[pull] master from langchain-ai:master #57
+506,059
−506,597
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
![pull[bot]](https://avatars.githubusercontent.com/in/12910?s=60&v=4){kind=small}
#20607) - **Description:** Add function call support in Sparkllm chat model. Related documents https://www.xfyun.cn/doc/spark/Web.html#_2-function-call%E8%AF%B4%E6%98%8E - @baskaryan --------- Co-authored-by: ccurme <chester.curme@gmail.com>
Thank you for contributing to LangChain! community:premai[patch]: standardize init args - updated `temperature` with Pydantic Field, updated the unit test. - updated `max_tokens` with Pydantic Field, updated the unit test. - updated `max_retries` with Pydantic Field, updated the unit test. Related to #20085 --------- Co-authored-by: Isaac Francisco <78627776+isahers1@users.noreply.github.com> Co-authored-by: ccurme <chester.curme@gmail.com>
- [ ] **PR title**: community: add tests for ChatOctoAI - [ ] **PR message**: Description: Added unit tests for the ChatOctoAI class in the community package to ensure proper validation and default values. These tests verify the correct initialization of fields, the handling of missing required parameters, and the proper setting of aliases. Issue: N/A Dependencies: None --------- Co-authored-by: ccurme <chester.curme@gmail.com> Co-authored-by: Eugene Yurtsev <eugene@langchain.dev>
Added missed provider pages. Added missed references to the integration components.
#25852) **Description:** Within AzureOpenAIEmbeddings there is a validation to cap `chunk_size` at 16. The value of 16 is either an old limitation or was erroneously chosen. I have checked all of the `preview` and `stable` releases to ensure that the `embeddings` endpoint can handle 2048 entries [Azure/azure-rest-api-specs](https://github.com/Azure/azure-rest-api-specs/tree/main/specification/cognitiveservices/data-plane/AzureOpenAI/inference). I have also found many locations that confirm this limit should be 2048: - https://learn.microsoft.com/en-us/azure/ai-services/openai/reference#embeddings - https://learn.microsoft.com/en-us/azure/ai-services/openai/quotas-limits **Issue:** fixes #25462
) **Description:** [This portion of code](https://github.com/langchain-ai/langchain/blob/v0.1.16/libs/partners/openai/langchain_openai/embeddings/base.py#L189-L196) has no use as a couple lines later a [`ValueError` is thrown](https://github.com/langchain-ai/langchain/blob/v0.1.16/libs/partners/openai/langchain_openai/embeddings/base.py#L209-L213). **Issue:** A follow up to #25852.
Update merging utils to - not mutate objects - have special handling to 'type' keys in dicts
) - **Description:** OpenAI recently introduced a "strict" parameter for [structured outputs in their API](https://openai.com/index/introducing-structured-outputs-in-the-api/). An optional `strict` parameter has been added to `create_openai_functions_agent()` and `create_openai_tools_agent()` so developers can use this feature in those agents. --------- Co-authored-by: Chester Curme <chester.curme@gmail.com>
…25284) # Description Milvus (and `pymilvus`) recently added the option to use [sparse vectors](https://milvus.io/docs/sparse_vector.md#Sparse-Vector) with appropriate search methods (e.g., `SPARSE_INVERTED_INDEX`) and embeddings (e.g., `BM25`, `SPLADE`). This PR allow creating a vector store using langchain's `Milvus` class, setting the matching vector field type to `DataType.SPARSE_FLOAT_VECTOR` and the default index type to `SPARSE_INVERTED_INDEX`. It is only extending functionality, and backward compatible. ## Note I also interested in extending the Milvus class further to support multi vector search (aka hybrid search). Will be happy to discuss that. See [here](#19955), [here](#20375), and [here](#22886) similar needs. --------- Co-authored-by: Erick Friis <erick@langchain.dev>
- [x] **PR title - community: add neo4j query constructor for self
query**
- [x] **PR message**
- **Description:** adding a Neo4jTranslator so that the Neo4j vector
database can use SelfQueryRetriever
- **Issue:** this issue had been raised before in #19748
- **Dependencies:** none.
- **Twitter handle:** @moyi_dang
- p.s. I have not added the query constructor in BUILTIN_TRANSLATORS in
this PR, I want to make changes to only one package at a time.
- [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.
---------
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
Co-authored-by: Chester Curme <chester.curme@gmail.com>
… in custom tools. (#25887) - **Description:** if you use callback handlers when using tool, run_manager will be added to input, so you need to explicitly specify args_schema, but i was confused because it was not listed, so i added it. Also, it seems that the type does not work with pydantic.BaseModel. - **Issue:** None - **Dependencies:** None
…25884) - Add tool-calling test case for `ChatZhipuAI`
- **Description:** When useing LLM integration moonshot,it's occurring error "'Moonshot' object has no attribute '_client'",it's because of the "_client" that is private in pydantic v1.0 so that we can't use it.I turn "_client" into "client" , the error to be resolved! - **Issue:** the issue #24390 - **Dependencies:** none - **Twitter handle:** @rainsubtime - [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: Cyue <Cyue_work2001@163.com>
**Description:** Fix async infinity embeddings **Issue:** #24942 @baskaryan, @ccurme
## Description - Updates the self-query retriever factory to check for the new Qdrant vector store class. i.e. `langchain_qdrant.QdrantVectorstore`. - Deprecates `QdrantSparseVectorRetriever`, since the vector store implementation natively supports it now. Resolves #25798
…ration, and update the documentation. (#25893) 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:update documentation for Vertex Embeddings Models
- **Issue:NA
- **Dependencies:NA
- **Twitter handle:NA
---------
Co-authored-by: adityarane@google.com <adityarane@google.com>
Added missed provider pages and links. Fixed inconsistent formatting. Co-authored-by: Erick Friis <erick@langchain.dev>
#20075) - **Description:** Added `ref` query parameter so data is not loaded only from the default branch but any branch passed --------- Co-authored-by: Osama Mehdi <mehdi@hm.edu> Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com> Co-authored-by: Erick Friis <erick@langchain.dev>
Thank you for contributing to LangChain!
- **AI Agent Built With LangChain and FireWorksAI**: "community
notebook"
- **Description:** Added a new AI agent in the cookbook folder that
integrates prompt compression using LLMLingua and arXiv retrieval tools.
The agent is designed to optimize the efficiency and performance of
research tasks by compressing lengthy prompts and retrieving relevant
academic papers. The agent also makes uses of MongoDB to store
conversational history and as it's knowledge base using MongoDB vector
store
- **Twitter handle:** https://x.com/richmondalake
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
Co-authored-by: Bagatur <baskaryan@gmail.com>
… by ruff (#26608) Ruff doesn't know about the python version in `[tool.poetry.dependencies]`. It can get it from `project.requires-python`. Notes: * poetry seems to have issues getting the python constraints from `requires-python` and using `python` in per dependency constraints. So I had to duplicate the info. I will open an issue on poetry. * `inspect.isclass()` doesn't work correctly with `GenericAlias` (`list[...]`, `dict[..., ...]`) on Python <3.11 so I added some `not isinstance(type, GenericAlias)` checks: Python 3.11 ```pycon >>> import inspect >>> inspect.isclass(list) True >>> inspect.isclass(list[str]) False ``` Python 3.9 ```pycon >>> import inspect >>> inspect.isclass(list) True >>> inspect.isclass(list[str]) True ``` Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
makes core incompatible with uv installs
tested on one of the replacement cases and seems to work! 
…er as agent tool (#26181) 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" Added search options for BoxRetriever and added documentation to demonstrate how to use BoxRetriever as an agent tool - @BoxPlatform - [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.
Co-authored-by: Erick Friis <erick@langchain.dev>
Fixes #26212: replaced the raw string with backslashes. Alternative: raw-stringif the full docstring. --------- Co-authored-by: Erick Friis <erickfriis@gmail.com>
…5970) Co-authored-by: Erick Friis <erick@langchain.dev>
Public classes/functions are not renamed and rule is ignored for them. Co-authored-by: Erick Friis <erick@langchain.dev>
Page content sometimes is empty when PyMuPDF can not find text on pages.
For example, this can happen when the text of the PDF is not copyable
"by hand". Then an OCR solution is need - which is not integrated here.
This warning should accurately warn the user that some pages are lost
during this process.
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, ccurme, vbarda, hwchase17.
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
…ore (#25486) # Description [Vector store base class](https://github.com/langchain-ai/langchain/blob/4cdaca67dc51dba887289f56c6fead3c1a52f97d/libs/core/langchain_core/vectorstores/base.py#L65) currently expects `ids` to be passed in and that is what it passes along to the AzureSearch vector store when attempting to `add_texts()`. However AzureSearch expects `keys` to be passed in. When they are not present, AzureSearch `add_embeddings()` makes up new uuids. This is a problem when trying to run indexing. [Indexing code expects](https://github.com/langchain-ai/langchain/blob/b297af5482ae7c6d26779513d637ec657a1cd552/libs/core/langchain_core/indexing/api.py#L371) the documents to be uploaded using provided ids. Currently AzureSearch ignores `ids` passed from `indexing` and makes up new ones. Later when `indexer` attempts to delete removed file, it uses the `id` it had stored when uploading the document, however it was uploaded under different `id`. **Twitter handle: @martintriska1**
removing Sambaverse llm model and references given is not available after Sep/10/2024 <img width="1781" alt="image" src="https://github.com/user-attachments/assets/4dcdb5f7-5264-4a03-b8e5-95c88304e059">
fix error in samba studio embeddings result unpacking
…eLoader (#26582) - **Description:** Added PebbloTextLoader for loading text in PebbloSafeLoader. - Since PebbloSafeLoader wraps document loaders, this new loader enables direct loading of text into Documents using PebbloSafeLoader. - **Issue:** NA - **Dependencies:** NA - [x] **Tests**: Added/Updated tests
MERGE ME PLEASE
- Add to tests on parsed content; - Add tests for async + lazy loading; - Add a test for `strategy="hi_res"`.
Thank you for contributing to LangChain! Fix error like <img width="1167" alt="image" src="https://github.com/user-attachments/assets/2e219b26-ec7e-48ef-8111-e0ff2f5ac4c0"> After the fix: <img width="584" alt="image" src="https://github.com/user-attachments/assets/48f36fe7-628c-48b6-81b2-7fe741e4ca85"> - [ ] **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. --------- Signed-off-by: serena-ruan <serena.rxy@gmail.com> Co-authored-by: Erick Friis <erick@langchain.dev>
remove beta namespace from core, add to community
`unstructured.partition.auto.partition` supports a `url` kwarg, but `url` in `UnstructuredLoader.__init__` is reserved for the server URL. Here we add a `web_url` kwarg that is passed to the partition kwargs: ```python self.unstructured_kwargs["url"] = web_url ```
Restore qa template that was working
Complementary PR to master for #26643. Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
There is a small bug in "TypedDict class" sample source.
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, ccurme, vbarda, hwchase17.
- [ ] **PR title**: "community:fix ChatZhipuAI tool call bug"
- [ ] **Description:** ZhipuAI api response as follows:
{'id': '20240920132549e379a9152a6a4d7c', 'created': 1726809949, 'model':
'glm-4-flash', 'choices': [{'index': 0, 'finish_reason': 'tool_calls',
'delta': {'role': 'assistant', 'tool_calls': [{'id':
'call_20240920132549e379a9152a6a4d7c', 'index': 0, 'type': 'function',
'function': {'name': 'get_datetime_offline', 'arguments': '{}'}}]}}]}
so, tool_calls = dct.get("tool_call", None) in
_convert_delta_to_message_chunk should be "tool_calls"
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
See Commits and Changes for more details.
Created by
pull[bot]
Can you help keep this open source service alive? 💖 Please sponsor : )