479 Commits (4d32441b869c0ddab99cd7082ae074922e3c6fe0)

 

All Branches   

Search

Author	SHA1	Message	Date
Harrison Chase	4d32441b86	bump version to 0076 (#847)	1 year ago
Harrison Chase	23d5f64bda	Harrison/ngram example (#846) ... Co-authored-by: Sean Spriggens <ssprigge@syr.edu>	1 year ago
Harrison Chase	0de55048b7	return code for pal (#844)	1 year ago
Harrison Chase	d564308e0f	rfc: instruct embeddings (#811) ... Co-authored-by: seanaedmiston <seane999@gmail.com>	1 year ago
Nick Furlotte	576609e665	Update PAL to allow passing local and global context to PythonREPL (#774) ... Passing additional variables to the python environment can be useful for example if you want to generate code to analyze a dataset. I also added a tracker for the executed code - `code_history`.	1 year ago
Harrison Chase	3f952eb597	add from string method (#820)	1 year ago
Ikko Eltociear Ashimine	ba26a879e0	Fix typo in crawler.py (#842) ... seperator -> separator	1 year ago
Eli Mernit	bfabd1d5c0	Added new deployment template (#835) ... This PR introduces a new template for deploying LangChain apps as web endpoints. It includes template code, and links to a detailed code-walkthrough.	1 year ago
Jonas Ehrenstein	f3508228df	Minor fix for google search util: it's uncertain if "snippet" in results exists (#830) ... The results from Google search may not always contain a "snippet". Example: `{'kind': 'customsearch#result', 'title': 'FEMA Flood Map', 'htmlTitle': 'FEMA Flood Map', 'link': 'https://msc.fema.gov/portal/home', 'displayLink': 'msc.fema.gov', 'formattedUrl': 'https://msc.fema.gov/portal/home', 'htmlFormattedUrl': 'https://<b>msc</b>.fema.gov/portal/home'}` This will cause a KeyError at line 99 `snippets.append(result["snippet"])`.	1 year ago
Zach Schillaci	b4eb043b81	Minor fix to SQLDatabaseChain doc (#826)	1 year ago
Istora Mandiri	06438794e1	Fix typo in textsplitter docs (#825)	1 year ago
Raza Habib	9f8e05ffd4	Update __init__.py (#827) ... Remove duplicate APIChain	1 year ago
Harrison Chase	b0d560be56	add to gallery (#824)	1 year ago
Johanna Appel	ebea40ce86	Add 'truncate' parameter for CohereEmbeddings (#798) ... Currently, the 'truncate' parameter of the cohere API is not supported. This means that by default, if trying to generate and embedding that is too big, the call will just fail with an error (which is frustrating if using this embedding source e.g. with GPT-Index, because it's hard to handle it properly when generating a lot of embeddings). With the parameter, one can decide to either truncate the START or END of the text to fit the max token length and still generate an embedding without throwing the error. In this PR, I added this parameter to the class. _Arguably, there should be a better way to handle this error, e.g. by optionally calling a function or so that gets triggered when the token limit is reached and can split the document or some such. Especially in the use case with GPT-Index, its often hard to estimate the token counts for each document and I'd rather sort out the troublemakers or simply split them than interrupting the whole execution. Thoughts?_ --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	1 year ago
Harrison Chase	b9045f7e0d	bump version to 0075 (#819)	1 year ago
Harrison Chase	7b4882a2f4	Harrison/tf embeddings (#817) ... Co-authored-by: Ryohei Kuroki <10434946+yakigac@users.noreply.github.com>	1 year ago
Harrison Chase	5d4b6e4d4e	conversational agent fix (#818)	1 year ago
Harrison Chase	94ae126747	return sql intermediate steps (#792)	1 year ago
bair82	ae5695ad32	Update cohere.py (#795) ... When stop tokens are set in Cohere LLM constructor, they are currently not stripped from the response, and they should be stripped	1 year ago
Johanna Appel	cacf4091c0	Fix documentation for 'model' parameter in CohereEmbeddings (#797) ... Currently, the class parameter 'model_name' of the CohereEmbeddings class is not supported, but 'model' is. The class documentation is inconsistent with this, though, so I propose to either fix the documentation (this PR right now) or fix the parameter. It will create the following error: ``` ValidationError: 1 validation error for CohereEmbeddings model_name extra fields not permitted (type=value_error.extra) ```	1 year ago
Jason Liu	54f9e4287f	Pass kwargs from initialize_agent into agent classmethod (#799) ... # Problem I noticed that in order to change the prefix of the prompt in the `zero-shot-react-description` agent we had to dig around to subset strings deep into the agent's attributes. It requires the user to inspect a long chain of attributes and classes. `initialize_agent -> AgentExecutor -> Agent -> LLMChain -> Prompt from Agent.create_prompt` ``` python agent = initialize_agent( tools=tools, llm=fake_llm, agent="zero-shot-react-description" ) prompt_str = agent.agent.llm_chain.prompt.template new_prompt_str = change_prefix(prompt_str) agent.agent.llm_chain.prompt.template = new_prompt_str ``` # Implemented Solution `initialize_agent` accepts `**kwargs` but passes it to `AgentExecutor` but not `ZeroShotAgent`, by simply giving the kwargs to the agent class methods we can support changing the prefix and suffix for one agent while allowing future agents to take advantage of `initialize_agent`. ``` agent = initialize_agent( tools=tools, llm=fake_llm, agent="zero-shot-react-description", agent_kwargs={"prefix": prefix, "suffix": suffix} ) ``` To be fair, this was before finding docs around custom agents here: https://langchain.readthedocs.io/en/latest/modules/agents/examples/custom_agent.html?highlight=custom%20#custom-llmchain but i find that my use case just needed to change the prefix a little. # Changes * Pass kwargs to Agent class method * Added a test to check suffix and prefix --------- Co-authored-by: Jason Liu <jason@jxnl.coA>	1 year ago
Roger Zurawicki	c331009440	docs: Update langchain link to PyPI (#800) ... Simple one-line fix CONTRIBUTING used a link that pointed to the `ruff` project.	1 year ago
Roy Williams	6086292252	Centralize logic for loading from LangChainHub, add ability to pin dependencies (#805) ... It's generally considered to be a good practice to pin dependencies to prevent surprise breakages when a new version of a dependency is released. This commit adds the ability to pin dependencies when loading from LangChainHub. Centralizing this logic and using urllib fixes an issue identified by some windows users highlighted in this video - https://youtu.be/aJ6IQUh8MLQ?t=537	1 year ago
Harrison Chase	b3916f74a7	enable mmr search (#807)	1 year ago
Harrison Chase	f46f1d28af	expose memory key name (#808)	1 year ago
Harrison Chase	7728a848d0	Harrison/tracing docs (#806) ... Co-authored-by: Ankush Gola <9536492+agola11@users.noreply.github.com>	1 year ago
Harrison Chase	f3da4dc6ba	Harrison/tracing docs (#804) ... Co-authored-by: Ankush Gola <9536492+agola11@users.noreply.github.com>	1 year ago
Harrison Chase	ae1b589f60	Harrison/add link for support (#794)	1 year ago
Harrison Chase	6a20f07f0d	add link for support (#793)	1 year ago
Harrison Chase	fb2d7afe71	bump version to 0074 (#791)	1 year ago
Harrison Chase	1ad7973cc6	Harrison/tool decorator (#790) ... Co-authored-by: Jason Liu <jxnl@users.noreply.github.com> Co-authored-by: Jason Liu <jason@jxnl.coA>	1 year ago
Harrison Chase	5f73d06502	Harrison/fix caching bug (#788) ... Co-authored-by: thepok <richterthepok@yahoo.de>	1 year ago
Harrison Chase	248c297f1b	Sample row in table info for SQLDatabase (#769) (#782) ... The agents usually benefit from understanding what the data looks like to be able to filter effectively. Sending just one row in the table info allows the agent to understand the data before querying and get better results. --------- Co-authored-by: Francisco Ingham <> --------- Co-authored-by: Francisco Ingham <fpingham@gmail.com>	1 year ago
Francisco Ingham	213c2e33e5	Sql prompt improvement (#787) ... Co-authored-by: Francisco Ingham <>	1 year ago
Harrison Chase	2e0219cac0	fixing bash util (#779)	1 year ago
Harrison Chase	966611bbfa	add model kwargs to handle stop token from cohere (#773)	1 year ago
Harrison Chase	7198a1cb22	Harrison/refactor agent (#781) ... Co-authored-by: Amos Ng <me@amos.ng>	1 year ago
Harrison Chase	5bb2952860	Harrison/hf pipeline (#780) ... Co-authored-by: Parth Chadha <parth29@gmail.com>	1 year ago
Harrison Chase	c658f0aed3	Harrison/add to search (#778) ... Co-authored-by: Enrico Shippole <enricoship@gmail.com>	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
Amos Ng	6ad360bdef	Suggestions for better debugging (#765) ... Please feel free to disregard any changes you disagree with	1 year ago
Albert Ziegler	5198d6f541	Add missing verb (#768) ... Mini drive-by PR: I came across this sentence in a stack trace for an error I had, and it confused me because the verb I missing. So I added the verb.	1 year ago
Harrison Chase	a5d003f0c9	update notebook and make backwards compatible (#772)	1 year ago
Harrison Chase	924b7ecf89	pass kwargs and bump (#770)	1 year ago
Harrison Chase	fc19d14a65	bump version to 0072 (#767)	1 year ago
Harrison Chase	b9ad214801	add docs for loading from hub (#763)	1 year ago
Samantha Whitmore	be7de427ca	Serialize all the chains! (#761) ... Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	1 year ago
Harrison Chase	e2a7fed890	Harrison/serialize from llm and tools (#760)	1 year ago
Harrison Chase	12dc7f26cc	load agents from hub (#759)	1 year ago
Harrison Chase	7129f23511	output parser serialization (#758)	1 year ago