41 Commits (a8e88e1874a7c689eb6cbdb0e1e8acd0abc2967f)

Author	SHA1	Message	Date
Harrison Chase	a8e88e1874	Harrison/logprobs (#1279) ... Co-authored-by: Prateek Shah <97124740+prateekspanning@users.noreply.github.com>	1 year ago
Zach Schillaci	159c560c95	Refactor some loops into list comprehensions (#1185)	1 year ago
Ankush Gola	caa8e4742e	Enable streaming for OpenAI LLM (#986) ... * Support a callback `on_llm_new_token` that users can implement when `OpenAI.streaming` is set to `True`	1 year ago
Oliver Klingefjord	20889205e8	Added retry for openai.error.ServiceUnavailableError (#1022) ... Imho retries should be performed for ServiceUnavailableError (which tends to happen to me quite often).	1 year ago
Ankush Gola	bc7e56e8df	Add asyncio support for LLM (OpenAI), Chain (LLMChain, LLMMathChain), and Agent (#841) ... Supporting asyncio in langchain primitives allows for users to run them concurrently and creates more seamless integration with asyncio-supported frameworks (FastAPI, etc.) Summary of changes: **LLM** * Add `agenerate` and `_agenerate` * Implement in OpenAI by leveraging `client.Completions.acreate` **Chain** * Add `arun`, `acall`, `_acall` * Implement them in `LLMChain` and `LLMMathChain` for now **Agent** * Refactor and leverage async chain and llm methods * Add ability for `Tools` to contain async coroutine * Implement async SerpaPI `arun` Create demo notebook. Open questions: * Should all the async stuff go in separate classes? I've seen both patterns (keeping the same class and having async and sync methods vs. having class separation)	1 year ago
Harrison Chase	777aaff841	fix routing to tiktoken encoder (#866)	1 year ago
Ankush Gola	933441cc52	Add retry to OpenAI llm (#849) ... add ability to retry when certain exceptions are raised by `openai.Completions.create` Test plan: ran all OpenAI integration tests.	1 year ago
Bill Kish	309d86e339	increase text-davinci-003 contextsize to 4097 (#748) ... text-davinci-003 supports a context size of 4097 tokens so return 4097 instead of 4000 in modelname_to_contextsize() for text-davinci-003 Co-authored-by: Bill Kish <bill@cogniac.co>	1 year ago
Harrison Chase	9194a8be89	add stop to stream (#729)	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
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
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
Harrison Chase	9e04c34e20	Add BaseCallbackHandler and CallbackManager (#478) ... Co-authored-by: Ankush Gola <9536492+agola11@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	3e41ab7bff	check keys before using (#475)	1 year ago
mrbean	136f759492	Mrbean/support timeout (#398) ... Add support for passing in a request timeout to the API	1 year ago
Keiji Kanazawa	543db9c2df	Add Azure OpenAI LLM (#395) ... Hi! This PR adds support for the Azure OpenAI service to LangChain. I've tried to follow the contributing guidelines. Co-authored-by: Keiji Kanazawa <{ID}+{username}@users.noreply.github.com>	1 year ago
Harrison Chase	3474f39e21	Harrison/improve cache (#368) ... make it so everything goes through generate, which removes the need for two types of caches	1 year ago
Harrison Chase	a7084ad6e4	Harrison/version 0040 (#366)	1 year ago
mrbean	50257fce59	Support Streaming Tokens from OpenAI (#364) ... https://github.com/hwchase17/langchain/issues/363 @hwchase17 how much does this make you want to cry?	1 year ago
Harrison Chase	809a9f485f	Harrison/new version (#362)	1 year ago
Harrison Chase	2dd895d98c	add openai tokenizer (#355)	1 year ago
Harrison Chase	78b31e5966	Harrison/cache (#343)	1 year ago
Harrison Chase	e26b6f9c89	fix batching (#339)	1 year ago
Harrison Chase	9bb7195085	Harrison/llm saving (#331) ... Co-authored-by: Akash Samant <70665700+asamant21@users.noreply.github.com>	1 year ago
Harrison Chase	595cc1ae1a	RFC: more complete return (#313) ... Co-authored-by: Andrew Williamson <awilliamson10@indstate.edu> Co-authored-by: awilliamson10 <aw.williamson10@gmail.com>	1 year ago
Harrison Chase	8861770bd0	expose get_num_tokens method (#327)	1 year ago
thepok	137356dbec	-1 max token description for openai (#330)	1 year ago
Harrison Chase	a7c8e37e77	Harrison/token counts (#311) ... Co-authored-by: thepok <richterthepok@yahoo.de>	1 year ago
Harrison Chase	7827f0a844	fix typing (int -> float) (#308)	1 year ago
Harrison Chase	3ca2c8d6c5	allow passing of stop params into openai (#232)	2 years ago
Shyamal H Anadkat	de4b255c1f	Switch default openai model to text-davinci-003 (#215)	2 years ago
Harrison Chase	ae9c6257fe	Harrison/arbitrary params (#186)	2 years ago
Harrison Chase	b504cd739f	Harrison/cleanup env check (#144)	2 years ago
Delip Rao	76cecf8165	A fix for Jupyter environment variable issue (#135) ... - fixes the Jupyter environment variable issues mentioned in issue #134 - fixes format/lint issues in some unrelated files (from make format/lint) 	2 years ago
Harrison Chase	db37bd089f	model laboratory (#95)	2 years ago
Cameron Whitehead	54e325be2f	Improve credential handing to allow passing in constructors (#79) ... Addresses the issue in #76 by either using the relevant environment variable if set or using a string passed in the constructor. Prefers the constructor string over the environment variable, which seemed like the natural choice to me.	2 years ago
Harrison Chase	5621ca7b07	Harrison/more documentation (#19)	2 years ago
Harrison Chase	18aeb72012	initial commit	2 years ago