langchain

Commit Graph

Author	SHA1	Message	Date
Saurav Kumar	bde199d128	Updating format of pip install (#19198 ) Thank you for contributing to LangChain! - [x] PR title: "Updating format of pip install in two files of docs/cookbook" - pip install is not reflecting properly in some of the files in cookbook - Example: [docs/expression_language/cookbook/sql_db](https://python.langchain.com/docs/expression_language/cookbook/sql_db) - [x] PR message: Updating format of pip install in two files of docs/cookbook - Description: a description of the change - Issue: #19197 - Note - let's do squash merge for the PR If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, hwchase17.	3 months ago
Rohit Gupta	785f8ab174	[langchain_community] milvus vectorstores upsert: add kwargs to make it use for other argument also (#19193 ) add kwargs in add_documents for upsert, to make it use for other argument also. Lets use this, it was unused as of now. - [ ] 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. Co-authored-by: Rohit Gupta <rohit.gupta2@walmart.com>	3 months ago
Cycle	77868b1974	experimental: add buffer_size hyperparameter to SemanticChunker as in source video (#19208 ) add buffer_size hyperparameter which used in combine_sentences function	3 months ago
HowardChan	ae3c7f702c	docs:Make url as a markdown link (#19212 ) Description: same as the title Co-authored-by: ChenZhengHao <chenzhenghao@mail.teletraan.io>	3 months ago
Shotaro Sano	ca9c8c58ea	text-splitters, infra: fix `libs/langchain/dev.Dockerfile` so that the `text-splitter` directory is copied before poetry installation (#19214 ) ## Description This PR modifies the settings in `libs/langchain/dev.Dockerfile` to ensure that the `text-splitters` directory is copied before the poetry installation process begins. Without this modification, the `docker build` command fails for `dev.Dockerfile`, preventing the setup of some development environments, including `.devcontainer`. ## Bug Details ### Repro Run the following command: ```bash docker build -f libs/langchain/dev.Dockerfile . ``` ### Current Behavior The docker build command fails, raising the following error: ``` ... => [langchain-dev-dependencies 4/5] COPY libs/community/ ../community/ 0.4s => ERROR [langchain-dev-dependencies 5/5] RUN poetry install --no-interaction --no-ansi --with dev,test,docs 1.1s ------ > [langchain-dev-dependencies 5/5] RUN poetry install --no-interaction --no-ansi --with dev,test,docs: #13 0.970 #13 0.970 Directory ../text-splitters does not exist ------ executor failed running [/bin/sh -c poetry install --no-interaction --no-ansi --with dev,test,docs]: exit code: 1 ``` ### Expected Behavior The `docker build` command successfully completes without the poetry error. ### Analysis The error occurs because the `text-splitters` directory is not copied into the build environment, unlike the other packages under the `libs` directory. I suspect that the `COPY` setting was overlooked since `text-splitters` was separated in a recent PR. ## Fix Add the following lines to the `libs/langchain/dev.Dockerfile`: ```dockerfile # Copy the text-splitters library for installation COPY libs/text-splitters/ ../text-splitters/ ```	3 months ago
Guangdong Liu	c3310c5e7f	community: Fix Milvus got multiple values for keyword argument 'timeout' (#19232 ) - Description: Fix Milvus got multiple values for keyword argument 'timeout' - Issue: fix #18580 - @baskaryan @eyurtsev PTAL	3 months ago
Erick Friis	95904fe443	langchain[patch]: update base imports to core (#19248 ) still deprecated, but was misleading before	3 months ago
Asaf Joseph Gardin	21c45475c5	ai21[patch]: AI21 Labs bump SDK version (#19114 ) Description: Added support AI21 SDK version 2.1.2 Twitter handle: https://github.com/AI21Labs --------- Co-authored-by: Asaf Gardin <asafg@ai21.com> Co-authored-by: Erick Friis <erick@langchain.dev>	3 months ago
daniel ung	edf9d1c905	templates: Added template for JaguarDB (#16757 ) - Description:: added langchain template for JaguarDB --------- Co-authored-by: Erick Friis <erick@langchain.dev>	3 months ago
gustavo-yt	7c26ef88a1	templates: Add rag lantern template (#16523 ) Replace this entire comment with: - Description: Added a template for lantern rag usage. --------- Co-authored-by: Erick Friis <erick@langchain.dev>	3 months ago
Jib	516cc44b3f	langchain-mongodb: [test-fix] add explicit index_name setting on test vector creation (#19245 ) - Description: Tests fail to do value lookup because it does not specify the index name - Issue: the issue # Failing integration test - [x] Add tests and docs: Tests now pass - [x] 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/	3 months ago
Estephania Calvo Carvajal	94e58dd827	docs:Fix links to LangSmith docs on Evaluation page (#19210 ) (#19216 ) - Description: Same as the title - Issue: #19210	3 months ago
William FH	780337488e	[Enhancement] Add support for directly providing a run_id (#18990 ) The root run id (~trace id's) is useful for assigning feedback, but the current recommended approach is to use callbacks to retrieve it, which has some drawbacks: 1. Doesn't work for streaming until after the first event 2. Doesn't let you call other endpoints with the same trace ID in parallel (since you have to wait until the call is completed/started to use This PR lets you provide = "run_id" in the runnable config. Couple considerations: 1. For batch calls, we split the trace up into separate trees (to permit better rendering). We keep the provided run ID for the first one and generate a unique one for other elements of the batch. 2. For nested calls, the provided ID is ONLY used on the top root/trace. ### Example Usage ``` chain.invoke("foo", {"run_id": uuid.uuid4()}) ```	3 months ago
Jacob Lee	bd329e9aad	core[patch]: Add LLM output to message response_metadata (#19158 ) This will more easily expose token usage information. CC @baskaryan --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	3 months ago
Erick Friis	6fa1438334	mongodb[patch]: release 0.1.2 (#19243 )	3 months ago
Leonid Ganeline	7de1d9acfd	community: `llms` imports fixes (#18943 ) Classes are missed in __all__ and in different places of __init__.py - BaichuanLLM - ChatDatabricks - ChatMlflow - Llamafile - Mlflow - Together Added classes to __all__. I also sorted __all__ list. --------- Co-authored-by: Erick Friis <erick@langchain.dev>	3 months ago
Anush	aee5138930	templates: update qdrant self query (#19218 ) ## Description This PR - Updates the Qdrant self-query template to reflect the recent updates. - Enables reading config values from `env` files as the README [mentions it](https://github.com/Anush008/langchain/tree/self-query-qdrant/templates/self-query-qdrant#environment-setup). Co-authored-by: Erick Friis <erick@langchain.dev>	3 months ago
Kenzie Mihardja	21f75991d4	deprecate community docugami loader (#19230 ) Thank you for contributing to LangChain! - [x] PR title: "community: deprecate DocugamiLoader" - [x] PR message: Deprecate the langchain_community and use the docugami_langchain DocugamiLoader --------- Co-authored-by: Kenzie Mihardja <kenzie28@cs.washington.edu>	3 months ago
Jib	ec026004cb	mongodb[patch]: Remove in-memory cache from cache abstractions (#18987 ) ## Description * In memory cache easily gets out of sync with the server cache, so we will remove it entirely to reduce the issues around invalidated caches. ## Dependencies None - [x] 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. - [x] 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/ Co-authored-by: Erick Friis <erick@langchain.dev>	3 months ago
Jib	866d6408af	mongodb[patch]: Remove embedding retrieval from mongodb payload (#19035 ) ## Description Returning the embedding is not necessary in the vector search functionality unless specified as a debugging step. This change defaults the behavior such that the server _only_ returns the embedding key if explicitly requested, such as in the case of `max_marginal_relevance_search`. - [x] Add tests and docs: If you're adding a new integration, please include * Added `test_from_documents_no_embedding_return` - [x] 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/ --------- Co-authored-by: Erick Friis <erick@langchain.dev>	3 months ago
Leonid Kuligin	366ba77459	core[minor]: moved fake llms and embeddings to core (#19226 ) - [ ] PR title: "core: moved fake llms and embeddings to core" - [ ] PR message: - Description: moved fake llms and embeddings to core"	3 months ago
Pengfei Jiang	514fe80778	community[patch]: add stop parameter support to volcengine maas (#19052 ) - Description: add stop parameter to volcengine maas model - Dependencies: no --------- Co-authored-by: 江鹏飞 <jiangpengfei.jiangpf@bytedance.com>	3 months ago
htaoruan	bcc771e37c	docs: ChatTongyi example error (#19013 )	3 months ago
Anubhav Madhav	9235dade90	docs: provided hyperlinks to text and fixed grammar (#19092 ) 1) Provided links to text in the prompt (Refer Page Link 1, Page Link 2 and Page Link 3) 2) Fixed Grammar in Considerations of Model I/O Concepts documentation page - Update concepts.mdx (Page Link 4) Issues are on the following pages: Page Link 1: https://python.langchain.com/docs/modules/model_io/concepts#prompttemplate Page Link 2: https://python.langchain.com/docs/modules/model_io/concepts#messageprompttemplate Page Link 3: https://python.langchain.com/docs/modules/model_io/concepts#chatprompttemplate Page Link 4: https://python.langchain.com/docs/modules/model_io/concepts#considerations Fix 1: Description: Fixed Grammar in Considerations of Model I/O Documentation Page Issue: "to work well with the model are you using" # "to work well with the model you are using" Dependencies: None Twitter handle: @Anubhav_Madhav (https://twitter.com/Anubhav_Madhav) Fix 2: Description: Provided links to text in the prompt (Refer Page Link 1, Page Link 2 and Page Link 3) Issue: links not provided # links have been provided to the text Dependencies: None Twitter handle: @Anubhav_Madhav (https://twitter.com/Anubhav_Madhav) baskaryan, efriis, eyurtsev, hwchase17. For Fix 1 Refer to the first word 'This" word in the image attached with this PR. PFA <img width="839" alt="Screenshot 2024-03-15 at 3 04 17 AM" src="https://github.com/langchain-ai/langchain/assets/42323737/94e8db16-249f-48c3-a1d1-dee8d36067fa"> If no one reviews your PR within a few days, please @-mention one of --------- Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	3 months ago
primate88	5aa68936e0	community: Fix import path for StreamingStdOutCallbackHandler example (#19170 ) - Description: - Updated the import path for `StreamingStdOutCallbackHandler` in the streaming response example within `huggingface_endpoint.py`. This change corrects the import statement to reflect the actual location of `StreamingStdOutCallbackHandler` in `langchain_core.callbacks.streaming_stdout`. - Issue: - None - Dependencies: - No additional dependencies are required for this change. - Twitter handle: - None ## Note: I have tested this change locally and confirmed that the `StreamingStdOutCallbackHandler` works as expected with the updated import path. This PR does not require the addition of new tests since it is a correction to documentation/examples rather than functional code.	3 months ago
Bagatur	611d5a1618	openai[patch]: fix async http client (#19164 ) Fix #19116	3 months ago
Nikhil Kumar	635b3372bd	community[minor]: Add support for translation in HuggingFacePipeline (#19190 ) - [x] Support for translation: "community: Add support for translation in `HuggingFacePipeline`" - [x] Add support for translation in `HuggingFacePipeline`: - Description: Add support for translation in `HuggingFacePipeline`, which earlier used to support only text summarization and generation. - Issue: N/A - Dependencies: N/A - Twitter handle: None	3 months ago
Nikhil Kumar	a1b26dd9b6	docs: Add docs for RouterRunnable (#19191 ) - [x] Docs for `RouterRunnable`: core: Add docs for `RouterRunnable` - [x] Add docs for `RouterRunnable`: - Description: Add docs for `RouterRunnable`, which was previously missing documentation - Issue: #18803 - Dependencies: N/A - Twitter handle: None	3 months ago
k.muto	8d2c34e655	community: Fix all page numbers were the same for _BaseGoogleVertexAISearchRetriever (#19175 ) - Description: - This pull request is to fix a bug where page numbers were not set correctly. In the current code, all chunks share the same metadata object doc_metadata, so the page number is set with the same value for all documents. To fix this, I changed to using separate metadata objects for each chunk. - Issue: - None - Dependencies: - No additional dependencies are required for this change. - Twitter handle: - @eycjur - Test - Even if it's not a bug, there are cases where everything ends up with the same number of pages, so it's very difficult for me to write integration tests.	3 months ago
Matt Frediani	160a7077b0	Update README.md (#19172 ) 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.	3 months ago
inpyeong	7c092f479f	docs: Update why.ipynb (#19173 ) I think that cell type for pip command may be 'code'. Please check, thank you :) If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, hwchase17.	3 months ago
Vitalii Korsakov	d96e0b2de7	docs: Remove duplicated line in Get Started section (#19182 ) Line `from langchain_openai import ChatOpenAI` is put twice in Get Started / Serving with LangServe section. Imports on lines 559 and 566 are identical Co-authored-by: Vitalii <vitalii@localhost>	3 months ago
Cailin Wang	7cd87d2f6a	community: Add `partition` parameter to DashVector (#19023 ) Description: DashVector Add partition parameter Twitter handle: @CailinWang_ --------- Co-authored-by: root <root@Bluedot-AI>	3 months ago
Rodrigo Nogueira	e64cf1aba4	community: Add model argument for maritalk models and better error handling (#19187 )	3 months ago
samanhappy	ff94f86ce1	docs: fix link to interface TextSplitter (#19177 )	3 months ago
Sergey Kozlov	1a55e950aa	community[patch]: support fastembed v1 and v2 (#19125 ) Description: #18040 forces `fastembed>2.0`, and this causes dependency conflicts with the new `unstructured` package (different `onnxruntime`). There may be other dependency conflicts.. The only way to use `langchain-community>=0.0.28` is rollback to `unstructured 0.10.X`. But new `unstructured` contains many fixes. This PR allows to use both `fastembed` `v1` and `v2`. How to reproduce: `pyproject.toml`: ```toml [tool.poetry] name = "depstest" version = "0.0.0" description = "test" authors = ["<dev@example.org>"] [tool.poetry.dependencies] python = ">=3.10,<3.12" langchain-community = "^0.0.28" fastembed = "^0.2.0" unstructured = {extras = ["pdf"], version = "^0.12"} ``` ```bash $ poetry lock ``` Co-authored-by: Sergey Kozlov <sergey.kozlov@ludditelabs.io>	3 months ago
six17	fd4f536c77	text-splitters[patch]: fix json split of RecursiveJsonSplitter (#19119 ) - Description: This modification addresses the issue of mutable default parameters in functions. In the original code, the `chunks` parameter is defaulted to a list containing an empty dictionary, which is mutable. Since default parameters in Python are evaluated only once at function definition time, modifications to the parameter would persist across future calls. By changing the default to `None` and checking/initializing within the function, a new list is created for each call, thus avoiding potential issues. --------- Co-authored-by: sixiang <sixiang@lixiang.com> Co-authored-by: Bagatur <baskaryan@gmail.com>	3 months ago
aditya thomas	05008c4f94	docs: update stale links in Together AI documentation (#19011 ) Description: Update stales link in Together AI documentation Issue: Some links pointed to legacy webpages on the Together AI website Dependencies: None Lint and test: `make format`, `make lint` were run	3 months ago
aditya thomas	80eb510a7b	docs: update docstring of Together class (#19008 ) Description: Update docstring of Together class to show example and update API URL Issue: Improves usability Dependencies: None Lint and test: `make format`, `make lint` and `make test` were run	3 months ago
高远	ef9813dae6	docs: add vikingdb docstrings(#19016 ) Co-authored-by: gaoyuan <gaoyuan.20001218@bytedance.com>	3 months ago
wulixuan	0e0030f494	community[patch]: fix yuan2 chat model errors while invoke. (#19015 ) 1. fix yuan2 chat model errors while invoke. 2. update related tests. 3. fix some deprecationWarning.	3 months ago
Shuai Liu	c244e1a50b	community[patch]: Fixed bug in merging `generation_info` during chunk concatenation in Tongyi and ChatTongyi (#19014 ) - Description: In #16218 , during the `GenerationChunk` and `ChatGenerationChunk` concatenation, the `generation_info` merging changed from simple keys & values replacement to using the util method [`merge_dicts`](https://github.com/langchain-ai/langchain/blob/master/libs/core/langchain_core/utils/_merge.py): ![image](https://github.com/langchain-ai/langchain/assets/2098020/10f315bf-7fe0-43a7-a0ce-6a3834b99a15) The `merge_dicts` method could not handle merging values of `int` or some other types, and would raise a [`TypeError`](https://github.com/langchain-ai/langchain/blob/master/libs/core/langchain_core/utils/_merge.py#L55). This PR fixes this issue in the Tongyi and ChatTongyi Model by adopting the `generation_info` of the last chunk and discarding the `generation_info` of the intermediate chunks, ensuring that `stream` and `astream` function correctly. - Issue: - Related issues or PRs about Tongyi & ChatTongyi: #16605, #17105 - Other models or cases: #18441, #17376 - Dependencies: No new dependencies	3 months ago
wulixuan	f79d0cb9fb	docs: update docs for yuan2 in LLMs and Chat models integration. (#19028 ) update yuan2.0 notebook in LLMs and Chat models. --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	3 months ago
Taraka Nithin Vankala	eec023766e	docs: Corrected error (#19030 ) - [ ] PR title: "docs: correction in "https://github.com/langchain-ai/langchain/blob/master/docs/docs/get_started/quickstart.mdx", line 289". - 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: - Corrected the spelling mistake - #18981	3 months ago
Christophe Bornet	f2a7dda4bd	community[patch]: Use langchain-astradb for AstraDB doc loader (#19071 ) Co-authored-by: Bagatur <baskaryan@gmail.com> Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	3 months ago
Leonid Ganeline	a49ac55964	docs: `providers` update 8 (#19053 ) Added missed providers. Added missed integrations. Fixed format.	3 months ago
Holt Skinner	cee03630d9	community[patch]: Add Blended Search Support to `GoogleVertexAISearchRetriever` (#19082 ) https://cloud.google.com/generative-ai-app-builder/docs/create-data-store-es#multi-data-stores --------- Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	3 months ago
Eugene Yurtsev	0ddfe7fc9d	langchain[patch]: make hub work with older langchainhub versions (#19076 ) Make it work with older clients	3 months ago
William W Wang	0a784074d1	docs: Update llm_caching.ipynb (#19085 )	3 months ago
William W Wang	6327be9048	docsUpdate azure_cosmos_db.ipynb (#19087 ) Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	3 months ago

... 3 4 5 6 7 ...

8382 Commits (5b1f9c6d3a095b1b11abd6fc9a94424fda4c07c7) All Branches Search

8382 Commits (5b1f9c6d3a095b1b11abd6fc9a94424fda4c07c7)

All Branches