Commit Graph

5897 Commits

Author SHA1 Message Date
Stuart Marsh
16bd0697dc milvus: fixed bug when using partition key and dynamic fields together (#25028)
**Description:**

This PR fixes a bug where if `enable_dynamic_field` and
`partition_key_field` are enabled at the same time, a pymilvus error
occurs.

Milvus requires the partition key field to be a full schema defined
field, and not a dynamic one, so it will throw the error "the specified
partition key field {field} not exist" when creating the collection.

When `enabled_dynamic_field` is set to `True`, all schema field creation
based on `metadatas` is skipped. This code now checks if
`partition_key_field` is set, and creates the field.

Integration test added.

**Twitter handle:** StuartMarshUK

---------

Co-authored-by: Stuart Marsh <stuart.marsh@qumata.com>
Co-authored-by: Erick Friis <erick@langchain.dev>
2024-08-05 16:01:55 +00:00
Jim Baldwin
6890daa90c community: make AthenaLoader profile_name optional and fix type hint (#24958)
- **Description:** This PR makes the AthenaLoader profile_name optional
and fixes the type hint which says the type is `str` but it should be
`str` or `None` as None is handled in the loader init. This is a minor
problem but it just confused me when I was using the Athena Loader to
why we had to use a Profile, as I want that for local but not
production.
- **Issue:** #24957 
- **Dependencies:** None.
2024-08-05 14:28:58 +00:00
Alexey Lapin
335894893b langchain: Make RetryWithErrorOutputParser.from_llm() create a correct retry chain (#25053)
Description: RetryWithErrorOutputParser.from_llm() creates a retry chain
that returns a Generation instance, when it should actually just return
a string.
This class was forgotten when fixing the issue in PR #24687
2024-08-05 14:21:27 +00:00
Dobiichi-Origami
c5cb52a3c6 community: fix issue of the existence of numeric object in additional_kwargs a… (#24863)
- **Description:** A previous PR breaks the code from
`baidu_qianfan_endpoint.py` which causes the malfunction of streaming
2024-08-05 10:15:55 -04:00
ZhangShenao
cda79dbb6c community[patch]: Optimize test case for MoonshotChat (#25050)
Optimize test case for `MoonshotChat`. Use standard
ChatModelIntegrationTests.
2024-08-05 10:11:25 -04:00
ZhangShenao
02c35da445 doc[Retriever] Enhance api docs for MultiQueryRetriever (#25035)
Enhance api docs for `MultiQueryRetriever`:

- Complete missing parameters
- Unify parameter name
2024-08-04 13:56:38 -04:00
Alex Sherstinsky
208042e0f2 community: Fix Predibase Integration for HuggingFace-hosted fine-tuned adapters (#25015)
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"


- [ ] **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!


- [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.


- [ ] **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, ccurme, vbarda, hwchase17.
2024-08-03 14:05:43 -07:00
maang-h
f5da0d6d87 docs: Standardize MiniMaxEmbeddings (#24983)
- **Description:** Standardize MiniMaxEmbeddings
  - docs, the issue #24856 
  - model init arg names, the issue #20085
2024-08-03 14:01:23 -04:00
ZhangShenao
2c3e3dc6b1 patch[Partners] Unified fix of incorrect variable declarations in all check_imports (#25014)
There are some incorrect declarations of variable `has_failure` in
check_imports. The purpose of this PR is to uniformly fix these errors.
2024-08-03 13:49:41 -04:00
maang-h
7de62abc91 docs: Standardize SparkLLMTextEmbeddings docstrings (#25021)
- **Description:** Standardize SparkLLMTextEmbeddings docstrings
- **Issue:** the issue #24856
2024-08-03 13:44:09 -04:00
Tomaz Bratanic
f9a11a9197 Add relik transformer config (#25019) 2024-08-03 08:41:45 -04:00
Bagatur
1dcee68cb8 docs: show beta directive (#25013)
![Screenshot 2024-08-02 at 7 15 34
PM](https://github.com/user-attachments/assets/086831c7-36f3-4962-98dc-d707b6289747)
2024-08-03 03:07:45 +00:00
Bagatur
e81ddb32a6 docs: fix kwargs docstring (#25010)
Fix:
![Screenshot 2024-08-02 at 5 33 37
PM](https://github.com/user-attachments/assets/7c56cdeb-ee81-454c-b3eb-86aa8a9bdc8d)
2024-08-02 19:54:54 -07:00
Bagatur
57747892ce docs: show deprecation warning first in api ref (#25001)
OLD
![Screenshot 2024-08-02 at 3 29 39
PM](https://github.com/user-attachments/assets/7f169121-1202-4770-a006-d72ac7a1aa33)


NEW
![Screenshot 2024-08-02 at 3 29 45
PM](https://github.com/user-attachments/assets/9cc07cbd-2ae9-4077-95c5-03cb051e6cd7)
2024-08-02 17:35:25 -07:00
Isaac Francisco
73570873ab docs: standardizing tavily tool docs (#24736)
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
2024-08-02 22:25:27 +00:00
Bagatur
4305f78e40 core[patch]: Release 0.2.28 (#25000) 2024-08-02 21:07:06 +00:00
Bagatur
dd8e4cd020 text-splitters[patch]: Release 0.2.3 (#24998) 2024-08-02 20:27:22 +00:00
Bagatur
0de0cd2d31 core[patch]: merge message runs nit (#24997)
Only add separator if both chunks are non-empty
2024-08-02 20:25:43 +00:00
Bagatur
8e2316b8c2 community[patch]: Release 0.2.11 (#24989) 2024-08-02 20:08:44 +00:00
ccurme
c2538e7834 experimental[patch]: bump min versions of core and community (#24996)
Ollama functions unit test broken with min version of community.
2024-08-02 19:58:55 +00:00
ccurme
22c1a4041b community[patch]: support named arguments in github toolkit (#24986)
Parameters may be passed in by name if generated from tool calls.
2024-08-02 18:27:32 +00:00
ccurme
4797b806c2 experimental[patch]: release 0.0.64 (#24990) 2024-08-02 18:00:57 +00:00
Tomaz Bratanic
7061869aec Add relik graph transformer (#24982)
Relik is a new library for graph extraction that offers smaller and
cheaper models for graph construction
2024-08-02 13:55:41 -04:00
ccurme
c04d95b962 standard-tests: set integration test parameters independent of unit test (#24979)
This ends up getting set in integration tests.
2024-08-02 10:40:11 -07:00
gbaian10
54e9ea433a fix: Modify the order of init_chat_model import ollama package. (#24977) 2024-08-02 08:32:56 -07:00
ZhangShenao
71c0564c9f community[patch]: Add test case for MoonshotChat (#24960)
Add test case for `MoonshotChat`.
2024-08-02 09:37:31 -04:00
ZhangShenao
c65e48996c patch[partners] Fix check_imports bugs in pinecone and milvus (#24971)
Fix wrong declared variables of `check_imports` in pinecone and milvus
2024-08-02 09:27:11 -04:00
Isaac Francisco
d7688a4328 community[patch]: adding artifact to Tavily search (#24376)
This allows you to get raw content as well as the answer, instead of
just getting the results.

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2024-08-01 21:12:11 -07:00
Bagatur
7b08de8909 langchain[patch]: Release 0.2.12 (#24954) 2024-08-02 04:04:49 +00:00
Bagatur
245cb5a252 core[patch]: Release 0.2.27 (#24952) 2024-08-02 01:43:24 +00:00
Bagatur
199e9c5ae0 core[patch]: Fix tool args schema inherited field parsing (#24936)
Fix #24925
2024-08-01 18:36:33 -07:00
Leonid Ganeline
4092876863 core: docstrings `BaseCallbackHandler update (#24948)
Added missed docstrings
2024-08-01 20:46:53 -04:00
WU LIFU
ad16eed119 core[patch]: runnable config ensure_config deep copy from var_child_runnable… (#24862)
**issue**: #24660 
RunnableWithMessageHistory.stream result in error because the
[evaluation](https://github.com/langchain-ai/langchain/blob/master/libs/core/langchain_core/runnables/branch.py#L220)
of the branch
[condition](99eb31ec41/libs/core/langchain_core/runnables/history.py (L328C1-L329C1))
unexpectedly trigger the
"[on_end](99eb31ec41/libs/core/langchain_core/runnables/history.py (L332))"
(exit_history) callback of the default branch


**descriptions**
After a lot of investigation I'm convinced that the root cause is that
1. during the execution of the runnable, the
[var_child_runnable_config](99eb31ec41/libs/core/langchain_core/runnables/config.py (L122))
is shared between the branch
[condition](99eb31ec41/libs/core/langchain_core/runnables/history.py (L328C1-L329C1))
runnable and the [default branch
runnable](99eb31ec41/libs/core/langchain_core/runnables/history.py (L332))
within the same context
2. when the default branch runnable runs, it gets the
[var_child_runnable_config](99eb31ec41/libs/core/langchain_core/runnables/config.py (L163))
and may unintentionally [add more handlers
](99eb31ec41/libs/core/langchain_core/runnables/config.py (L325))to
the callback manager of this config
3. when it is again the turn for the
[condition](99eb31ec41/libs/core/langchain_core/runnables/history.py (L328C1-L329C1))
to run, it gets the `var_child_runnable_config` whose callback manager
has the handlers added by the default branch. When it runs that handler
(`exit_history`) it leads to the error
   
with the assumption that, the `ensure_config` function actually does
want to create a immutable copy from `var_child_runnable_config` because
it starts with an [`empty` variable
](99eb31ec41/libs/core/langchain_core/runnables/config.py (L156)),
i go ahead to do a deepcopy to ensure that future modification to the
returned value won't affect the `var_child_runnable_config` variable
   
   Having said that I actually 
1. don't know if this is a proper fix
2. don't know whether it will lead to other unintended consequence 
3. don't know why only "stream" runs into this issue while "invoke" runs
without problem

so @nfcampos @hwchase17 please help review, thanks!

---------

Co-authored-by: Lifu Wu <lifu@nextbillion.ai>
Co-authored-by: Nuno Campos <nuno@langchain.dev>
Co-authored-by: Bagatur <baskaryan@gmail.com>
2024-08-01 17:30:32 -07:00
ccurme
9cb69a8746 docs: update retriever template, add arxiv retriever (#24947) 2024-08-01 16:53:18 -04:00
Casey Clements
db3ceb4d0a partners/mongodb: Improved search index commands (#24745)
Hardens index commands with try/except for free clusters and optional
waits for syncing and tests.

[efriis](https://github.com/efriis) These are the upgrades to the search
index commands (CRUD) that I mentioned.

---------

Co-authored-by: Erick Friis <erick@langchain.dev>
2024-08-01 20:16:32 +00:00
ccurme
41ed23a050 docs: update retriever integration pages (#24931) 2024-08-01 14:37:07 -04:00
maang-h
ea505985c4 docs: Standardize ZhipuAIEmbeddings docstrings (#24933)
- **Description:** Standardize ZhipuAIEmbeddings rich docstrings.
- **Issue:** the issue #24856
2024-08-01 14:06:53 -04:00
Anneli Samuel
2204d8cb7d community[patch]: Invoke on_llm_new_token callback before yielding chunk (#24938)
**Description**: Invoke on_llm_new_token callback before yielding chunk
in streaming mode
**Issue**:
[#16913](https://github.com/langchain-ai/langchain/issues/16913)
2024-08-01 16:39:04 +00:00
Eugene Yurtsev
75776e4a54 core[patch]: In unit tests, use _schema() instead of BaseModel.schema() (#24930)
This PR introduces a module with some helper utilities for the pydantic
1 -> 2 migration.

They're meant to be used in the following way:

1) Use the utility code to get unit tests pass without requiring
modification to the unit tests
2) (If desired) upgrade the unit tests to match pydantic 2 output
3) (If desired) stop using the utility code

Currently, this module contains a way to map `schema()` generated by
pydantic 2 to (mostly) match the output from pydantic v1.
2024-08-01 11:59:04 -04:00
Serena Ruan
1827bb4042 community[patch]: support bind_tools for ChatMlflow (#24547)
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"


- **Description:** 
Support ChatMlflow.bind_tools method
Tested in Databricks:
<img width="836" alt="image"
src="https://github.com/user-attachments/assets/fa28ef50-0110-4698-8eda-4faf6f0b9ef8">



- [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/

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, ccurme, vbarda, hwchase17.

---------

Signed-off-by: Serena Ruan <serena.rxy@gmail.com>
2024-08-01 08:43:07 -07:00
BottlePumpkin
bfc59c1d26 community: Fix KeyError in NotionDB loader when 'name' is missing (#24224)
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:** 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!


- [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/

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, ccurme, vbarda, hwchase17.



**Description:** This PR fixes a KeyError in NotionDBLoader when the
"name" key is missing in the "people" property.

**Issue:** Fixes #24223 

**Dependencies:** None

---------

Co-authored-by: Chester Curme <chester.curme@gmail.com>
2024-08-01 13:55:40 +00:00
alexqiao
8eb0bdead3 community[patch]: Invoke callback prior to yielding token (#24917)
**Description: Invoke callback prior to yielding token in stream method
for chat_models .**
**Issue**: https://github.com/langchain-ai/langchain/issues/16913
#16913
2024-08-01 13:19:55 +00:00
ZhangShenao
b2dd9ffaaf patch[cli] Fix bug in check_imports.py (#24918)
The variable `has_failure` in check_imports.py is wrong-declared. It's
actually an another variable.
2024-08-01 09:08:12 -04:00
Erick Friis
600fc233ef partners/ollama: release 0.1.1 (#24910) 2024-07-31 17:31:29 -07:00
Bagatur
25b93cc4c0 core[patch]: stringify tool non-content blocks (#24626)
Slightly breaking bugfix. Shouldn't cause too many issues since no
models would be able to handle non-content block ToolMessage.content
anyways.
2024-07-31 16:42:38 -07:00
Nikita Pakunov
c776471ac6 community: fix AttributeError: 'YandexGPT' object has no attribute '_grpc_metadata' (#24432)
Fixes #24049

---------

Co-authored-by: Erick Friis <erick@langchain.dev>
2024-07-31 21:18:33 +00:00
Bagatur
752a71b688 integrations[patch]: release model packages (#24900) 2024-07-31 20:48:20 +00:00
Jacob Lee
1213a59f87 docs[patch]: Update kv store docs pages (#24848) 2024-07-31 13:23:24 -07:00
Erick Friis
a7380dd531 cli: release 0.0.28 (#24852) 2024-07-31 13:03:24 -07:00
Erick Friis
e98e4be0f7 cli: register new integration doc templates (#24854)
- wait to merge for retriever.ipynb merge #24836
2024-07-31 13:03:05 -07:00