langchain

Commit Graph

Author	SHA1	Message	Date
Bagatur	46446a100d	core[patch]: deprecate v1 tracer (#15608 )	6 months ago
Bagatur	96b47e18e0	core[patch]: Release 0.1.7 (#15610 )	6 months ago
Erick Friis	ebc75c5ca7	openai[minor]: implement langchain-openai package (#15503 ) Todo - [x] copy over integration tests - [x] update docs with new instructions in #15513 - [x] add linear ticket to bump core -> community, community->langchain, and core->openai deps - [ ] (optional): add `pip install langchain-openai` command to each notebook using it - [x] Update docstrings to not need `openai` install - [x] Add serialization - [x] deprecate old models Contributor steps: - [x] Add secret names to manual integrations workflow in .github/workflows/_integration_test.yml - [x] Add secrets to release workflow (for pre-release testing) in .github/workflows/_release.yml Maintainer steps (Contributors should not do these): - [x] set up pypi and test pypi projects - [x] add credential secrets to Github Actions - [ ] add package to conda-forge Functional changes to existing classes: - now relies on openai client v1 (1.6.1) via concrete dep in langchain-openai package Codebase organization - some function calling stuff moved to `langchain_core.utils.function_calling` in order to be used in both community and langchain-openai	6 months ago
Bagatur	a7d023aaf0	core[patch], community[patch]: mark runnable context, lc load as beta (#15603 )	6 months ago
Bagatur	e1fc4d5b95	core[patch]: add beta decorator (#15589 )	6 months ago
Bagatur	00dfbd2a99	core[minor], langchain[minor]: deprecate old Chain and LLM methods (#15499 )	6 months ago
Eugene Yurtsev	bf0b3cc0b5	core[patch]: Further restrict recursive URL loader (#15559 ) Includes code from this PR: https://github.com/langchain-ai/langchain/compare/HEAD...m0kr4n3:security/fix_ssrf with additional fixes Unit tests cover new test cases	6 months ago
Bagatur	817b84de9e	core[patch]: Release 0.1.6 (#15547 )	6 months ago
Bagatur	b2f15738dd	core[patch], langchain[patch], community[patch]: Revert #15326 (#15546 )	6 months ago
Bagatur	b317ad2472	core[patch]: Release 0.1.5 (#15480 )	6 months ago
chyroc	b65e57971e	Patch: improve type hint (#15451 )	6 months ago
Li-Lun Lin	cda68d717c	core[patch]: update LanguageModelInput from List to Sequence (#14405 ) Co-authored-by: Erick Friis <erick@langchain.dev>	6 months ago
amaleki2	413a56b8f1	adding vectorstore_kwarg attribute to search_similarity function (#14604 ) - Description: the ability to add all extra parameter of vectorstore and using them SemanticSimilarityExampleSelector. - Issue: #14583 - Dependencies: no dependensies - Tag maintainer: - Twitter handle: @AmirMalekiz --------- Co-authored-by: Amir Maleki <amaleki@fb.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	6 months ago
Antonio Pisani	d4a98e4e04	core: update json output parser (#15079 ) - Description: changed json.py to handle additional cases of partial json string to be parsed, basically by dropping the last character in the string until a valid json string is found or the string is empty. Also added additional test cases. - Issue: function parse_partial_json could not parse cases where the key is present but the value is not. --------- Co-authored-by: Nuno Campos <nuno@langchain.dev>	6 months ago
Dariusz Kajtoch	15b6c049d4	core:adds tests for partial_variables (#15427 ) Description: Added small tests to test partial_variables in PromptTemplate. It was missing.	6 months ago
Bagatur	fa5d49f2c1	docs, experimental[patch], langchain[patch], community[patch]: update storage imports (#15429 ) ran ```bash g grep -l "langchain.vectorstores" \| xargs -L 1 sed -i '' "s/langchain\.vectorstores/langchain_community.vectorstores/g" g grep -l "langchain.document_loaders" \| xargs -L 1 sed -i '' "s/langchain\.document_loaders/langchain_community.document_loaders/g" g grep -l "langchain.chat_loaders" \| xargs -L 1 sed -i '' "s/langchain\.chat_loaders/langchain_community.chat_loaders/g" g grep -l "langchain.document_transformers" \| xargs -L 1 sed -i '' "s/langchain\.document_transformers/langchain_community.document_transformers/g" g grep -l "langchain\.graphs" \| xargs -L 1 sed -i '' "s/langchain\.graphs/langchain_community.graphs/g" g grep -l "langchain\.memory\.chat_message_histories" \| xargs -L 1 sed -i '' "s/langchain\.memory\.chat_message_histories/langchain_community.chat_message_histories/g" gco master libs/langchain/tests/unit_tests//test_imports.py gco master libs/langchain/tests/unit_tests/*/test_public_api.py ```	6 months ago
Harrison Chase	a33d92306c	add get prompts method (#15425 )	6 months ago
Nuno Campos	6810b4b0bc	Use tz-aware utc datetimes in tracer (#15187 ) <!-- Thank you for contributing to LangChain! Please title your PR "<package>: <description>", where <package> is whichever of langchain, community, core, experimental, etc. is being modified. Replace this entire comment with: - Description: a description of the change, - Issue: the issue # it fixes if applicable, - Dependencies: any dependencies required for this change, - Twitter handle: we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` from the root of the package you've modified to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://python.langchain.com/docs/contributing/ If you're adding a new integration, please include: 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. -->	6 months ago
Bagatur	480626dc99	docs, community[patch], experimental[patch], langchain[patch], cli[pa… (#15412 ) …tch]: import models from community ran ```bash git grep -l 'from langchain\.chat_models' \| xargs -L 1 sed -i '' "s/from\ langchain\.chat_models/from\ langchain_community.chat_models/g" git grep -l 'from langchain\.llms' \| xargs -L 1 sed -i '' "s/from\ langchain\.llms/from\ langchain_community.llms/g" git grep -l 'from langchain\.embeddings' \| xargs -L 1 sed -i '' "s/from\ langchain\.embeddings/from\ langchain_community.embeddings/g" git checkout master libs/langchain/tests/unit_tests/llms git checkout master libs/langchain/tests/unit_tests/chat_models git checkout master libs/langchain/tests/unit_tests/embeddings/test_imports.py make format cd libs/langchain; make format cd ../experimental; make format cd ../core; make format ```	6 months ago
Nuno Campos	9cbf14dec2	Fetch runnable config from context var inside runnable lambda and runnable generator (#15334 ) - easier to write custom logic/loops with automatic tracing - if you don't want to streaming support write a regular function and pass to RunnableLambda - if you do want streaming write a generator and pass it to RunnableGenerator ```py import json from typing import AsyncIterator from langchain_core.messages import BaseMessage, FunctionMessage, HumanMessage from langchain_core.agents import AgentAction, AgentFinish from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder from langchain_core.runnables import Runnable, RunnableGenerator, RunnablePassthrough from langchain_core.tools import BaseTool from langchain.agents.output_parsers import OpenAIFunctionsAgentOutputParser from langchain.chat_models import ChatOpenAI from langchain.tools.render import format_tool_to_openai_function def _get_tavily(): from langchain.tools.tavily_search import TavilySearchResults from langchain.utilities.tavily_search import TavilySearchAPIWrapper tavily_search = TavilySearchAPIWrapper() return TavilySearchResults(api_wrapper=tavily_search) async def _agent_executor_generator( input: AsyncIterator[list[BaseMessage]], *, max_iterations: int = 10, tools: dict[str, BaseTool], agent: Runnable[list[BaseMessage], BaseMessage], parser: Runnable[BaseMessage, AgentAction \| AgentFinish], ) -> AsyncIterator[BaseMessage]: messages = [m async for mm in input for m in mm] for _ in range(max_iterations): next_message = await agent.ainvoke(messages) yield next_message messages.append(next_message) parsed = await parser.ainvoke(next_message) if isinstance(parsed, AgentAction): result = await tools[parsed.tool].ainvoke(parsed.tool_input) next_message = FunctionMessage(name=parsed.tool, content=json.dumps(result)) yield next_message messages.append(next_message) elif isinstance(parsed, AgentFinish): return def get_agent_executor(tools: list[BaseTool], system_message: str): llm = ChatOpenAI(model="gpt-4-1106-preview", temperature=0, streaming=True) prompt = ChatPromptTemplate.from_messages( [ ("system", system_message), MessagesPlaceholder(variable_name="messages"), ] ) llm_with_tools = llm.bind( functions=[format_tool_to_openai_function(t) for t in tools] ) agent = {"messages": RunnablePassthrough()} \| prompt \| llm_with_tools parser = OpenAIFunctionsAgentOutputParser() executor = RunnableGenerator(_agent_executor_generator) return executor.bind( tools={tool.name for tool in tools}, agent=agent, parser=parser ) agent = get_agent_executor([_get_tavily()], "You are a very nice agent!") async def main(): async for message in agent.astream( [HumanMessage(content="whats the weather in sf tomorrow?")] ): print(message) if __name__ == "__main__": import asyncio asyncio.run(main()) ``` results in this trace https://smith.langchain.com/public/fa17f05d-9724-4d08-8fa1-750f8fcd051b/r	6 months ago
Bagatur	8e0d5813c2	langchain[patch], experimental[patch]: replace langchain.schema imports (#15410 ) Import from core instead. Ran: ```bash git grep -l 'from langchain.schema\.output_parser' \| xargs -L 1 sed -i '' "s/from\ langchain\.schema\.output_parser/from\ langchain_core.output_parsers/g" git grep -l 'from langchain.schema\.messages' \| xargs -L 1 sed -i '' "s/from\ langchain\.schema\.messages/from\ langchain_core.messages/g" git grep -l 'from langchain.schema\.document' \| xargs -L 1 sed -i '' "s/from\ langchain\.schema\.document/from\ langchain_core.documents/g" git grep -l 'from langchain.schema\.runnable' \| xargs -L 1 sed -i '' "s/from\ langchain\.schema\.runnable/from\ langchain_core.runnables/g" git grep -l 'from langchain.schema\.vectorstore' \| xargs -L 1 sed -i '' "s/from\ langchain\.schema\.vectorstore/from\ langchain_core.vectorstores/g" git grep -l 'from langchain.schema\.language_model' \| xargs -L 1 sed -i '' "s/from\ langchain\.schema\.language_model/from\ langchain_core.language_models/g" git grep -l 'from langchain.schema\.embeddings' \| xargs -L 1 sed -i '' "s/from\ langchain\.schema\.embeddings/from\ langchain_core.embeddings/g" git grep -l 'from langchain.schema\.storage' \| xargs -L 1 sed -i '' "s/from\ langchain\.schema\.storage/from\ langchain_core.stores/g" git checkout master libs/langchain/tests/unit_tests/schema/ make format cd libs/experimental make format cd ../langchain make format ```	6 months ago
Ankush Gola	f50dba12ff	Calculate trace_id and dotted_order client side (#15351 ) <!-- Thank you for contributing to LangChain! Please title your PR "<package>: <description>", where <package> is whichever of langchain, community, core, experimental, etc. is being modified. Replace this entire comment with: - Description: a description of the change, - Issue: the issue # it fixes if applicable, - Dependencies: any dependencies required for this change, - Twitter handle: we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` from the root of the package you've modified to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://python.langchain.com/docs/contributing/ If you're adding a new integration, please include: 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. -->	6 months ago
Paresh Chiramel	9be08a1956	Update _retrieve_ref inside json_schema.py to include an isdigit() check (#14745 ) - Description: Update _retrieve_ref inside json_schema.py to include an isdigit() check - Issue: This library is used inside dereference_refs inside langchain_community.agent_toolkits.openapi.spec. When I read in a yaml file which has references for "400", "401" etc; the line "out = out[component]" causes a KeyError. The isdigit() check ensures that if it is an integer like "400" or "401"; it converts it into integer before using it as a key to prevent the error. - Dependencies: No dependencies - Tag maintainer: @baskaryan --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	6 months ago
chyroc	0665a7da19	Docs: add param comment for `tracing_v2_enabled` (#15308 ) Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	6 months ago
Nuno Campos	b9636e5c98	Catch type errors in dumps/dumpd (#15336 ) These can happen for edge cases not covered by `default` handler (eg. "strange" keys in dicts) <!-- Thank you for contributing to LangChain! Please title your PR "<package>: <description>", where <package> is whichever of langchain, community, core, experimental, etc. is being modified. Replace this entire comment with: - Description: a description of the change, - Issue: the issue # it fixes if applicable, - Dependencies: any dependencies required for this change, - Twitter handle: we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` from the root of the package you've modified to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://python.langchain.com/docs/contributing/ If you're adding a new integration, please include: 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. -->	6 months ago
Nuno Campos	99000c612e	Propagate context vars in all classes/methods (#15329 ) - Any direct usage of ThreadPoolExecutor or asyncio.run_in_executor needs manual handling of context vars <!-- Thank you for contributing to LangChain! Please title your PR "<package>: <description>", where <package> is whichever of langchain, community, core, experimental, etc. is being modified. Replace this entire comment with: - Description: a description of the change, - Issue: the issue # it fixes if applicable, - Dependencies: any dependencies required for this change, - Twitter handle: we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` from the root of the package you've modified to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://python.langchain.com/docs/contributing/ If you're adding a new integration, please include: 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. -->	6 months ago
Ankush Gola	7eec8f2487	Delete V1 tracer and refactor tracer tests to core (#15326 )	6 months ago
Nuno Campos	4e4b119614	Fix executor	6 months ago
chyroc	7ce338201c	Patch: improve check openai version (#15301 )	6 months ago
Jon Nolen	27ee61645d	core: Update messages/__init__.py to account for AIMessageChunk which breaks message history runnable. (#15327 ) - Description: fix parse issue for AIMessageChunk when using - Issue: https://github.com/langchain-ai/langchain/issues/14511 - Dependencies: none - Twitter handle: none Taken from this fix: https://github.com/gpt-engineer-org/gpt-engineer/issues/804#issuecomment-1769853850 Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` from the root of the package you've modified to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://python.langchain.com/docs/contributing/ If you're adding a new integration, please include: 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	6 months ago
Nuno Campos	f7313adf2a	old py compat	6 months ago
Nuno Campos	eb5e250188	Propagate context vars in all classes/methods - Any direct usage of ThreadPoolExecutor or asyncio.run_in_executor needs manual handling of context vars	6 months ago
Harrison Chase	c3b3b77a11	[core] add test for json parser (#15297 ) this should fail, but isnt --------- Co-authored-by: Nuno Campos <nuno@langchain.dev>	6 months ago
Nuno Campos	ec090745a6	Improve markdown list parser (#15295 ) - do not match text after - in the middle of a sentence <!-- Thank you for contributing to LangChain! Please title your PR "<package>: <description>", where <package> is whichever of langchain, community, core, experimental, etc. is being modified. Replace this entire comment with: - Description: a description of the change, - Issue: the issue # it fixes if applicable, - Dependencies: any dependencies required for this change, - Twitter handle: we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` from the root of the package you've modified to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://python.langchain.com/docs/contributing/ If you're adding a new integration, please include: 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. -->	6 months ago
Bagatur	80ceed6da5	core[patch]: Release 0.1.4 (#15319 )	6 months ago
Nuno Campos	36ceffd2cd	Strip code block fences and extra test from xml when doing streaming … (#15293 ) …parse <!-- Thank you for contributing to LangChain! Please title your PR "<package>: <description>", where <package> is whichever of langchain, community, core, experimental, etc. is being modified. Replace this entire comment with: - Description: a description of the change, - Issue: the issue # it fixes if applicable, - Dependencies: any dependencies required for this change, - Twitter handle: we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` from the root of the package you've modified to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://python.langchain.com/docs/contributing/ If you're adding a new integration, please include: 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. -->	6 months ago
joshy-deshaw	bf5385592e	core, community: propagate context between threads (#15171 ) While using `chain.batch`, the default implementation uses a `ThreadPoolExecutor` and run the chains in separate threads. An issue with this approach is that that [the token counting callback](https://python.langchain.com/docs/modules/callbacks/token_counting) fails to work as a consequence of the context not being propagated between threads. This PR adds context propagation to the new threads and adds some thread synchronization in the OpenAI callback. With this change, the token counting callback works as intended. Having the context propagation change would be highly beneficial for those implementing custom callbacks for similar functionalities as well. --------- Co-authored-by: Nuno Campos <nuno@langchain.dev>	6 months ago
Nuno Campos	f74151b4e4	Make all json parsing less strict by default (#15287 ) - Enables strict=False by default - Uses partial json recovery logic by default <!-- Thank you for contributing to LangChain! Please title your PR "<package>: <description>", where <package> is whichever of langchain, community, core, experimental, etc. is being modified. Replace this entire comment with: - Description: a description of the change, - Issue: the issue # it fixes if applicable, - Dependencies: any dependencies required for this change, - Twitter handle: we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` from the root of the package you've modified to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://python.langchain.com/docs/contributing/ If you're adding a new integration, please include: 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. -->	6 months ago
Harrison Chase	b86803153e	[core, langchain] modelio code improvements (#15277 )	6 months ago
Nuno Campos	22b3a233b8	Update passthrough.py (#15252 ) <!-- Thank you for contributing to LangChain! Please title your PR "<package>: <description>", where <package> is whichever of langchain, community, core, experimental, etc. is being modified. Replace this entire comment with: - Description: a description of the change, - Issue: the issue # it fixes if applicable, - Dependencies: any dependencies required for this change, - Twitter handle: we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` from the root of the package you've modified to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://python.langchain.com/docs/contributing/ If you're adding a new integration, please include: 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. -->	6 months ago
chyroc	6fb3cc6f27	Fix: Use `Union` instead of `\|` to improve compatibility, fix #15244 (#15245 )	6 months ago
Nuno Campos	6a5a2fb9c8	Add .pick and .assign methods to Runnable (#15229 ) <!-- Thank you for contributing to LangChain! Please title your PR "<package>: <description>", where <package> is whichever of langchain, community, core, experimental, etc. is being modified. Replace this entire comment with: - Description: a description of the change, - Issue: the issue # it fixes if applicable, - Dependencies: any dependencies required for this change, - Twitter handle: we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` from the root of the package you've modified to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://python.langchain.com/docs/contributing/ If you're adding a new integration, please include: 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. -->	6 months ago
Nuno Campos	0252a24471	Implement nicer runnable seq constructor, Propagate name through Runn… (#15226 ) …ableBinding <!-- Thank you for contributing to LangChain! Please title your PR "<package>: <description>", where <package> is whichever of langchain, community, core, experimental, etc. is being modified. Replace this entire comment with: - Description: a description of the change, - Issue: the issue # it fixes if applicable, - Dependencies: any dependencies required for this change, - Twitter handle: we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` from the root of the package you've modified to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://python.langchain.com/docs/contributing/ If you're adding a new integration, please include: 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. -->	6 months ago
Nuno Campos	f36ef0739d	Add create_conv_retrieval_chain func (#15084 ) ``` +----------+ \| MapInput \| +----------+ * +------------------------------------+ \| Lambda(itemgetter('chat_history')) \| * +------------------------------------+ * * * * * * * +---------------------------+ +--------------------------------+ \| Lambda(_get_chat_history) \| \| Lambda(itemgetter('question')) \| +---------------------------+ +--------------------------------+ * * * * * * +----------------------------+ +------------------------+ \| ContextSet('chat_history') \| \| ContextSet('question') \| +----------------------------+ +------------------------+ ** ** +-----------+ \| MapOutput \| +-----------+ * * * +----------------+ \| PromptTemplate \| +----------------+ * * * +-------------+ \| FakeListLLM \| +-------------+ * * * +-----------------+ \| StrOutputParser \| +-----------------+ * * * +----------------------------+ \| ContextSet('new_question') \| +----------------------------+ * * * +---------------------+ \| SequentialRetriever \| +---------------------+ * * * +------------------------------------+ \| Lambda(_reduce_tokens_below_limit) \| +------------------------------------+ * * * +-------------------------------+ \| ContextSet('input_documents') \| +-------------------------------+ * * * +----------+ *\| MapInput \| *** +----------+ **** ****** * ***** ***** * ****** ** * ** +-------------------------------+ +----------------------------+ +----------------------------+ \| ContextGet('input_documents') \| \| ContextGet('chat_history') \| \| ContextGet('new_question') \| +-------------------------------+ +----------------------------+ +----------------------------+ ******* * ***** ****** * **** *** * **** +-----------+ \| MapOutput \| +-----------+ * * * +-------------+ \| FakeListLLM \| +-------------+ * * * +----------+ *\| MapInput \|* ****** +----------+ ** ***** * *** ****** * **** ** * * +-------------------------------+ +----------------------------+ +-------------+ \| ContextGet('input_documents') \| \| ContextGet('new_question') \| \| Passthrough \| +-------------------------------+ +----------------------------+ ***** +-------------+ ***** * **** **** * ***** ** * **** +-----------+ \| MapOutput \| +-----------+ ``` --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	6 months ago
Harrison Chase	4ad77f777e	[core] prompt changes (#15186 ) change it to pass all variables through all the way in invoke	6 months ago
Nuno Campos	ccf9c8e0be	Better input and output schemas for chains that start or end with a R… (#15185 ) …unnableAssign or RunnablePick <!-- Thank you for contributing to LangChain! Please title your PR "<package>: <description>", where <package> is whichever of langchain, community, core, experimental, etc. is being modified. Replace this entire comment with: - Description: a description of the change, - Issue: the issue # it fixes if applicable, - Dependencies: any dependencies required for this change, - Twitter handle: we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` from the root of the package you've modified to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://python.langchain.com/docs/contributing/ If you're adding a new integration, please include: 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. -->	6 months ago
Nuno Campos	8cdc633465	Implement RunnablePassthrough.pick() (#15184 ) <!-- Thank you for contributing to LangChain! Please title your PR "<package>: <description>", where <package> is whichever of langchain, community, core, experimental, etc. is being modified. Replace this entire comment with: - Description: a description of the change, - Issue: the issue # it fixes if applicable, - Dependencies: any dependencies required for this change, - Twitter handle: we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` from the root of the package you've modified to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://python.langchain.com/docs/contributing/ If you're adding a new integration, please include: 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. -->	6 months ago
Quy Tang	7ef25a3c1b	Implement stream and astream for RunnableLambda (#14794 ) Description: Implement stream and astream methods for RunnableLambda to make streaming work for functions returning Runnable - Issue: https://github.com/langchain-ai/langchain/issues/11998 - Dependencies: No new dependencies - Twitter handle: https://twitter.com/qtangs --------- Co-authored-by: Nuno Campos <nuno@langchain.dev>	6 months ago
Nuno Campos	7e26559256	Fix runnable vistitor for funcs without pos args (#15182 )	6 months ago
Harrison Chase	b4a0d206d9	[core: minor] fix getters (#15181 )	6 months ago
Harrison Chase	63916cfe35	[core] langauge model like (#15180 )	6 months ago
Harrison Chase	33e024ad10	[core] print ascii (#15179 )	6 months ago
Nuno Campos	a2d3042823	Improve graph repr for runnable passthrough and itemgetter (#15083 ) <!-- Thank you for contributing to LangChain! Please title your PR "<package>: <description>", where <package> is whichever of langchain, community, core, experimental, etc. is being modified. Replace this entire comment with: - Description: a description of the change, - Issue: the issue # it fixes if applicable, - Dependencies: any dependencies required for this change, - Twitter handle: we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` from the root of the package you've modified to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://python.langchain.com/docs/contributing/ If you're adding a new integration, please include: 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. -->	7 months ago
Nuno Campos	0d0901ea18	Nc/dec22/runnable graph lambda (#15078 ) <!-- Thank you for contributing to LangChain! Please title your PR "<package>: <description>", where <package> is whichever of langchain, community, core, experimental, etc. is being modified. Replace this entire comment with: - Description: a description of the change, - Issue: the issue # it fixes if applicable, - Dependencies: any dependencies required for this change, - Twitter handle: we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` from the root of the package you've modified to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://python.langchain.com/docs/contributing/ If you're adding a new integration, please include: 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. -->	7 months ago
Sypherd	d4f45b1421	core(minor): Allow explicit types for ChatMessageHistory adds (#14967 ) <!-- Thank you for contributing to LangChain! Replace this entire comment with: - Description: a description of the change, - Issue: the issue # it fixes (if applicable), - Dependencies: any dependencies required for this change, - Tag maintainer: for a quicker response, tag the relevant maintainer (see below), - Twitter handle: we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://python.langchain.com/docs/contributing/ If you're adding a new integration, please include: 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/extras` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. --> ## Description Changes the behavior of `add_user_message` and `add_ai_message` to allow for messages of those types to be passed in. Currently, if you want to use the `add_user_message` or `add_ai_message` methods, you have to pass in a string. For `add_message` on `ChatMessageHistory`, however, you have to pass a `BaseMessage`. This behavior seems a bit inconsistent. Personally, I'd love to be able to be explicit that I want to `add_user_message` and pass in a `HumanMessage` without having to grab the `content` attribute. This PR allows `add_user_message` to accept `HumanMessage`s or `str`s and `add_ai_message` to accept `AIMessage`s or `str`s to add that functionality and ensure backwards compatibility. ## Issue * None ## Dependencies * None ## Tag maintainer @hinthornw @baskaryan ## Note `make test` results in `make: *** No rule to make target 'test'. Stop.`	7 months ago
chyroc	0e149bbb4c	Improve: remove extra spaces in get_from_env error (#15064 )	7 months ago
Nuno Campos	7d5800ee51	Add Runnable.get_graph() to get a graph representation of a Runnable (#15040 ) It can be drawn in ascii with Runnable.get_graph().draw()	7 months ago
Ran	129a929d69	infra: Fix test filesystem paths incompatible with windows (#14388 ) - Description: This PR fixes test failures on Windows caused by path handling differences and unescaped special characters in regex. The failing tests are: ``` FAILED tests/unit_tests/storage/test_filesystem.py::test_yield_keys - AssertionError: assert ['key1', 'subdir\\key2'] == ['key1', 'subdir/key2'] FAILED tests/unit_tests/test_imports.py::test_importable_all - ModuleNotFoundError: No module named 'langchain_community.langchain_community\\adapters' FAILED tests/unit_tests/tools/file_management/test_utils.py::test_get_validated_relative_path_errs_on_absolute - re.error: incomplete escape \U at position 53 FAILED tests/unit_tests/tools/file_management/test_utils.py::test_get_validated_relative_path_errs_on_parent_dir - re.error: incomplete escape \U at position 69 FAILED tests/unit_tests/tools/file_management/test_utils.py::test_get_validated_relative_path_errs_for_symlink_outside_root - re.error: incomplete escape \U at position 64 ``` - Issue: fixes https://github.com/langchain-ai/langchain/issues/11775 (partially) - Dependencies: none	7 months ago
Nuno Campos	71076cceaf	Move json and xml parsers to core (#15026 ) <!-- Thank you for contributing to LangChain! Please title your PR "<package>: <description>", where <package> is whichever of langchain, community, core, experimental, etc. is being modified. Replace this entire comment with: - Description: a description of the change, - Issue: the issue # it fixes if applicable, - Dependencies: any dependencies required for this change, - Twitter handle: we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` from the root of the package you've modified to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://python.langchain.com/docs/contributing/ If you're adding a new integration, please include: 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. -->	7 months ago
Nuno Campos	d5533b7081	Add option to make messages placeholder optional (#15031 ) <!-- Thank you for contributing to LangChain! Please title your PR "<package>: <description>", where <package> is whichever of langchain, community, core, experimental, etc. is being modified. Replace this entire comment with: - Description: a description of the change, - Issue: the issue # it fixes if applicable, - Dependencies: any dependencies required for this change, - Twitter handle: we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` from the root of the package you've modified to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://python.langchain.com/docs/contributing/ If you're adding a new integration, please include: 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. -->	7 months ago
Bagatur	7eb1100925	core[patch]: Release 0.1.3 (#15022 )	7 months ago
Nuno Campos	63e512b680	Implement streaming for all list output parsers (#14981 ) <!-- Thank you for contributing to LangChain! Please title your PR "<package>: <description>", where <package> is whichever of langchain, community, core, experimental, etc. is being modified. Replace this entire comment with: - Description: a description of the change, - Issue: the issue # it fixes if applicable, - Dependencies: any dependencies required for this change, - Twitter handle: we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` from the root of the package you've modified to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://python.langchain.com/docs/contributing/ If you're adding a new integration, please include: 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. -->	7 months ago
chyroc	57d1eb733f	core[patch]: update langchain-core runtime library name (#14884 ) Co-authored-by: Erick Friis <erick@langchain.dev>	7 months ago
Quy Tang	42822484ef	core(minor): Implement stream and astream for RunnableBranch (#14805 ) * This PR adds `stream` implementations to Runnable Branch. * Runnable Branch still does not support `transform` so it'll break streaming if it happens in middle or end of sequence, but will work if happens at beginning of sequence. * Fixes use the async callback manager for async methods * Handle BaseException rather than Exception, so more errors could be logged as errors when they are encountered --------- Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>	7 months ago
Bagatur	a841f62791	core[patch]: 0.1.2 (#14959 )	7 months ago
Leonid Ganeline	14d04180eb	docstrings `core` update (#14871 ) Added missed docstrings	7 months ago
Harrison Chase	193f107cb5	add methods to deserialize prompts that were old (#14857 )	7 months ago
Erick Friis	8a07c56313	docs: developer docs (#14776 ) Builds out a developer documentation section in the docs - Links it from contributing.md - Adds an initial guide on how to contribute an integration --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	7 months ago
William FH	93c7eb4e6b	[Tracing] String Stacktrace (#14131 ) Add full stacktrace	7 months ago
Bagatur	b802dd96f2	core[patch]: Release 0.1.1 (#14738 )	7 months ago
Bagatur	47451951a1	core[patch]: Fix runnable with message history (#14629 ) Fix bug shown in #14458. Namely, that saving inputs to history fails when the input to base runnable is a list of messages	7 months ago
Nuno Campos	a16f4a318f	\Fix tool_calls message merge (#14613 ) <!-- Thank you for contributing to LangChain! Replace this entire comment with: - Description: a description of the change, - Issue: the issue # it fixes (if applicable), - Dependencies: any dependencies required for this change, - Tag maintainer: for a quicker response, tag the relevant maintainer (see below), - Twitter handle: we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md If you're adding a new integration, please include: 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/extras` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. -->	7 months ago
Bagatur	ca7da8f7ef	docs: fix links in readme (#14624 )	7 months ago
Bagatur	2a10cabf66	docs: core and community readme (#14623 )	7 months ago
Bagatur	5d1deddbfb	core[minor]: Release 0.1.0 (#14607 )	7 months ago
Harrison Chase	ad8d8f71aa	allow other namespaces (#14606 )	7 months ago
Eugene Yurtsev	76905aa043	Update RunnableWithMessageHistory (#14351 ) This PR updates RunnableWithMessage history to support user specific configuration for the factory. It extends support to passing multiple named arguments into the factory if the factory takes more than a single argument.	7 months ago
Erick Friis	0a9d933bb2	infra: import checking bugfix (#14569 )	7 months ago
Erick Friis	482e2b94fa	infra: import CI speed (#14566 ) Was taking 10 mins. Now a few seconds.	7 months ago
Erick Friis	5418d8bfd6	infra: import CI fix (#14562 ) TIL `**` globstar doesn't work in make Makefile changes fix that. `__getattr__` changes allow import of all files, but raise error when accessing anything from the module. file deletions were corresponding libs change from #14559	7 months ago
Bagatur	9cb128e6e2	core[patch]: Release 0.0.13 (#14558 )	7 months ago
Nuno Campos	3b5b0f16c6	Move runnable context to beta (#14507 ) <!-- Thank you for contributing to LangChain! Replace this entire comment with: - Description: a description of the change, - Issue: the issue # it fixes (if applicable), - Dependencies: any dependencies required for this change, - Tag maintainer: for a quicker response, tag the relevant maintainer (see below), - Twitter handle: we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md If you're adding a new integration, please include: 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/extras` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. -->	7 months ago
Bagatur	ed58eeb9c5	community[major], core[patch], langchain[patch], experimental[patch]: Create langchain-community (#14463 ) Moved the following modules to new package langchain-community in a backwards compatible fashion: ``` mv langchain/langchain/adapters community/langchain_community mv langchain/langchain/callbacks community/langchain_community/callbacks mv langchain/langchain/chat_loaders community/langchain_community mv langchain/langchain/chat_models community/langchain_community mv langchain/langchain/document_loaders community/langchain_community mv langchain/langchain/docstore community/langchain_community mv langchain/langchain/document_transformers community/langchain_community mv langchain/langchain/embeddings community/langchain_community mv langchain/langchain/graphs community/langchain_community mv langchain/langchain/llms community/langchain_community mv langchain/langchain/memory/chat_message_histories community/langchain_community mv langchain/langchain/retrievers community/langchain_community mv langchain/langchain/storage community/langchain_community mv langchain/langchain/tools community/langchain_community mv langchain/langchain/utilities community/langchain_community mv langchain/langchain/vectorstores community/langchain_community mv langchain/langchain/agents/agent_toolkits community/langchain_community mv langchain/langchain/cache.py community/langchain_community mv langchain/langchain/adapters community/langchain_community mv langchain/langchain/callbacks community/langchain_community/callbacks mv langchain/langchain/chat_loaders community/langchain_community mv langchain/langchain/chat_models community/langchain_community mv langchain/langchain/document_loaders community/langchain_community mv langchain/langchain/docstore community/langchain_community mv langchain/langchain/document_transformers community/langchain_community mv langchain/langchain/embeddings community/langchain_community mv langchain/langchain/graphs community/langchain_community mv langchain/langchain/llms community/langchain_community mv langchain/langchain/memory/chat_message_histories community/langchain_community mv langchain/langchain/retrievers community/langchain_community mv langchain/langchain/storage community/langchain_community mv langchain/langchain/tools community/langchain_community mv langchain/langchain/utilities community/langchain_community mv langchain/langchain/vectorstores community/langchain_community mv langchain/langchain/agents/agent_toolkits community/langchain_community mv langchain/langchain/cache.py community/langchain_community ``` Moved the following to core ``` mv langchain/langchain/utils/json_schema.py core/langchain_core/utils mv langchain/langchain/utils/html.py core/langchain_core/utils mv langchain/langchain/utils/strings.py core/langchain_core/utils cat langchain/langchain/utils/env.py >> core/langchain_core/utils/env.py rm langchain/langchain/utils/env.py ``` See .scripts/community_split/script_integrations.sh for all changes	7 months ago
Eugene Yurtsev	c0f4b95aa9	RunnableWithMessageHistory: Fix input schema (#14516 ) Input schema should not have history key	7 months ago
Harrison Chase	f5befe3b89	manual mapping (#14422 )	7 months ago
Erick Friis	b3f226e8f8	core[patch], langchain[patch], experimental[patch]: import CI (#14414 )	7 months ago
Eugene Yurtsev	37bee92b8a	Use deepcopy in RunLogPatch (#14244 ) This PR adds deepcopy usage in RunLogPatch. I included a unit-test that shows an issue that was caused in LangServe in the RemoteClient. ```python import jsonpatch s1 = {} s2 = {'value': []} s3 = {'value': ['a']} ops0 = list(jsonpatch.JsonPatch.from_diff(None, s1)) ops1 = list(jsonpatch.JsonPatch.from_diff(s1, s2)) ops2 = list(jsonpatch.JsonPatch.from_diff(s2, s3)) ops = ops0 + ops1 + ops2 jsonpatch.apply_patch(None, ops) {'value': ['a']} jsonpatch.apply_patch(None, ops) {'value': ['a', 'a']} jsonpatch.apply_patch(None, ops) {'value': ['a', 'a', 'a']} ```	7 months ago
Bagatur	eb209e7ee3	core[patch]: Release 0.0.12 (#14415 )	7 months ago
Bagatur	b2280fd874	core[patch], langchain[patch]: fix required deps (#14373 )	7 months ago
Bagatur	a7271cf5bd	core[patch]: Release 0.0.11 (#14367 )	7 months ago
Nuno Campos	77c38df36c	[core/minor] Runnables: Implement a context api (#14046 ) <!-- Thank you for contributing to LangChain! Replace this entire comment with: - Description: a description of the change, - Issue: the issue # it fixes (if applicable), - Dependencies: any dependencies required for this change, - Tag maintainer: for a quicker response, tag the relevant maintainer (see below), - Twitter handle: we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md If you're adding a new integration, please include: 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/extras` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. --> --------- Co-authored-by: Brace Sproul <braceasproul@gmail.com>	7 months ago
Erick Friis	8f95a8206b	core[patch]: message history error typo (#14361 )	7 months ago
Erick Friis	7bdfc43766	core[patch], langchain[patch]: ByteStore (#14312 )	7 months ago
Eugene Yurtsev	0dea8cc62d	Update doc-string in RunnableWithMessageHistory (#14262 ) Update doc-string in RunnableWithMessageHistory	7 months ago
James Braza	3b75d37cee	Adding `BaseChatMessageHistory.__str__` (#14311 ) Adding __str__ to base chat message history to make it easier to debug	7 months ago
James Braza	8b0060184d	Fixing empty input variable crashing `PromptTemplate` validations (#14314 ) - Fixes `input_variables=[""]` crashing validations with a template `"{}"` - Uses `__cause__` for proper `Exception` chaining in `check_valid_template`	7 months ago
Bagatur	4a5a13aab3	core[patch]: Release 0.0.10 (#14303 )	7 months ago
Harrison Chase	8eab4d95c0	Harrison/delegate from template (#14266 ) Co-authored-by: M.R. Sopacua <144725145+msopacua@users.noreply.github.com>	7 months ago
Jon Watte	e042e5df35	fix: call _on_llm_error() (#13581 ) Description: There's a copy-paste typo where on_llm_error() calls _on_chain_error() instead of _on_llm_error(). Issue: #13580 Dependencies: None Tag maintainer: @hwchase17 Twitter handle: @jwatte "Run `make format`, `make lint` and `make test` to check this locally." The test scripts don't work in a plain Ubuntu LTS 20.04 system. It looks like the dev container pulling is stuck. Or maybe the internet is just ornery today. --------- Co-authored-by: jwatte <jwatte@observeinc.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	7 months ago
Hynek Kydlíček	aa8ae31e5b	core[patch]: add response kwarg to on_llm_error # Dependencies None # Twitter handle @HKydlicek --------- Co-authored-by: Erick Friis <erick@langchain.dev>	7 months ago
Vincent Brouwers	67662564f3	langchain[patch]: Fix `config` arg detection for wrapped lambdarunnable (#14230 ) Description: When a RunnableLambda only receives a synchronous callback, this callback is wrapped into an async one since #13408. However, this wrapping with `(args, *kwargs)` causes the `accepts_config` check at [/libs/core/langchain_core/runnables/config.py#L342](`ee94ef55ee/libs/core/langchain_core/runnables/config.py (L342)`) to fail, as this checks for the presence of a "config" argument in the method signature. Adding a `functools.wraps` around it, resolves it.	7 months ago
Hendrik Hogertz	e6862e6e7d	Fix Azure Openai function calling in streaming mode (#13768 ) - Description: This PR addresses an issue with the OpenAI API streaming response, where initially the key (arguments) is provided but the value is None. Subsequently, it updates with {"arguments": "{\n"}, leading to a type inconsistency that causes an exception. The specific error encountered is ValueError: additional_kwargs["arguments"] already exists in this message, but with a different type. This change aims to resolve this inconsistency and ensure smooth API interactions. - Issue: None. - Dependencies: None. - Tag maintainer: @eyurtsev This is an updated version of #13229 based on the refactored code. Credit goes to @superken01. Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	7 months ago
James Braza	3833882ab7	Removing extra `StdOutCallbackHandler` overridden methods (#14136 ) Unnecessarily overridden methods: - Give the idea the subclass is doing something special (when it isn't) - Block CTRL-click to the actual method This PR removes some unnecessarily overridden methods in `StdOutCallbackHandler` Supercedes https://github.com/langchain-ai/langchain/pull/12858	7 months ago
Bagatur	15c04a5670	core[patch]: Release 0.0.9 (#14182 )	7 months ago
James Braza	bdb6ae2ed3	core[patch]: `BaseTracer` helper method for `Run` lookup (#14139 ) I observed the same run ID extraction logic is repeated many times in `BaseTracer`. This PR creates a helper method for DRY code.	7 months ago
James Braza	24385a00de	core[minor], langchain[patch], experimental[patch]: Added missing `py.typed` to `langchain_core` (#14143 ) See PR title. From what I can see, `poetry` will auto-include this. Please let me know if I am missing something here. --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	7 months ago
William FH	528fc76d6a	Update Prompt Format Error (#14044 ) The number of times I try to format a string (especially in lcel) is embarrassingly high. Think this may be more actionable than the default error message. Now I get nice helpful errors ``` KeyError: "Input to ChatPromptTemplate is missing variable 'input'. Expected: ['input'] Received: ['dialogue']" ```	7 months ago
Bagatur	efce352d6b	core[patch]: release 0.0.8 (#14086 )	7 months ago
Jeremy Naccache	a14cf87576	core[patch]: Add kwargs to Langchain's dumps() to allow passing of json.dumps() … (#10628 ) …parameters. In Langchain's `dumps()` function, I've added a `kwargs` parameter. This allows users to pass additional parameters to the underlying `json.dumps()` function, providing greater flexibility and control over JSON serialization. Many parameters available in `json.dumps()` can be useful or even necessary in specific situations. For example, when using an Agent with return_intermediate_steps set to true, the output is a list of AgentAction objects. These objects can't be serialized without using Langchain's `dumps()` function. The issue arises when using the Agent with a language other than English, which may contain non-ASCII characters like 'é'. The default behavior of `json.dumps()` sets ensure_ascii to true, converting `{"name": "José"}` into `{"name": "Jos\u00e9"}`. This can make the output hard to read, especially in the case of intermediate steps in agent logs. By allowing users to pass additional parameters to `json.dumps()` via Langchain's dumps(), we can solve this problem. For instance, users can set `ensure_ascii=False` to maintain the original characters. This update also enables users to pass other useful `json.dumps()` parameters like `sort_keys`, providing even more flexibility. The implementation takes into account edge cases where a user might pass a "default" parameter, which is already defined by `dumps()`, or an "indent" parameter, which is also predefined if `pretty=True` is set. --------- Co-authored-by: Erick Friis <erick@langchain.dev>	7 months ago
Bagatur	14799b139a	infra[patch]: add base deps and fix docs lint (#13998 )	7 months ago
Bagatur	1aed2d1f08	core[patch]: release 0.0.7 (#13989 )	7 months ago
David Duong	eb67f07e32	Track RunnableAssign as a separate run trace (#13972 ) Addressing incorrect order being sent to callbacks / tracers, due to the nature of threading --------- Co-authored-by: Nuno Campos <nuno@boringbits.io>	7 months ago
Nuno Campos	0f255bb6c4	In Runnable.stream_log build up final_output from adding output chunks (#12781 ) Add arg to omit streamed_output list, in cases where final_output is enough this saves bandwidth <!-- Thank you for contributing to LangChain! Replace this entire comment with: - Description: a description of the change, - Issue: the issue # it fixes (if applicable), - Dependencies: any dependencies required for this change, - Tag maintainer: for a quicker response, tag the relevant maintainer (see below), - Twitter handle: we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md If you're adding a new integration, please include: 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/extras` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. -->	7 months ago
Nuno Campos	970fe23feb	Fixes for opengpts release (#13960 )	7 months ago
Bagatur	48fbc5513d	infra[patch], langchain[patch]: fix test deps and upper bound langchain dep on core(#13984 )	7 months ago
mengjincn	05ea4fd37d	fix merge None value and non None value error (#13703 ) <!-- Thank you for contributing to LangChain! Replace this entire comment with: - Description: a description of the change, - Issue: the issue # it fixes (if applicable), - Dependencies: any dependencies required for this change, - Tag maintainer: for a quicker response, tag the relevant maintainer (see below), - Twitter handle: we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md If you're adding a new integration, please include: 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/extras` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. -->	7 months ago
Erick Friis	f9bef600f1	RELEASE: core 0.0.7 (#13973 )	7 months ago
Nicolas Bondoux	e17edc4d0b	RunnableLambda: create afunc instance from func when not provided (#13408 ) Fixes #13407. This workaround consists in letting the RunnableLambda create its self.afunc from its self.func when self.afunc is not provided; the change has no dependency. <!-- Thank you for contributing to LangChain! Replace this entire comment with: - Description: a description of the change, - Issue: the issue # it fixes (if applicable), - Dependencies: any dependencies required for this change, - Tag maintainer: for a quicker response, tag the relevant maintainer (see below), - Twitter handle: we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md If you're adding a new integration, please include: 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/extras` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. --> --------- Co-authored-by: Erick Friis <erick@langchain.dev> Co-authored-by: Nuno Campos <nuno@langchain.dev>	7 months ago
Nuno Campos	391f200eaa	Implement stream() and astream() for agents (#12783 ) ``` ---- chunk 1 {'actions': [AgentActionMessageLog(tool='Search', tool_input="Leo DiCaprio's current girlfriend", log="\nInvoking: `Search` with `Leo DiCaprio's current girlfriend`\n\n\n", message_log=[AIMessageChunk(content='', additional_kwargs={'function_call': {'name': 'Search', 'arguments': '{\n "__arg1": "Leo DiCaprio\'s current girlfriend"\n}'}})])], 'messages': [AIMessageChunk(content='', additional_kwargs={'function_call': {'name': 'Search', 'arguments': '{\n "__arg1": "Leo DiCaprio\'s current girlfriend"\n}'}})]} ---- chunk 2 {'messages': [FunctionMessage(content="According to Us, the 48-year-old actor is now “exclusively” dating Italian model Vittoria Ceretti. A source told Us that DiCaprio is “completely smitten” with Ceretti, and their relationship is “going so well that Leo's actually being exclusive.”", name='Search')], 'steps': [AgentStep(action=AgentActionMessageLog(tool='Search', tool_input="Leo DiCaprio's current girlfriend", log="\nInvoking: `Search` with `Leo DiCaprio's current girlfriend`\n\n\n", message_log=[AIMessageChunk(content='', additional_kwargs={'function_call': {'name': 'Search', 'arguments': '{\n "__arg1": "Leo DiCaprio\'s current girlfriend"\n}'}})]), observation="According to Us, the 48-year-old actor is now “exclusively” dating Italian model Vittoria Ceretti. A source told Us that DiCaprio is “completely smitten” with Ceretti, and their relationship is “going so well that Leo's actually being exclusive.”")]} ---- chunk 3 {'actions': [AgentActionMessageLog(tool='Search', tool_input='Vittoria Ceretti age', log='\nInvoking: `Search` with `Vittoria Ceretti age`\n\n\n', message_log=[AIMessageChunk(content='', additional_kwargs={'function_call': {'name': 'Search', 'arguments': '{\n "__arg1": "Vittoria Ceretti age"\n}'}})])], 'messages': [AIMessageChunk(content='', additional_kwargs={'function_call': {'name': 'Search', 'arguments': '{\n "__arg1": "Vittoria Ceretti age"\n}'}})]} ---- chunk 4 {'messages': [FunctionMessage(content='25 years', name='Search')], 'steps': [AgentStep(action=AgentActionMessageLog(tool='Search', tool_input='Vittoria Ceretti age', log='\nInvoking: `Search` with `Vittoria Ceretti age`\n\n\n', message_log=[AIMessageChunk(content='', additional_kwargs={'function_call': {'name': 'Search', 'arguments': '{\n "__arg1": "Vittoria Ceretti age"\n}'}})]), observation='25 years')]} ---- chunk 5 {'actions': [AgentActionMessageLog(tool='Calculator', tool_input='25^0.43', log='\nInvoking: `Calculator` with `25^0.43`\n\n\n', message_log=[AIMessageChunk(content='', additional_kwargs={'function_call': {'name': 'Calculator', 'arguments': '{\n "__arg1": "25^0.43"\n}'}})])], 'messages': [AIMessageChunk(content='', additional_kwargs={'function_call': {'name': 'Calculator', 'arguments': '{\n "__arg1": "25^0.43"\n}'}})]} ---- chunk 6 {'messages': [FunctionMessage(content='Answer: 3.991298452658078', name='Calculator')], 'steps': [AgentStep(action=AgentActionMessageLog(tool='Calculator', tool_input='25^0.43', log='\nInvoking: `Calculator` with `25^0.43`\n\n\n', message_log=[AIMessageChunk(content='', additional_kwargs={'function_call': {'name': 'Calculator', 'arguments': '{\n "__arg1": "25^0.43"\n}'}})]), observation='Answer: 3.991298452658078')]} ---- chunk 7 {'messages': [AIMessage(content="Leonardo DiCaprio's current girlfriend is the Italian model Vittoria Ceretti, who is 25 years old. Her age raised to the 0.43 power is approximately 3.99.")], 'output': "Leonardo DiCaprio's current girlfriend is the Italian model " 'Vittoria Ceretti, who is 25 years old. Her age raised to the 0.43 ' 'power is approximately 3.99.'} ---- final {'actions': [AgentActionMessageLog(tool='Search', tool_input="Leo DiCaprio's current girlfriend", log="\nInvoking: `Search` with `Leo DiCaprio's current girlfriend`\n\n\n", message_log=[AIMessageChunk(content='', additional_kwargs={'function_call': {'name': 'Search', 'arguments': '{\n "__arg1": "Leo DiCaprio\'s current girlfriend"\n}'}})]), AgentActionMessageLog(tool='Search', tool_input='Vittoria Ceretti age', log='\nInvoking: `Search` with `Vittoria Ceretti age`\n\n\n', message_log=[AIMessageChunk(content='', additional_kwargs={'function_call': {'name': 'Search', 'arguments': '{\n "__arg1": "Vittoria Ceretti age"\n}'}})]), AgentActionMessageLog(tool='Calculator', tool_input='25^0.43', log='\nInvoking: `Calculator` with `25^0.43`\n\n\n', message_log=[AIMessageChunk(content='', additional_kwargs={'function_call': {'name': 'Calculator', 'arguments': '{\n "__arg1": "25^0.43"\n}'}})])], 'messages': [AIMessageChunk(content='', additional_kwargs={'function_call': {'name': 'Search', 'arguments': '{\n "__arg1": "Leo DiCaprio\'s current girlfriend"\n}'}}), FunctionMessage(content="According to Us, the 48-year-old actor is now “exclusively” dating Italian model Vittoria Ceretti. A source told Us that DiCaprio is “completely smitten” with Ceretti, and their relationship is “going so well that Leo's actually being exclusive.”", name='Search'), AIMessageChunk(content='', additional_kwargs={'function_call': {'name': 'Search', 'arguments': '{\n "__arg1": "Vittoria Ceretti age"\n}'}}), FunctionMessage(content='25 years', name='Search'), AIMessageChunk(content='', additional_kwargs={'function_call': {'name': 'Calculator', 'arguments': '{\n "__arg1": "25^0.43"\n}'}}), FunctionMessage(content='Answer: 3.991298452658078', name='Calculator'), AIMessage(content="Leonardo DiCaprio's current girlfriend is the Italian model Vittoria Ceretti, who is 25 years old. Her age raised to the 0.43 power is approximately 3.99.")], 'output': "Leonardo DiCaprio's current girlfriend is the Italian model " 'Vittoria Ceretti, who is 25 years old. Her age raised to the 0.43 ' 'power is approximately 3.99.', 'steps': [AgentStep(action=AgentActionMessageLog(tool='Search', tool_input="Leo DiCaprio's current girlfriend", log="\nInvoking: `Search` with `Leo DiCaprio's current girlfriend`\n\n\n", message_log=[AIMessageChunk(content='', additional_kwargs={'function_call': {'name': 'Search', 'arguments': '{\n "__arg1": "Leo DiCaprio\'s current girlfriend"\n}'}})]), observation="According to Us, the 48-year-old actor is now “exclusively” dating Italian model Vittoria Ceretti. A source told Us that DiCaprio is “completely smitten” with Ceretti, and their relationship is “going so well that Leo's actually being exclusive.”"), AgentStep(action=AgentActionMessageLog(tool='Search', tool_input='Vittoria Ceretti age', log='\nInvoking: `Search` with `Vittoria Ceretti age`\n\n\n', message_log=[AIMessageChunk(content='', additional_kwargs={'function_call': {'name': 'Search', 'arguments': '{\n "__arg1": "Vittoria Ceretti age"\n}'}})]), observation='25 years'), AgentStep(action=AgentActionMessageLog(tool='Calculator', tool_input='25^0.43', log='\nInvoking: `Calculator` with `25^0.43`\n\n\n', message_log=[AIMessageChunk(content='', additional_kwargs={'function_call': {'name': 'Calculator', 'arguments': '{\n "__arg1": "25^0.43"\n}'}})]), observation='Answer: 3.991298452658078')]} ```	7 months ago
Bagatur	10a6e7cbb6	langchain[patch], core[patch]: Make common utils public (#13932 ) - rename `langchain_core.chat_models.base._generate_from_stream` -> `generate_from_stream` - rename `langchain_core.chat_models.base._agenerate_from_stream` -> `agenerate_from_stream` - export `langchain_core.utils.utils.build_extra_kwargs` from `langchain_core.utils`	7 months ago
Eugene Yurtsev	e186637921	Document Runnable Binding (#13927 ) Document runnable binding	7 months ago
Bagatur	46b3311190	RELEASE: 0.0.341 (#13926 )	7 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	7 months ago
Nuno Campos	8a3e0c9afa	Add option to prefix config keys in configurable_alts (#13714 )	7 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>	7 months ago
Bagatur	7222c42077	RELEASE: core 0.0.6 (#13853 )	7 months ago
Bagatur	58f7e109ac	BUGFIX: Add import types and typevars from core (#13829 )	7 months ago
Bagatur	300ff01824	RELEASE: core 0.0.5 (#13786 )	7 months ago
Bagatur	72c108b003	IMPROVEMENT: filter global warnings properly (#13754 )	8 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	8 months ago
Bagatur	2bc5bd67f7	RELEASE: core 0.0.4 (#13745 )	8 months ago
Bagatur	32d087fcb8	REFACTOR: combine core documents files (#13733 )	8 months ago
Bagatur	16af282429	BUGFIX: add prompt imports for backwards compat (#13702 )	8 months ago
Bagatur	e327bb4ba4	IMPROVEMENT: Conditionally import core type hints (#13700 )	8 months ago
Bagatur	a21e84faf7	BUGFIX: llm backwards compat imports (#13698 )	8 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>	8 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>	8 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	8 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	8 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	8 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>	8 months ago

1 2 3 4 5

241 Commits (a8f530bc4d2692d0e1c3713643522751f85df51c)