langchain

Commit Graph

Author	SHA1	Message	Date
Wickes Wong	ee1adaacaa	langchain[patch]: Fix summary buffer memory with return message flag (#21115 ) ## Description Memory return could be set as `str` or `message` by `return_messages` flag as mentioned in https://python.langchain.com/docs/modules/memory/#whether-memory-is-a-string-or-a-list-of-messages, where `langchain.chains.conversation.memory.ConversationSummaryBufferMemory` did not implement that. This commit added `buffer_as_str` and `buffer_as_messages` function, and `buffer` now affected by `return_messages` flag. ## Example Test Code and Output ```python # Fix: ConversationSummaryBufferMemory with return_messages flag function # Test code from langchain.chains.conversation.memory import ConversationSummaryBufferMemory from langchain_community.llms.ollama import Ollama llm = Ollama() # Create an instance of ConversationSummaryBufferMemory with return_messages set to True memory = ConversationSummaryBufferMemory(return_messages=True, llm=llm) # Add user and AI messages to the chat memory memory.chat_memory.add_user_message("hi!") memory.chat_memory.add_ai_message("what's up?") # Print the buffer print("Buffer:") print(map(type, memory.buffer), sep="\n") print(memory.buffer, "\n") # Print the buffer as a string print("Buffer as String:") print(type(memory.buffer_as_str)) print(memory.buffer_as_str, "\n") # Print the buffer as messages print("Buffer as Messages:") print(map(type, memory.buffer_as_messages), sep="\n") print(memory.buffer_as_messages, "\n") # Print the buffer after setting return_messages to False memory.return_messages = False print("Buffer after setting return_messages to False:") print(type(memory.buffer)) print(memory.buffer, "\n") ``` ```plaintext Buffer: <class 'langchain_core.messages.human.HumanMessage'> <class 'langchain_core.messages.ai.AIMessage'> [HumanMessage(content='hi!'), AIMessage(content="what's up?")] Buffer as String: <class 'str'> Human: hi! AI: what's up? Buffer as Messages: <class 'langchain_core.messages.human.HumanMessage'> <class 'langchain_core.messages.ai.AIMessage'> [HumanMessage(content='hi!'), AIMessage(content="what's up?")] Buffer after setting return_messages to False: <class 'str'> Human: hi! AI: what's up? ``` --------- Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	2 weeks ago
Leonid Ganeline	9639457222	community[patch]: `tools` imports (#21156 ) Issue: we have several helper functions to import third-party libraries like tools.gmail.utils.import_google in [community.tools](https://api.python.langchain.com/en/latest/community_api_reference.html#id37). And we have core.utils.utils.guard_import that works exactly for this purpose. The import_<package> functions work inconsistently and rather be private functions. Change: replaced these functions with the guard_import function. Related to #21133	2 weeks ago
Leonid Ganeline	3ef8b24277	core[patch]: `utils.guard_import` fix (#21133 ) Issues (nit): 1. `utils.guard_import` prints wrong error message when there is an import `error.` It prints the whole `module_name` but should be only the first part as the pip package name. E.i. `langchain_core.utils` -> print not `langchain-core` but `langchain_core.utils`. Also replace '_' with '-' in the pip package name. 2. it does not handle the `ModuleNotFoundError` which raised if `guard_import("wrong_module")` Fixed issues; added ut-s. Controversial: I've reraised `ModuleNotFoundError` as `ImportError`, since in case of the error, the proposed action is the same - we need to install a missed package.	2 weeks ago
Erick Friis	36c2ca3c8b	mistralai: relax tokenizers dep (#21277 )	2 weeks ago
Nuno Campos	6e1e0c7d5c	fix: core: draw_mermaid() would create subgroup for edges with same src and tgt (#21275 ) Thank you for contributing to LangChain! - [ ] PR title: "package: description" - Where "package" is whichever of langchain, community, core, experimental, etc. is being modified. Use "docs: ..." for purely docs changes, "templates: ..." for template changes, "infra: ..." for CI changes. - Example: "community: add foobar LLM" - [ ] PR message: *Delete this entire checklist* and replace with - Description: a description of the change - Issue: the issue # it fixes, if applicable - Dependencies: any dependencies required for this change - Twitter handle: if your PR gets announced, and you'd like a mention, we'll gladly shout you out! - [ ] Add tests and docs: 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. - [ ] Lint and test: Run `make format`, `make lint` and `make test` from the root of the package(s) you've modified. See contribution guidelines for more: https://python.langchain.com/docs/contributing/ Additional guidelines: - Make sure optional dependencies are imported within a function. - Please do not add dependencies to pyproject.toml files (even optional ones) unless they are required for unit tests. - Most PRs should not touch more than one package. - Changes should be backwards compatible. - If you are adding something to community, do not re-import it in langchain. If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, hwchase17.	2 weeks ago
Eugene Yurtsev	26a37dce0a	langchain[patch]: Remove jsonpatch from poetry file (#21272 ) jsonpatch is only used in langchain-core not in langchain	2 weeks ago
Eugene Yurtsev	335bd01e45	langchain[patch]: Update deprecation warning (#21268 ) Update deprecation warning	2 weeks ago
Leonid Ganeline	23a05c3986	langchain: `summarize` chain fix (#21266 ) Issue: `load_summarize_chain` is placed in the __init__.py file. As a result, it doesn't listed in the API Reference docs. Change: moved code from __init__.py into a new file.	2 weeks ago
ccurme	6da3d92b42	(all): update removal in deprecation warnings from 0.2 to 0.3 (#21265 ) We are pushing out the removal of these to 0.3. `find . -type f -name "*.py" -exec sed -i '' 's/removal="0\.2/removal="0.3/g' {} +`	2 weeks ago
Eugene Yurtsev	d6e34f9ee5	langchain[patch]: Improve deprecation warnings (#21262 ) * Remove spurious derprecation warning * Make deprecation warnings consistent with 0.1 namespaces that were announced as deprecated	2 weeks ago
Eugene Yurtsev	487aff7e46	langchain[patch]: Revert 20794 until 0.2 release (#21257 ) PR of 2079 was already released as part of 0.1.17rc. Issue for 0.2 release: https://github.com/langchain-ai/langchain/issues/21080	2 weeks ago
Eugene Yurtsev	ba4a309d98	langchain[patch]: Revert breaking change until 0.2 release (#21256 ) Reverts a minor breaking change until 0.2 release	2 weeks ago
Eugene Yurtsev	66a1e3f083	langchain[patch]: Fix flaky unit test (#21258 ) Should sort the results of the import test since it depends on import order	2 weeks ago
Eugene Yurtsev	0989c48028	langchain[minor]: Re-add deleted ainetwork tool (#21254 ) * Adding __init__.py to turn it into a package in community * Adding proxy imports that assume that langchain_community is optional	2 weeks ago
Christophe Bornet	2fbe82f5e6	community[minor]: Relax constraints on CassandraChatMessageHistory constructor (#21241 )	2 weeks ago
Chris Germann	3a8d1d8838	Hotfix RetrievalQA Docs: docs: Fix formatting (#21183 ) # Newline Characters breaking formatting Description: As you can see in the image below, the formatting in the documentation is broken. As far as I can see the two added `\n` characters are breaking the documentation. Therefore I would propose to remove those ![image](https://github.com/langchain-ai/langchain/assets/88305668/23b6e726-71b2-4812-91ea-3e8600683733) Dependencies: None Twitter Handle - epu9byj --------- Co-authored-by: gere <gere@kapo.zh.ch> Co-authored-by: Chester Curme <chester.curme@gmail.com>	2 weeks ago
andyjessen	64e17bd793	docs: Fix comment within "handle long text" example (#21248 ) The current doc-string comment is referring to the wrong schema.	2 weeks ago
Daniel Glogowski	c3d169ab00	docs: Update Nvidia documentation (#21240 ) Updating Nvidia docs ahead for 5/15 competition. Thanks!	2 weeks ago
Bagatur	70bde15480	docs: add tool choice to tool calling (#21229 )	2 weeks ago
Bagatur	67a5cc34c6	openai[patch]: Release 0.1.6 (#21236 )	2 weeks ago
Erick Friis	c1eb95b967	core: release 0.1.50 (#21230 )	2 weeks ago
Nuno Campos	47ce8d5a57	core: tracer: remove numeric execution order (#21220 ) - this hasn't been used in a long time and requires some additional bookkeeping i'm going to streamline in the next pr	2 weeks ago
Bagatur	6ac6158a07	openai[patch]: support tool_choice="required" (#21216 ) Co-authored-by: ccurme <chester.curme@gmail.com>	2 weeks ago
Erick Friis	aa9faa8512	docs: model table keywords, remove tool calling from llm (#21225 )	2 weeks ago
xindoo	c1aa237bc2	langchain: fix syntax error in code comment for create_tool_calling_agent (#21205 ) PR message: - Description: Corrected a syntax error in the code comments within the `create_tool_calling_agent` function in the langchain package. - Issue: N/A - Dependencies: No additional dependencies required. - Twitter handle: N/A	2 weeks ago
ccurme	eb0a2fd53a	mistral: release 0.1.6 (#21214 )	2 weeks ago
ccurme	2d77e5e3a1	(standard tests): add test for basic conversation sequence (#21213 )	2 weeks ago
Maxime Perrin	1ebb5a70ad	partners(mistralai): Removing unused variable in completion request (using tool_calls or content) (#21201 ) This PR fixes #21196. The error was occurring when calling chat completion API with a chat history. Indeed, the Mistral API does not accept both `content` and `tool_calls` in the same body. This PR removes one of theses variables depending on the necessity. --------- Co-authored-by: Maxime Perrin <mperrin@doing.fr> Co-authored-by: Chester Curme <chester.curme@gmail.com>	2 weeks ago
Christophe Bornet	683fb45c6b	community[patch]: Refactor CassandraDatabase wrapper (#21075 ) * Introduce individual `fetch_` methods for easier typing. * Rework some docstrings to google style * Move some logic to the tool * Merge the 2 cassandra utility files	2 weeks ago
Bagatur	b00fd1dbde	infra: Undo gh cache removal (#21210 ) Co-authored-by: Nuno Campos <nuno@langchain.dev>	2 weeks ago
Aditya	ee2c55ca09	docs: Added documentation on Anthropic models on vertex (#21070 ) Description:Added documentation on Anthropic models on Vertex @lkuligin for review --------- Co-authored-by: adityarane@google.com <adityarane@google.com>	2 weeks ago
Raghav Dixit	7d451d0041	community[patch]: Update lancedb.py (#21192 ) very minor update in LanceDB integration, 'metric' argument was missing.	2 weeks ago
Bagatur	d297d90ad9	core[patch]: Release 0.1.49 (#21211 )	2 weeks ago
Nuno Campos	663747b730	core[patch]: Fixes for convert_messages (#21207 ) - support two-tuples of any sequence type (eg. json.loads never produces tuples) - support type alias for role key - if id is passed in in dict form use it - if tool_calls passed in in dict form use them --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	2 weeks ago
Eugene Yurtsev	df49404794	langchain[patch]: Make more memory code handle community dependency as optional (#21199 )	2 weeks ago
ccurme	bd5d2c2674	langchain: import InMemoryChatMessageHistory from core (#21198 )	2 weeks ago
Eugene Yurtsev	3cd7fced5f	langchain[patch],community[minor]: Migrate memory implementations to community (#20845 ) Migrates memory implementations to community	2 weeks ago
Eugene Yurtsev	b5c3a04e4b	langchain[patch]: chat histories to handle optional community dependence (#21194 )	2 weeks ago
Eugene Yurtsev	c9119b0e75	langchain[patch],community[minor]: Move some unit tests from langchain to community, use core for fake models (#21190 )	2 weeks ago
Eugene Yurtsev	c306364b06	langchain[patch]: Update more code to use langchain community as an optional dependency (#21170 ) More code to use langchain community as an optional dependency	2 weeks ago
Erick Friis	cd4c54282a	infra: cleanup docs build (#21134 ) Refactors the docs build in order to: - run the same `make build` command in both vercel and local build - incrementally build artifacts in 2 distinct steps, instead of building all docs in-place (in vercel) or in a _dist dir (locally) Highlights: - introduces `make build` in order to build the docs - collects and generates all files for the build in `docs/build/intermediate` - renders those jupyter notebook + markdown files into `docs/build/outputs` And now the outputs to host are in `docs/build/outputs`, which will need a vercel settings change. Todo: - [ ] figure out how to point the right directory (right now deleting and moving docs dir in vercel_build.sh isn't great)	2 weeks ago
Bagatur	6fa8626e2f	openai[patch]: fix azure open lc serialization, release 0.1.5 (#21159 )	2 weeks ago
Eugene Yurtsev	94a838740e	langchain[patch]: Migrate more code in utils to use optional langchain import (#21166 ) Moving is interactive util to avoid circular deps	2 weeks ago
Eugene Yurtsev	23fdd320bc	langchain[patch]: Migrate more code to use optional community in agents namespace (#21167 )	2 weeks ago
Tomaz Bratanic	9e53fa7d2e	Some more fixes to neo4j enhanced schema (#21139 )	2 weeks ago
Erick Friis	0694538c39	ai21: fix core version (#21168 )	2 weeks ago
Eugene Yurtsev	44602bdc20	langchain[patch],community[minor]: Move load_tools to community (#21158 ) Move load tools to community	2 weeks ago
Eugene Yurtsev	9932f49b3e	langchain[patch]: Migrate llms to use optional community imports (#21101 )	2 weeks ago
Eugene Yurtsev	57e8e70daa	langchain[patch]: Migrate chat models to optional community imports (#21090 ) Migrate chat models to optional community imports	2 weeks ago
Eugene Yurtsev	2914abd747	langchain[patch]: Fix how the serializable test identifies serializable objects (#21165 ) dir() will not work if we're using optional imports. The only way to do this is by using contents of __all__	2 weeks ago

... 2 3 4 5 6 ...

9294 Commits (master) All Branches Search

9294 Commits (master)

All Branches