Commit Graph

9215 Commits (aa966b616111081c17b1285c6f074e79b380d615)
 

Author SHA1 Message Date
Shailendra Mishra aa966b6161
Replaced bind variable in SQL with formatted string for compatibility with sql syntax. (#21439)
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 months ago
Eugene Yurtsev f92006de3c
multiple: langchain 0.2 in master (#21191)
0.2rc 

migrations

- [x] Move memory
- [x] Move remaining retrievers
- [x] graph_qa chains
- [x] some dependency from evaluation code potentially on math utils
- [x] Move openapi chain from `langchain.chains.api.openapi` to
`langchain_community.chains.openapi`
- [x] Migrate `langchain.chains.ernie_functions` to
`langchain_community.chains.ernie_functions`
- [x] migrate `langchain/chains/llm_requests.py` to
`langchain_community.chains.llm_requests`
- [x] Moving `langchain_community.cross_enoders.base:BaseCrossEncoder`
->
`langchain_community.retrievers.document_compressors.cross_encoder:BaseCrossEncoder`
(namespace not ideal, but it needs to be moved to `langchain` to avoid
circular deps)
- [x] unit tests langchain -- add pytest.mark.community to some unit
tests that will stay in langchain
- [x] unit tests community -- move unit tests that depend on community
to community
- [x] mv integration tests that depend on community to community
- [x] mypy checks

Other todo

- [x] Make deprecation warnings not noisy (need to use warn deprecated
and check that things are implemented properly)
- [x] Update deprecation messages with timeline for code removal (likely
we actually won't be removing things until 0.4 release) -- will give
people more time to transition their code.
- [ ] Add information to deprecation warning to show users how to
migrate their code base using langchain-cli
- [ ] Remove any unnecessary requirements in langchain (e.g., is
SQLALchemy required?)

---------

Co-authored-by: Erick Friis <erick@langchain.dev>
2 months ago
ccurme 6b392d6d12
robocorp: release 0.0.6 (#21441) 2 months ago
Erick Friis 21d14549a9
docs: v0.2 docs in master (#21438)
current python.langchain.com is building from branch `v0.1`. Iterate on
v0.2 docs here.

---------

Signed-off-by: Weichen Xu <weichen.xu@databricks.com>
Signed-off-by: Rahul Tripathi <rauhl.psit.ec@gmail.com>
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Co-authored-by: jacoblee93 <jacoblee93@gmail.com>
Co-authored-by: Leonid Ganeline <leo.gan.57@gmail.com>
Co-authored-by: Leonid Kuligin <lkuligin@yandex.ru>
Co-authored-by: Averi Kitsch <akitsch@google.com>
Co-authored-by: Nuno Campos <nuno@langchain.dev>
Co-authored-by: Nuno Campos <nuno@boringbits.io>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
Co-authored-by: Martín Gotelli Ferenaz <martingotelliferenaz@gmail.com>
Co-authored-by: Fayfox <admin@fayfox.com>
Co-authored-by: Eugene Yurtsev <eugene@langchain.dev>
Co-authored-by: Dawson Bauer <105886620+djbauer2@users.noreply.github.com>
Co-authored-by: Ravindu Somawansa <ravindu.somawansa@gmail.com>
Co-authored-by: Dhruv Chawla <43818888+Dominastorm@users.noreply.github.com>
Co-authored-by: ccurme <chester.curme@gmail.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
Co-authored-by: WeichenXu <weichen.xu@databricks.com>
Co-authored-by: Benito Geordie <89472452+benitoThree@users.noreply.github.com>
Co-authored-by: kartikTAI <129414343+kartikTAI@users.noreply.github.com>
Co-authored-by: Kartik Sarangmath <kartik@thirdai.com>
Co-authored-by: Sevin F. Varoglu <sfvaroglu@octoml.ai>
Co-authored-by: MacanPN <martin.triska@gmail.com>
Co-authored-by: Prashanth Rao <35005448+prrao87@users.noreply.github.com>
Co-authored-by: Hyeongchan Kim <kozistr@gmail.com>
Co-authored-by: sdan <git@sdan.io>
Co-authored-by: Guangdong Liu <liugddx@gmail.com>
Co-authored-by: Rahul Triptahi <rahul.psit.ec@gmail.com>
Co-authored-by: Rahul Tripathi <rauhl.psit.ec@gmail.com>
Co-authored-by: pjb157 <84070455+pjb157@users.noreply.github.com>
Co-authored-by: Eun Hye Kim <ehkim1440@gmail.com>
Co-authored-by: kaijietti <43436010+kaijietti@users.noreply.github.com>
Co-authored-by: Pengcheng Liu <pcliu.fd@gmail.com>
Co-authored-by: Tomer Cagan <tomer@tomercagan.com>
Co-authored-by: Christophe Bornet <cbornet@hotmail.com>
2 months ago
Tommi Holmgren ee35b9ba56
langchain-robocorp: remove toolkit return content max length (#21436)
Robocorp (action server) toolkit had a limitation that the content
length returned by the tool was always cut to max 5000 chars. This was
from the time when context windows were much more limited.

This PR removes the limitation. Whatever the underlying tool provides
gets sent back to the agent.

As the robocorp toolkit no longer restricts the content, the implication
is that either the Action (tool) developer or the agent developer needs
to be aware of potentially oversized tool responses. Our point of view
is this should be the agent developer's responsibility, them being in
control of the use case and aware of the context window the LLM has.
2 months ago
JuHyung Son 710e57d779
upstage: deprecate UPSTAGE_DOCUMENT_AI_API_KEY (#21363)
Description: We are merging UPSTAGE_DOCUMENT_AI_API_KEY and
UPSTAGE_API_KEY into one, and only UPSTAGE_API_KEY will be used going
forward. And we changed the base class of ChatUpstage to BaseChatOpenAI.

---------

Co-authored-by: Sean <chosh0615@gmail.com>
Co-authored-by: Erick Friis <erick@langchain.dev>
2 months ago
Erick Friis 6a295d1ec0
upstage: release 0.1.4 (#21432) 2 months ago
Mateusz Szewczyk 7926cc1929
ibm: Fix llm and embeddings "verify" attribute default value (#21429)
Thank you for contributing to LangChain!

- [x] **PR title**: "langchain-ibm: Fix llm and embeddings 'verify'
attribute default value"


- [x] **PR message**: 
    - **Description:** fix default value of "verify" attribute
    - **Dependencies:** `ibm_watsonx_ai`


- [x] **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.


- [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>
2 months ago
Kevin Zhang 0715545378
docs: fix typo in text (#21393)
**Description:** The previous text had an unclosed parenthesis, this fix
adds the closing parenthesis
2 months ago
Dobiichi-Origami 5b00885b49
community: add `bind_tools` and `with_structured_output` support to `QianfanChatEndpoint` (#21412)
…Endpoint`

Thank you for contributing to LangChain!

- [x] **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"


- [x] **PR message**: ***Delete this entire checklist*** and replace
with
- **Description:** add `bind_tools` and `with_structured_output` support
to `QianfanChatEndpoint`


- [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/
2 months ago
Silas Xu aafaf3e193
The predict_and_parse is deprecated, instead pass an output parser directly to LLMChain. (#20130)
The `predict_and_parse` method is deprecated, instead pass an output
parser directly to LLMChain.

- [x] **PR title**: "langchain: update chain_extract.py"


![image](https://github.com/langchain-ai/langchain/assets/40889019/e950d79f-5a0f-4086-86e9-89f627990fe5)

---------

Co-authored-by: Chester Curme <chester.curme@gmail.com>
2 months ago
ccurme 3c31bd0ed0
langchain: update use of predict_and_parse in LLMChainFilter (#21389)
Following https://github.com/langchain-ai/langchain/pull/20130

Removes deprecation warnings in docs here:
https://python.langchain.com/docs/modules/data_connection/retrievers/contextual_compression/

Tested using the same docs notebook + existing integration test.
2 months ago
Tomaz Bratanic dd70f2f473
Update graph docs (#21414)
Update the deprecated docs and added node properties to graph
construction
2 months ago
Erick Friis bbdf0f8801
experimental[patch]: core and langchain dep (#21402) 2 months ago
Erick Friis e4aca0d052
experimental[patch]: release 0.0.58 (#21397) 2 months ago
Erick Friis 893f06b5de
infra: rewrite ipynb links to md (#21392) 2 months ago
Hassan El Mghari 225ceedcb6
docs: Add together docs in chat models & update provider docs (#21391)
- Added Together docs in chat models section
- Update Together provider docs to match the LLM & chat models sections

---------

Co-authored-by: Erick Friis <erick@langchain.dev>
2 months ago
Heidi Steen af97d58c9e
docs: update docs/integrations/retrievers/azure_ai_search.ipynb (#21160)
This is a doc update. It fixes up formatting and product name
references. The example code is updated to use a local built-in text
file.

@mmhangami Please take a look

---------

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2 months ago
snova-jamesv ca753e7c15
community: updated performance limitation wording in sambanova.ipynb (#21390)
- **Description:** updated performance limitation wording in
sambanova.ipynb
    - **Issue:** NA
    - **Dependencies:** NA
    - **Twitter handle:** NA
2 months ago
Leonid Ganeline 791d59a2c8
community: `callbacks` guard_imports (#21173)
Issue: we have several helper functions to import third-party libraries
like import_uptrain in
[community.callbacks](https://api.python.langchain.com/en/latest/callbacks/langchain_community.callbacks.uptrain_callback.import_uptrain.html#langchain_community.callbacks.uptrain_callback.import_uptrain).
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 months ago
Hassan El Mghari 416549bed2
docs: Updated Together integration docs (#21388)
**Description:** Updated the together integration docs by leading with
the streaming example, explicitly specifying a model to show users how
to do that, and updating the sections to more closely match other
integrations.
2 months ago
Rahul Triptahi 7994cba18d
[Community][Minor]: Fetch loader_source of GoogleDriveLoader in PebbloSafeLoader. (#21314)
Description: This PR includes fix for loader_source to be fetched from
metadata in case of GdriveLoaders.
Documentation: NA
Unit Test: NA

Signed-off-by: Rahul Tripathi <rauhl.psit.ec@gmail.com>
Co-authored-by: Rahul Tripathi <rauhl.psit.ec@gmail.com>
2 months ago
Leonid Ganeline 7cbf1c31aa
docs: table legend updated (#21351)
Compacted the table column legends. Added links. Similar to #21259
2 months ago
Erick Friis d5bde4fa91
infra: use nbconvert for docs build (#21135)
todo

- [x] remove quarto build semantics
- [x] remove quarto download/install
- [x] make `uv` not verbose
2 months ago
Nuno Campos ad0f3c14c2
core: allow mermaid node labels to have any characters (#21385)
- it's only node ids that are limited

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 months ago
Eugene Yurtsev 6a1d61dbf1
community[patch]: Fix in memory vectorstore to take into account ids when adding docs (#21384)
Should respect `ids` if passed
2 months ago
Ikko Eltociear Ashimine 80170da6c5
docs: update cassandra_database.ipynb (#21145)
Enviroment -> Environment
2 months ago
Miroslav 04e2611fea
Added additional headers for HuggingFaceInferenceAPIEmbeddings endpoint. (#21282)
Thank you for contributing to LangChain!

- [ ] **HuggingFaceInferenceAPIEmbeddings**: "Additional Headers"
  - Where: langchain, community, embeddings. huggingface.py.
- Community: add additional headers when needed by custom HuggingFace
TEI embedding endpoints. HuggingFaceInferenceAPIEmbeddings"


- [ ] **PR message**: ***Delete this entire checklist*** and replace
with
- **Description:** Adding the `additional_headers` to be passed to
requests library if needed
    - **Dependencies:** none
 

- [ ] **Add tests and docs**: If you're adding a new integration, please
include
1. Tested with locally available TEI endpoints with and without
`additional_headers`
  2. Example  Usage
  
```python
embeddings=HuggingFaceInferenceAPIEmbeddings(
                             api_key=MY_CUSTOM_API_KEY,
                             api_url=MY_CUSTOM_TEI_URL,
                             additional_headers={
                                "Content-Type": "application/json"
                               }
)
```

 

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: Massimiliano Pronesti <massimiliano.pronesti@gmail.com>
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2 months ago
Ikko Eltociear Ashimine c34419e200
docs: update quick_start.ipynb (#21358)
initalize -> initialize



- [x] **PR title**: "package: description"
2 months ago
Guangdong Liu 1fe66f5d39
community(patch) fix MoonshotChat moonshot_api_key is invaild for api key (#21361)
Description: close
https://github.com/langchain-ai/langchain/issues/21237
@baskaryan, @eyurtsev
2 months ago
snova-jamesv c2ed484653
community: add Sambaverse rate limitation info to sambanova.ipynb (#21379)
- **Description:** add Sambaverse rate limitation info to
sambanova.ipynb
    - **Issue:** NA
    - **Dependencies:** NA
2 months ago
Tomaz Bratanic 0bf7596839
Add simple node properties to llm graph transformer (#21369)
Add support for simple node properties in llm graph transformer.

Linter and dynamic pydantic classes aren't friends, hence I added two
ignores
2 months ago
ccurme 080af0ec53
langchain: sync -> async methods in OpenAI assistants (#21378) 2 months ago
Tomaz Bratanic ad3fd44a7f
experimental: Fix llm graph transformer bug (#21362) 2 months ago
Erick Friis bb81ae5c8c
together: fix chat model and embedding classes (#21353) 2 months ago
Hassan El Mghari d6ef5fe86a
together: add chat models, use openai base (#21337)
**Description:** Adding chat completions to the Together AI package,
which is our most popular API. Also staying backwards compatible with
the old API so folks can continue to use the completions API as well.
Also moved the embedding API to use the OpenAI library to standardize it
further.

**Twitter handle:** @nutlope

- [x] **Add tests and docs**: If you're adding a new integration, please
include
- [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/

If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, hwchase17.

---------

Co-authored-by: Erick Friis <erick@langchain.dev>
2 months ago
Jacob Lee a2d31307bb
Adds confirmation logs after creating a new project (#12618)
@efriis @hwchase17

---------

Co-authored-by: Erick Friis <erick@langchain.dev>
2 months ago
Erick Friis 0fb93cd740
core: release 0.1.52 (#21350) 2 months ago
Wu Enze 32c61b3ece
community[patch]: chat message history mypy fixes #17048 (#20114)
Relates [#17048]
Description : Applied fix to redis and neo4j file.

Error was : `Cannot override writeable attribute with read-only
property`

fix with the same solution of
[[langchain/libs/community/langchain_community/chat_message_histories/elasticsearch.py](d5c412b0a9/libs/community/langchain_community/chat_message_histories/elasticsearch.py (L170-L175))]

---------

Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
Co-authored-by: Chester Curme <chester.curme@gmail.com>
2 months ago
nrpd25 95cc8e3fc3
premai[patch]:Standardized model init args (#21308)
[Standardized model init args
#20085](https://github.com/langchain-ai/langchain/issues/20085)
- Enable premai chat model to be initialized with `model_name` as an
alias for `model`, `api_key` as an alias for `premai_api_key`.
- Add initialization test `test_premai_initialization`

---------

Co-authored-by: Chester Curme <chester.curme@gmail.com>
2 months ago
Nuno Campos 6f17158606
fix: core: Include in json output also fields set outside the constructor (#21342) 2 months ago
Tomaz Bratanic ac14f171ac
Add indexed properties to neo4j enhanced schema (#21335) 2 months ago
scaserini a6cdf6572f
community: add Kendra DocumentRelevanceOverrideConfigurations request parameter (#20695)
- **Description:** add **DocumentRelevanceOverrideConfigurations**
request parameter to Kendra retriever

Co-authored-by: Simone Caserini <simone.caserini@klarna.com>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
2 months ago
Nuno Campos 0345bcf4ef
Fix failing test for serialization (#21344)
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 months ago
Trayan Azarov 93226b1945
community: Updated Chroma version range to include 0.5.0 release (#21224)
- Updated Chroma version range to allow releases in 0.5.x.
- Bumped mypy version as linting was failing
2 months ago
Jorge Piedrahita Ortiz e65652c3e8
community: add SambaNova embeddings integration (#21227)
- **Description:**  SambaNova hosted embeddings integration
2 months ago
Jorge Piedrahita Ortiz df1c10260c
community: minor changes sambanova integration (#21231)
- **Description:** fix: variable names in root validator not allowing
pass credentials as named parameters in llm instancing, also added
sambanova's sambaverse and sambastudio llms to __init__.py for module
import
2 months ago
Jan Soubusta d9a61c0fa9
fix: respect table_name argument when calling from_texts (#21252)
valid for from_documents() as well

fixes #21251
2 months ago
Pedro Lima bebf46c4a2
community: added args_schema to YahooFinanceNewsTool (#21232)
Description: this change adds args_schema (pydantic BaseModel) to
YahooFinanceNewsTool for correct schema formatting on LLM function calls

Issue: currently using YahooFinanceNewsTool with OpenAI function calling
returns the following error "TypeError("YahooFinanceNewsTool._run() got
an unexpected keyword argument '__arg1'")". This happens because the
schema sent to the LLM is "input: "{'__arg1': 'MSFT'}"" while the method
should be called with the "query" parameter.

Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
2 months ago
Mark Cusack 060987d755
community[minor]: Add indexing via locality sensitive hashing to the Yellowbrick vector store (#20856)
- **Description:** Add LSH-based indexing to the Yellowbrick vector
store module
- **Twitter handle:** @markcusack

---------

Co-authored-by: markcusack <markcusack@markcusacksmac.lan>
Co-authored-by: markcusack <markcusack@Mark-Cusack-sMac.local>
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
2 months ago