lambda type annotations over inferred dict schema - For sequences that start with RunnableAssign infer seq input type as "input type of 2nd item in sequence - output type of runnable assign"	11 months ago
Nuno Campos	2f563cee20	Add Runnable.with_listeners() (#12549 ) - This binds start/end/error listeners to a runnable, which will be called with the Run object	11 months ago
Bagatur	bcc62d63be	bump 327 (#12623 )	11 months ago
Erick Friis	a1fae1fddd	Readme rewrite (#12615 ) Co-authored-by: Lance Martin <lance@langchain.dev> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	11 months ago
Ankur Singh	00766c9f31	Improves the description of the installation command (#12354 ) - Description: Before: ` To install modules needed for the common LLM providers, run: ` After: ` To install modules needed for the common LLM providers, run the following command. Please bear in mind that this command is exclusively compatible with the `bash` shell: ` > This is required for the user so that the user will know if this command is compatible with `zsh` or not. --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	11 months ago

1 2 3 4 5 ...

5642 Commits (3405dbbc6446ffccba4392ee6773ea6af496abda) All Branches Search

5642 Commits (3405dbbc6446ffccba4392ee6773ea6af496abda)

All Branches