langchain

Commit Graph

Author	SHA1	Message	Date
blob42	897cad58dc	[agent_executor] convenience func: lookup tool by name	1 year ago
Harrison Chase	40e9488055	fix async in agent (#1723 )	1 year ago
Harrison Chase	7cf46b3fee	Harrison/convo agent (#1642 )	1 year ago
Harrison Chase	aed9f9febe	Harrison/return intermediate (#1633 ) Co-authored-by: Mario Kostelac <mario@intercom.io>	1 year ago
Ryan Dao	a950287206	Strip trailing whitespaces in agent's stop sequences (#1566 ) Fixes #1489	1 year ago
Ankush Gola	82baecc892	Add a SQL agent for interacting with SQL Databases and JSON Agent for interacting with large JSON blobs (#1150 ) This PR adds * `ZeroShotAgent.as_sql_agent`, which returns an agent for interacting with a sql database. This builds off of `SQLDatabaseChain`. The main advantages are 1) answering general questions about the db, 2) access to a tool for double checking queries, and 3) recovering from errors * `ZeroShotAgent.as_json_agent` which returns an agent for interacting with json blobs. * Several examples in notebooks --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	1 year ago
kurehajime	6c629b54e6	Fixed arguments passed to InvalidTool.run(). (#1340 ) [InvalidTool.run()](`72ef69d1ba/langchain/agents/tools.py (L43)`) returns "{arg}is not a valid tool, try another one.". However, no function name is actually given in the argument. This causes LLM to be stuck in a loop, unable to find the right tool. This may resolve these Issues. https://github.com/hwchase17/langchain/issues/998 https://github.com/hwchase17/langchain/issues/702	1 year ago
Harrison Chase	b7708bbec6	rfc: callback changes (#1165 ) conceptually, no reason a tool should know what an "agent action" is unless any objections, can change in all callback handlers	1 year ago
Ankush Gola	7b5e160d28	Make Tools own model, add ToolKit Concept (#1095 ) Follow-up of @hinthornw's PR: - Migrate the Tool abstraction to a separate file (`BaseTool`). - `Tool` implementation of `BaseTool` takes in function and coroutine to more easily maintain backwards compatibility - Add a Toolkit abstraction that can own the generation of tools around a shared concept or state --------- Co-authored-by: William FH <13333726+hinthornw@users.noreply.github.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com> Co-authored-by: Francisco Ingham <fpingham@gmail.com> Co-authored-by: Dhruv Anand <105786647+dhruv-anand-aintech@users.noreply.github.com> Co-authored-by: cragwolfe <cragcw@gmail.com> Co-authored-by: Anton Troynikov <atroyn@users.noreply.github.com> Co-authored-by: Oliver Klingefjord <oliver@klingefjord.com> Co-authored-by: William Fu-Hinthorn <whinthorn@Williams-MBP-3.attlocal.net> Co-authored-by: Bruno Bornsztein <bruno.bornsztein@gmail.com>	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
Harrison Chase	0f0e69adce	agent refactors (#997 )	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	7198a1cb22	Harrison/refactor agent (#781 ) Co-authored-by: Amos Ng <me@amos.ng>	1 year ago
Harrison Chase	a5d003f0c9	update notebook and make backwards compatible (#772 )	1 year ago
Harrison Chase	1b89a438cf	(wip) Harrison/serialize agents (#725 )	1 year ago
Francisco Ingham	374e510f94	Upper bound on number of iterations (#754 ) Some custom agents might continue to iterate until they find the correct answer, getting stuck on loops that generate request after request and are really expensive for the end user. Putting an upper bound for the number of iterations by default controls this and can be explicitly tweaked by the user if necessary. Co-authored-by: Francisco Ingham <>	1 year ago
Ankush Gola	57609845df	add tracing support to langchain (#741 ) * add implementations of `BaseCallbackHandler` to support tracing: `SharedTracer` which is thread-safe and `Tracer` which is not and is meant to be used locally. * Tracers persist runs to locally running `langchain-server` Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	1 year ago
Harrison Chase	cbc146720b	verbose flag (#683 )	1 year ago
Harrison Chase	74932f2516	RFC: conversational agent (#464 ) Co-authored-by: Bruno Bornsztein <bruno.bornsztein@gmail.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	5aefc2b7ce	add handling on error (#541 )	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
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	d0f194de73	add logic for agent stopping (#420 )	1 year ago
Harrison Chase	cf98f219f9	Harrison/tools exp (#372 )	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	e02d6b2288	beta: logger (#307 )	1 year ago
John McDonnell	68666d6a22	Gracefully degrade when model asks for nonexistent tool (#268 ) Not yet tested, but very simple change, assumption is that we're cool with just producing a generic output when tool is not found	2 years ago
Xupeng (Tony) Tong	bb4bf9d6d0	chore: minor clean up / formatting (#233 ) to get familiarize with the project	2 years ago
Harrison Chase	0568998166	Harrison/fix react stateful (#219 ) fix issue with react being stateful	2 years ago
Harrison Chase	6eab5254e5	add docs for custom agents (#196 )	2 years ago
Harrison Chase	5d887970f6	change to agent (#173 )	2 years ago
Harrison Chase	d3a7429f61	(WIP) agents (#171 )	2 years ago

33 Commits (897cad58dc09374667f95b31383f7dd18d8eddfe)