421 Commits (7f76a1189c1e2628c9d442519bf315eab15fbb40)

 

All Branches   

Search

Author	SHA1	Message	Date
Harrison Chase	1511606799	Harrison/fix splitting (#563) ... fix issue where text splitting could possibly create empty docs	1 year ago
Harrison Chase	1192cc0767	smart text splitter (#530) ... smart text splitter that iteratively tries different separators until it works!	1 year ago
Harrison Chase	8dfad874a2	map rerank chain (#516) ... add a chain that applies a prompt to all inputs and then returns not only an answer but scores it add examples for question answering and question answering with sources	1 year ago
Nicolas	948eee9fe1	Docs: side menu to match the order (llms) (#557) ... Small quick fix: Suggest making the order of the menu the same as it is written on the page (Getting Started -> Key Concepts). Before the menu order was not the same as it was on the page. Not sure if this is the only place the menu is affected. Mismatch is found here: https://langchain.readthedocs.io/en/latest/modules/llms.html	1 year ago
Harrison Chase	823a44ef80	bump to 0058 (#556)	1 year ago
Benjamin	42d5d988fa	add openai logit bias (#553) ... Add [`logit_bias`](https://beta.openai.com/docs/api-reference/completions/create#completions/create-logit_bias) params to OpenAI See [here](https://beta.openai.com/tokenizer) for the tokenizer. NB: I see that others (like Cohere) have the same parameter, but since I don't have an access to it, I don't want to make a mistake. --- Just to make sure the default "{}" works for openai: ``` from langchain.llms import OpenAI OPENAI_API_KEY="XXX" llm = OpenAI(openai_api_key=OPENAI_API_KEY) llm.generate('Write "test":') llm = OpenAI(openai_api_key=OPENAI_API_KEY, logit_bias={'9288': -100, '1332': -100, '14402': -100, '6208': -100}) llm.generate('Write "test":') ```	1 year ago
Harrison Chase	9833fcfe32	fix caching (#555)	1 year ago
Harrison Chase	74932f2516	RFC: conversational agent (#464) ... Co-authored-by: Bruno Bornsztein <bruno.bornsztein@gmail.com>	1 year ago
Harrison Chase	330a5b42d4	fix map reduce chain (#550)	1 year ago
Diwank Singh Tomer	ba0cbb4a41	Add finish reason to Generation for usage downstream (#526) ... Add `finish_reason` to `Generation` as well as extend `BaseOpenAI._generate` to include it in the output. This can be useful for usage in downstream tasks when we need to filter for only generations that finished because of `"stop"` for example. Maybe we should add this to `LLMChain` as well? For more details, see https://beta.openai.com/docs/guides/completion/best-practices Signed-off-by: Diwank Singh Tomer <diwank.singh@gmail.com>	1 year ago
Harrison Chase	e64ed7b975	Harrison/tools priority (#554) ... Co-authored-by: Yong723 <50616781+Yongtae723@users.noreply.github.com>	1 year ago
Harrison Chase	4974f49bb7	add return_direct flag to tool (#537) ... adds a return_direct flag to tools, which just returns the tool output as the final output	1 year ago
Harrison Chase	1f248c47f3	bump version to 0.0.57 (#548)	1 year ago
Harrison Chase	0c2f7d8da1	changes to qa chain (#543)	1 year ago
Hunter Gerlach	5b4c972fc5	Add linkcheck badge to signify when/if links are failing (#546) ... Detect whether or not most recent GitHub Action running linkcheck was successful.	1 year ago
Harrison Chase	9753bccc71	Feature: linkcheck-action (#534) (#542) ... - Add support for local build and linkchecking of docs - Add GitHub Action to automatically check links before prior to publication - Minor reformat of Contributing readme - Fix existing broken links Co-authored-by: Hunter Gerlach <hunter@huntergerlach.com> Co-authored-by: Hunter Gerlach <HunterGerlach@users.noreply.github.com> Co-authored-by: Hunter Gerlach <hunter@huntergerlach.com>	1 year ago
Harrison Chase	5aefc2b7ce	add handling on error (#541)	1 year ago
Harrison Chase	1631981f84	Harrison/fix and test caching (#538)	1 year ago
Harrison Chase	73f7ebd9d1	Harrison/sqlalchemy cache store (#536) ... Co-authored-by: Jason Gill <jasongill@gmail.com>	1 year ago
Sam Ching	870cccb877	Add info to Contributors.md to avoid Conda/Pyenv dependency conflicts (#540) ... As discussed in the [Discord](https://discord.com/channels/1038097195422978059/1038097349660135474/1060194710485995521), adding the following instructions to help future contributors avoid dependency conflicts if they use Conda / Pyenv on their system.	1 year ago
Yongtae723	f48ab642be	replace forbid into ignore (#539) ... this is the second PR of #519. in #519 I suggested deleting Extra.forbid. I was very confused but I replaced Extra.forbid to Extra.ignore, which is the default of pydantic. Since the [BaseLLM](4b7b8229de/langchain/llms/base.py (L20)) from which it is inherited is set in Extra.forbid, I wanted to avoid having the Extra.forbid settings inherited by simply deleting it.	1 year ago
Yongtae723	4b7b8229de	add logger (#529) ... As talking #519, I made 2 PRs. this is the first PR for adding a logger. I am concerned about the following two points and would appreciate your opinion. 1. Since the logger is not formatted, the statement itself is output like a print statement, and I thought it was difficult to understand that it was a warning, so I put WARNING! at the beginning of the warning statement. After the logger formatting is done properly, the word WARNING can be repeated. 2. Statement `Please confirm that {field_name} is what you intended.` can be replaced like `If {field_name} is intended parameters, enter it to model_kwargs` thank you! Yongtae	1 year ago
Rubens Mau	020e73017b	Updated embeddings.ipynb (#531) ... updated embeddings.ipynb	1 year ago
Ikko Eltociear Ashimine	ca9aaac36e	Fix typo in key_concepts.md (#535) ... therefor -> therefore	1 year ago
Harrison Chase	680f267179	bump version to 0056 (#533)	1 year ago
Harrison Chase	9e04c34e20	Add BaseCallbackHandler and CallbackManager (#478) ... Co-authored-by: Ankush Gola <9536492+agola11@users.noreply.github.com>	1 year ago
Nuno Campos	6d78be0c83	Add link to gihub repo in header of new docs (#524)	1 year ago
Harrison Chase	447683de6f	bump version to 0.0.55 (#521)	1 year ago
Harrison Chase	0db05b6725	Harrison/add human prefix (#520) ... Co-authored-by: Andrew Huang <jhuang16888@gmail.com>	1 year ago
Harrison Chase	03f185bcd5	more robust handling for max iterations (#514) ... add a `generate` method which makes one final forward pass through the llm	1 year ago
Harrison Chase	40326c698c	unify argument name (#513) ... unify names in map reduce and refine chains to just be return_intermediate_steps also unify the return key	1 year ago
lewtun	12108104c9	Add links to Hugging Face Hub docs (#518) ... This PR adds some tweaks to the Hugging Face docs, mostly with links to the Hub + relevant docs.	1 year ago
Harrison Chase	3efec55f93	update lobby link (#517)	1 year ago
Harrison Chase	8f6c08863a	bump version to 0.0.54 (#512)	1 year ago
Hunter Gerlach	7253fada0d	Fix/broken getting started link (#511) ... I noticed (after publication) that the getting_started link on the main page was borked. This should fix it. Co-authored-by: Hunter Gerlach <hunter@huntergerlach.com>	1 year ago
Harrison Chase	985496f4be	Docs refactor (#480) ... Big docs refactor! Motivation is to make it easier for people to find resources they are looking for. To accomplish this, there are now three main sections: - Getting Started: steps for getting started, walking through most core functionality - Modules: these are different modules of functionality that langchain provides. Each part here has a "getting started", "how to", "key concepts" and "reference" section (except in a few select cases where it didnt easily fit). - Use Cases: this is to separate use cases (like summarization, question answering, evaluation, etc) from the modules, and provide a different entry point to the code base. There is also a full reference section, as well as extra resources (glossary, gallery, etc) Co-authored-by: Shreya Rajpal <ShreyaR@users.noreply.github.com>	1 year ago
Keiji Kanazawa	c5f0af9398	Minor docstring update (#507) ... Update `model=` to `model_name=`. No need to credit me for this 😄	1 year ago
Harrison Chase	d95b39d37f	version 0.0.53 (#497)	1 year ago
Harrison Chase	0072686aab	Harrison/new search engine (#477) ... Co-authored-by: Nicolas <nicolascamara29@gmail.com>	1 year ago
Harrison Chase	3e41ab7bff	check keys before using (#475)	1 year ago
Shuchang Zhou	12aa43469f	Update prompt_management.ipynb (#484)	1 year ago
Harrison Chase	0f1df0dc2c	bump to version 0.0.52 (#470)	1 year ago
Parth Chadha	e88e66f982	Pass verbose argument to LLMChains when using *DocumentsChain (#458) ... When using chains such as Summarization chain (`load_summarize_chain`), the verbose flag wasn't propagated to the `LLMChain`.	1 year ago
Harrison Chase	d0f194de73	add logic for agent stopping (#420)	1 year ago
Harrison Chase	c65efd2986	fix llm math prompt (#466) ... basically, it didnt realize that the question was over after the input and would some times hallucinate more input	1 year ago
Harrison Chase	95157d0aad	Add schema property to sql database utility class (#448) (#462) ... Co-authored-by: Harrison Chase <hw.chase.17@gmail.com> Signed-off-by: Diwank Singh Tomer <diwank.singh@gmail.com> Co-authored-by: Nuno Campos <nuno@boringbits.io> Co-authored-by: Diwank Singh Tomer <diwank.singh@gmail.com>	1 year ago
Nuno Campos	451665cfdf	Add watch mode for test runner (#453)	1 year ago
Harrison Chase	2b84e5cda3	Harrison/fix memory and serp (#457) ... Co-authored-by: Bruno Bornsztein <bruno.bornsztein@gmail.com>	1 year ago
Harrison Chase	d98607408b	Harrison/v0050 (#452)	1 year ago
Harrison Chase	55007e71be	add output key for memory (#443) ... this allows chains that return multiple values to use memory	1 year ago