71 Commits (dce3c74905ce2632f614961d3462960d2ce2ad28)

Author	SHA1	Message	Date
Eugene Yurtsev	e186637921	Document Runnable Binding (#13927) ... Document runnable binding	10 months ago
Bagatur	46b3311190	RELEASE: 0.0.341 (#13926)	10 months ago
umair mehmood	b3e08f9239	improvement: fix chat prompt loading from config (#13818) ... Add loader for loading chat prompt from config file. fixed: #13667 @efriis @baskaryan	10 months ago
Nuno Campos	8a3e0c9afa	Add option to prefix config keys in configurable_alts (#13714)	10 months ago
ggeutzzang	3749af79ae	DOCS: fixed error in the docstring of RunnablePassthrough class (#13843) ... This pull request addresses an issue found in the example code within the docstring of `libs/core/langchain_core/runnables/passthrough.py` The original code snippet caused a `NameError` due to the missing import of `RunnableLambda`. The error was as follows: ``` 12 return "completion" 13 ---> 14 chain = RunnableLambda(fake_llm) | { 15 'original': RunnablePassthrough(), # Original LLM output 16 'parsed': lambda text: text[::-1] # Parsing logic NameError: name 'RunnableLambda' is not defined ``` To resolve this, I have modified the example code to include the necessary import statement for `RunnableLambda`. Additionally, I have adjusted the indentation in the code snippet to ensure consistency and readability. The modified code now successfully defines and utilizes `RunnableLambda`, ensuring that users referencing the docstring will have a functional and clear example to follow. There are no related GitHub issues for this particular change. Modified Code: ```python from langchain_core.runnables import RunnablePassthrough, RunnableParallel from langchain_core.runnables import RunnableLambda runnable = RunnableParallel( origin=RunnablePassthrough(), modified=lambda x: x+1 ) runnable.invoke(1) # {'origin': 1, 'modified': 2} def fake_llm(prompt: str) -> str: # Fake LLM for the example return "completion" chain = RunnableLambda(fake_llm) | { 'original': RunnablePassthrough(), # Original LLM output 'parsed': lambda text: text[::-1] # Parsing logic } chain.invoke('hello') # {'original': 'completion', 'parsed': 'noitelpmoc'} ``` --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	10 months ago
Bagatur	7222c42077	RELEASE: core 0.0.6 (#13853)	10 months ago
Bagatur	58f7e109ac	BUGFIX: Add import types and typevars from core (#13829)	10 months ago
Bagatur	300ff01824	RELEASE: core 0.0.5 (#13786)	10 months ago
Bagatur	72c108b003	IMPROVEMENT: filter global warnings properly (#13754)	10 months ago
William FH	163bf165ed	Add Batch Size kwarg to the llm start callback (#13483) ... So you can more easily use the token counts directly from the API endpoint for batch size of 1	10 months ago
Bagatur	2bc5bd67f7	RELEASE: core 0.0.4 (#13745)	10 months ago
Bagatur	32d087fcb8	REFACTOR: combine core documents files (#13733)	10 months ago
Bagatur	16af282429	BUGFIX: add prompt imports for backwards compat (#13702)	10 months ago
Bagatur	e327bb4ba4	IMPROVEMENT: Conditionally import core type hints (#13700)	10 months ago
Bagatur	a21e84faf7	BUGFIX: llm backwards compat imports (#13698)	10 months ago
tanujtiwari-at	5064890fcf	BUGFIX: handle tool message type when converting to string (#13626) ... **Description:** Currently, if we pass in a ToolMessage back to the chain, it crashes with error `Got unsupported message type: ` This fixes it. Tested locally --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	10 months ago
Josep Pon Farreny	143049c90f	Added partial_variables to BaseStringMessagePromptTemplate.from_template(...) (#13645) ... **Description:** BaseStringMessagePromptTemplate.from_template was passing the value of partial_variables into cls(...) via **kwargs, rather than passing it to PromptTemplate.from_template. Which resulted in those *partial_variables being* lost and becoming required *input_variables*. Co-authored-by: Josep Pon Farreny <josep.pon-farreny@siemens.com> Co-authored-by: Bagatur <baskaryan@gmail.com>	10 months ago
Erick Friis	c5ae9f832d	INFRA: Lint for imports (#13632) ... - Adds pydantic/import linting to core - Adds a check for `langchain_experimental` imports to langchain	10 months ago
Bagatur	c61e30632e	BUG: more core fixes (#13665) ... Fix some circular deps: - move PromptValue into top level module bc both PromptTemplates and OutputParsers import - move tracer context vars to `tracers.context` and import them in functions in `callbacks.manager` - add core import tests	10 months ago
Bagatur	d32e511826	REFACTOR: Refactor langchain_core (#13627) ... Changes: - remove langchain_core/schema since no clear distinction b/n schema and non-schema modules - make every module that doesn't end in -y plural - where easy have 1-2 classes per file - no more than one level of nesting in directories - only import from top level core modules in langchain	10 months ago
Harrison Chase	d82cbf5e76	Separate out langchain_core package (#13577) ... Co-authored-by: Nuno Campos <nuno@boringbits.io> Co-authored-by: Bagatur <baskaryan@gmail.com> Co-authored-by: Erick Friis <erick@langchain.dev>	10 months ago