**Description:** When an OpenAI assistant is invoked, it creates a run
by default, allowing users to set only a few request fields. The
truncation strategy is set to auto, which includes previous messages in
the thread along with the current question until the context length is
reached. This causes token usage to grow incrementally:
consumed_tokens = previous_consumed_tokens + current_consumed_tokens.
This PR adds support for user-defined truncation strategies, giving
better control over token consumption.
**Issue:** High token consumption.
## Description
This PR addresses the following:
**Fixes Issue #25343:**
- Adds additional logic to parse shallowly nested JSON-encoded strings
in tool call arguments, allowing for proper parsing of responses like
that of Llama3.1 and 3.2 with nested schemas.
**Adds Integration Test for Fix:**
- Adds a Ollama specific integration test to ensure the issue is
resolved and to prevent regressions in the future.
**Fixes Failing Integration Tests:**
- Fixes failing integration tests (even prior to changes) caused by
`llama3-groq-tool-use` model. Previously,
tests`test_structured_output_async` and
`test_structured_output_optional_param` failed due to the model not
issuing a tool call in the response. Resolved by switching to
`llama3.1`.
## Issue
Fixes#25343.
## Dependencies
No dependencies.
____
Done in collaboration with @ishaan-upadhyay @mirajismail @ZackSteine.
- **Description:** `add_texts` was using `get_setting` for marqo client
which was being used according to 1.5.x API version. However, this PR
updates the `add_text` accounting for updated response payload for 2.x
and later while maintaining backward compatibility. Plus I have verified
this was the only place where marqo client was not accounting for
updated API version.
- **Issue:** #28323
---------
Co-authored-by: ccurme <chester.curme@gmail.com>
_This should only be merged once neo4j is included under libs/partners._
# **Description:**
Neo4jVector from langchain-community is being moved to langchain-neo4j:
[see
link](https://github.com/langchain-ai/langchain-neo4j/blob/main/libs/neo4j/langchain_neo4j/vectorstores/neo4j_vector.py#L436).
To solve the issue below, this PR adds an attempt to import
`Neo4jVector` from the partner package `langchain-neo4j`, similarly to
the other partner packages.
# **Issue:**
When initializing `SelfQueryRetriever`, the following error is raised:
```
ValueError: Self query retriever with Vector Store type <class 'langchain_neo4j.vectorstores.neo4j_vector.Neo4jVector'> not supported.
```
[See related
issue](https://github.com/langchain-ai/langchain/issues/19748).
# **Dependencies:**
- langchain-neo4j
v0.4 of the Python SDK is already installed via the lock file in CI, but
our current implementation is not compatible with it.
This also addresses an issue introduced in
https://github.com/langchain-ai/langchain/pull/28299. @RyanMagnuson
would you mind explaining the motivation for that change? From what I
can tell the Ollama SDK [does not support
kwargs](6c44bb2729/ollama/_client.py (L286)).
Previously, unsupported kwargs were ignored, but they currently raise
`TypeError`.
Some of LangChain's standard test suite expects `tool_choice` to be
supported, so here we catch it in `bind_tools` so it is ignored and not
passed through to the client.
Adds deprecation notices for Neo4j components moving to the
`langchain_neo4j` partner package.
- Adds deprecation warnings to all Neo4j-related classes and functions
that have been migrated to the new `langchain_neo4j` partner package
- Updates documentation to reference the new `langchain_neo4j` package
instead of `langchain_community`
**Description:**
Currently, the docstring for `LanceDB.__init__()` provides the default
value for `mode`, but not the list of valid values. This PR adds that
list to the docstring.
**Issue:**
N/A
**Dependencies:**
N/A
**Twitter handle:**
`@metadaddy`
[Leaving as a reminder: If no one reviews your PR within a few days,
please @-mention one of baskaryan, efriis, eyurtsev, ccurme, vbarda,
hwchase17.]
We have a test
[test_structured_few_shot_examples](ad4333ca03/libs/standard-tests/langchain_tests/integration_tests/chat_models.py (L546))
in standard integration tests that implements a version of tool-calling
few shot examples that works with ~all tested providers. The formulation
supported by ~all providers is: `human message, tool call, tool message,
AI reponse`.
Here we update
`langchain_core.utils.function_calling.tool_example_to_messages` to
support this formulation.
The `tool_example_to_messages` util is undocumented outside of our API
reference. IMO, if we are testing that this function works across all
providers, it can be helpful to feature it in our guides. The structured
few-shot examples we document at the moment require users to implement
this function and can be simplified.
From what I can tell response using SDK is not deterministic:
```python
import numpy as np
import openai
documents = ["disallowed special token '<|endoftext|>'"]
model = "text-embedding-ada-002"
direct_output_1 = (
openai.OpenAI()
.embeddings.create(input=documents, model=model)
.data[0]
.embedding
)
for i in range(10):
direct_output_2 = (
openai.OpenAI()
.embeddings.create(input=documents, model=model)
.data[0]
.embedding
)
print(f"{i}: {np.isclose(direct_output_1, direct_output_2).all()}")
```
```
0: True
1: True
2: True
3: True
4: False
5: True
6: True
7: True
8: True
9: True
```
See related discussion here:
https://community.openai.com/t/can-text-embedding-ada-002-be-made-deterministic/318054
Found the same result using `"text-embedding-3-small"`.
Fixed a compatibility issue in the `load_messages_from_context()`
function for the Kinetica chat model integration. The issue was caused
by stricter validation introduced in Pydantic 2.
deleting the following docker things from monorepo. they aren't
currently usable because of old dependencies, and I'd rather avoid
people using them / having to maintain them
- /docker
- this folder has a compose file that spins up postgres,pgvector
(separate from postgres and very stale version),mongo instance with
default user/password that we've gotten security pings about before. not
worth having
- also spins up a custom dockerfile with onttotext/graphdb - not even
sure what that is
- /libs/langchain/dockerfile + dev.dockerfile
- super old poetry version, doesn't implement the right thing anymore
- .github/workflows/_release_docker.yml, langchain_release_docker.yml
- not used anymore, not worth having an alternate release path
In collaboration with @rlouf I build an
[outlines](https://dottxt-ai.github.io/outlines/latest/) integration for
langchain!
I think this is really useful for doing any type of structured output
locally.
[Dottxt](https://dottxt.co) spend alot of work optimising this process
at a lower level
([outlines-core](https://pypi.org/project/outlines-core/0.1.14/) written
in rust) so I think this is a better alternative over all current
approaches in langchain to do structured output.
It also implements the `.with_structured_output` method so it should be
a drop in replacement for a lot of applications.
The integration includes:
- **Outlines LLM class**
- **ChatOutlines class**
- **Tutorial Cookbooks**
- **Documentation Page**
- **Validation and error messages**
- **Exposes Outlines Structured output features**
- **Support for multiple backends**
- **Integration and Unit Tests**
Dependencies: `outlines` + additional (depending on backend used)
I am not sure if the unit-tests comply with all requirements, if not I
suggest to just remove them since I don't see a useful way to do it
differently.
### Quick overview:
Chat Models:
<img width="698" alt="image"
src="https://github.com/user-attachments/assets/05a499b9-858c-4397-a9ff-165c2b3e7acc">
Structured Output:
<img width="955" alt="image"
src="https://github.com/user-attachments/assets/b9fcac11-d3e5-4698-b1ae-8c4cb3d54c45">
---------
Co-authored-by: Vadym Barda <vadym@langchain.dev>
- **Description:** We have released the
[langchain-gigachat](https://github.com/ai-forever/langchain-gigachat?tab=readme-ov-file)
with new GigaChat integration that support's function/tool calling. This
PR deprecated legacy GigaChat class in community package.
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
Thank you for reading my first PR!
**Description:**
Deduplicate content in AzureSearch vectorstore.
Currently, by default, the content of the retrieval is placed both in
metadata and page_content of a Document.
This PR removes the content from metadata, and leaves it in
page_content.
**Issue:**:
Previously, the content was popped from result before metadata was
populated.
In #25828 , the order was changed which leads to a response with
duplicated content.
This was not the intention of that PR and seems undesirable.
Looking forward to seeing my contribution in the next version!
Cheers,
Renzo
**Description:** Add tool calling and structured output support for
SambaNovaCloud chat models, docs included
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
This change refines the handling of _model_kwargs in POST requests.
Instead of nesting _model_kwargs as a dictionary under the parameters
key, it is now directly unpacked and merged into the request's JSON
payload. This ensures that the model parameters are passed correctly and
avoids unnecessary nesting.E. g.:
```python
import asyncio
from langchain_huggingface.embeddings import HuggingFaceEndpointEmbeddings
embedding_input = ["This input will get multiplied" * 10000]
embeddings = HuggingFaceEndpointEmbeddings(
model="http://127.0.0.1:8081/embed",
model_kwargs={"truncate": True},
)
# Truncated parameters in synchronized methods are handled correctly
embeddings.embed_documents(texts=embedding_input)
# The truncate parameter is not handled correctly in the asynchronous method,
# and 413 Request Entity Too Large is returned.
asyncio.run(embeddings.aembed_documents(texts=embedding_input))
```
Co-authored-by: af su <saf@zjuici.com>
Co-authored-by: Erick Friis <erick@langchain.dev>
Description:
* I'm planning to add `Document.id` support to the Chroma VectorStore,
but first I wanted to make sure all the integration tests were passing
first. They weren't. This PR fixes the broken tests.
* I found 2 issues:
* This change (from a year ago, exactly :) ) for supporting multi-modal
embeddings:
https://docs.trychroma.com/deployment/migration#migration-to-0.4.16---november-7,-2023
* This change https://github.com/langchain-ai/langchain/pull/27827 due
to an update in the chroma client.
Also ran `format` and `lint` on the changes.
Note: I am not a member of the Chroma team.
# Description
- adding stopReason to response_metadata to call stream and astream
- excluding NCP_APIGW_API_KEY input required validation
- to remove warning Field "model_name" has conflict with protected
namespace "model_".
cc. @vbarda
Description:
* Updated the OpenSearchVectorStore to use the `engine` parameter
captured at `init()` time as the default when adding documents to the
store.
Formatted, Linted, and Tested.
**Description:** The issue concerns the unexpected behavior observed
using the bind_tools method in LangChain's ChatOllama. When tools are
not bound, the llm.stream() method works as expected, returning
incremental chunks of content, which is crucial for real-time
applications such as conversational agents and live feedback systems.
However, when bind_tools([]) is used, the streaming behavior changes,
causing the output to be delivered in full chunks rather than
incrementally. This change negatively impacts the user experience by
breaking the real-time nature of the streaming mechanism.
**Issue:** #26971
---------
Co-authored-by: 4meyDam1e <amey.damle@mail.utoronto.ca>
Co-authored-by: Chester Curme <chester.curme@gmail.com>
Last week Anthropic released version 0.39.0 of its python sdk, which
enabled support for Python 3.13. This release deleted a legacy
`client.count_tokens` method, which we currently access during init of
the `Anthropic` LLM. Anthropic has replaced this functionality with the
[client.beta.messages.count_tokens()
API](https://github.com/anthropics/anthropic-sdk-python/pull/726).
To enable support for `anthropic >= 0.39.0` and Python 3.13, here we
drop support for the legacy token counting method, and add support for
the new method via `ChatAnthropic.get_num_tokens_from_messages`.
To fully support the token counting API, we update the signature of
`get_num_tokens_from_message` to accept tools everywhere.
---------
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
Description:
* When working with OpenSearchVectorSearch to make
OpenSearchGraphVectorStore (coming soon), I noticed that there wasn't
type hinting for the underlying OpenSearch clients. This fixes that
issue.
* Confirmed tests are still passing with code changes.
Note that there is some additional code duplication now, but I think
this approach is cleaner overall.
## Description
As proposed in our earlier discussion #26977 we have introduced a Google
Books API Tool that leverages the Google Books API found at
[https://developers.google.com/books/docs/v1/using](https://developers.google.com/books/docs/v1/using)
to generate book recommendations.
### Sample Usage
```python
from langchain_community.tools import GoogleBooksQueryRun
from langchain_community.utilities import GoogleBooksAPIWrapper
api_wrapper = GoogleBooksAPIWrapper()
tool = GoogleBooksQueryRun(api_wrapper=api_wrapper)
tool.run('ai')
```
### Sample Output
```txt
Here are 5 suggestions based off your search for books related to ai:
1. "AI's Take on the Stigma Against AI-Generated Content" by Sandy Y. Greenleaf: In a world where artificial intelligence (AI) is rapidly advancing and transforming various industries, a new form of content creation has emerged: AI-generated content. However, despite its potential to revolutionize the way we produce and consume information, AI-generated content often faces a significant stigma. "AI's Take on the Stigma Against AI-Generated Content" is a groundbreaking book that delves into the heart of this issue, exploring the reasons behind the stigma and offering a fresh, unbiased perspective on the topic. Written from the unique viewpoint of an AI, this book provides readers with a comprehensive understanding of the challenges and opportunities surrounding AI-generated content. Through engaging narratives, thought-provoking insights, and real-world examples, this book challenges readers to reconsider their preconceptions about AI-generated content. It explores the potential benefits of embracing this technology, such as increased efficiency, creativity, and accessibility, while also addressing the concerns and drawbacks that contribute to the stigma. As you journey through the pages of this book, you'll gain a deeper understanding of the complex relationship between humans and AI in the realm of content creation. You'll discover how AI can be used as a tool to enhance human creativity, rather than replace it, and how collaboration between humans and machines can lead to unprecedented levels of innovation. Whether you're a content creator, marketer, business owner, or simply someone curious about the future of AI and its impact on our society, "AI's Take on the Stigma Against AI-Generated Content" is an essential read. With its engaging writing style, well-researched insights, and practical strategies for navigating this new landscape, this book will leave you equipped with the knowledge and tools needed to embrace the AI revolution and harness its potential for success. Prepare to have your assumptions challenged, your mind expanded, and your perspective on AI-generated content forever changed. Get ready to embark on a captivating journey that will redefine the way you think about the future of content creation.
Read more at https://play.google.com/store/books/details?id=4iH-EAAAQBAJ&source=gbs_api
2. "AI Strategies For Web Development" by Anderson Soares Furtado Oliveira: From fundamental to advanced strategies, unlock useful insights for creating innovative, user-centric websites while navigating the evolving landscape of AI ethics and security Key Features Explore AI's role in web development, from shaping projects to architecting solutions Master advanced AI strategies to build cutting-edge applications Anticipate future trends by exploring next-gen development environments, emerging interfaces, and security considerations in AI web development Purchase of the print or Kindle book includes a free PDF eBook Book Description If you're a web developer looking to leverage the power of AI in your projects, then this book is for you. Written by an AI and ML expert with more than 15 years of experience, AI Strategies for Web Development takes you on a transformative journey through the dynamic intersection of AI and web development, offering a hands-on learning experience.The first part of the book focuses on uncovering the profound impact of AI on web projects, exploring fundamental concepts, and navigating popular frameworks and tools. As you progress, you'll learn how to build smart AI applications with design intelligence, personalized user journeys, and coding assistants. Later, you'll explore how to future-proof your web development projects using advanced AI strategies and understand AI's impact on jobs. Toward the end, you'll immerse yourself in AI-augmented development, crafting intelligent web applications and navigating the ethical landscape.Packed with insights into next-gen development environments, AI-augmented practices, emerging realities, interfaces, and security governance, this web development book acts as your roadmap to staying ahead in the AI and web development domain. What you will learn Build AI-powered web projects with optimized models Personalize UX dynamically with AI, NLP, chatbots, and recommendations Explore AI coding assistants and other tools for advanced web development Craft data-driven, personalized experiences using pattern recognition Architect effective AI solutions while exploring the future of web development Build secure and ethical AI applications following TRiSM best practices Explore cutting-edge AI and web development trends Who this book is for This book is for web developers with experience in programming languages and an interest in keeping up with the latest trends in AI-powered web development. Full-stack, front-end, and back-end developers, UI/UX designers, software engineers, and web development enthusiasts will also find valuable information and practical guidelines for developing smarter websites with AI. To get the most out of this book, it is recommended that you have basic knowledge of programming languages such as HTML, CSS, and JavaScript, as well as a familiarity with machine learning concepts.
Read more at https://play.google.com/store/books/details?id=FzYZEQAAQBAJ&source=gbs_api
3. "Artificial Intelligence for Students" by Vibha Pandey: A multifaceted approach to develop an understanding of AI and its potential applications KEY FEATURES ● AI-informed focuses on AI foundation, applications, and methodologies. ● AI-inquired focuses on computational thinking and bias awareness. ● AI-innovate focuses on creative and critical thinking and the Capstone project. DESCRIPTION AI is a discipline in Computer Science that focuses on developing intelligent machines, machines that can learn and then teach themselves. If you are interested in AI, this book can definitely help you prepare for future careers in AI and related fields. The book is aligned with the CBSE course, which focuses on developing employability and vocational competencies of students in skill subjects. The book is an introduction to the basics of AI. It is divided into three parts – AI-informed, AI-inquired and AI-innovate. It will help you understand AI's implications on society and the world. You will also develop a deeper understanding of how it works and how it can be used to solve complex real-world problems. Additionally, the book will also focus on important skills such as problem scoping, goal setting, data analysis, and visualization, which are essential for success in AI projects. Lastly, you will learn how decision trees, neural networks, and other AI concepts are commonly used in real-world applications. By the end of the book, you will develop the skills and competencies required to pursue a career in AI. WHAT YOU WILL LEARN ● Get familiar with the basics of AI and Machine Learning. ● Understand how and where AI can be applied. ● Explore different applications of mathematical methods in AI. ● Get tips for improving your skills in Data Storytelling. ● Understand what is AI bias and how it can affect human rights. WHO THIS BOOK IS FOR This book is for CBSE class XI and XII students who want to learn and explore more about AI. Basic knowledge of Statistical concepts, Algebra, and Plotting of equations is a must. TABLE OF CONTENTS 1. Introduction: AI for Everyone 2. AI Applications and Methodologies 3. Mathematics in Artificial Intelligence 4. AI Values (Ethical Decision-Making) 5. Introduction to Storytelling 6. Critical and Creative Thinking 7. Data Analysis 8. Regression 9. Classification and Clustering 10. AI Values (Bias Awareness) 11. Capstone Project 12. Model Lifecycle (Knowledge) 13. Storytelling Through Data 14. AI Applications in Use in Real-World
Read more at https://play.google.com/store/books/details?id=ptq1EAAAQBAJ&source=gbs_api
4. "The AI Book" by Ivana Bartoletti, Anne Leslie and Shân M. Millie: Written by prominent thought leaders in the global fintech space, The AI Book aggregates diverse expertise into a single, informative volume and explains what artifical intelligence really means and how it can be used across financial services today. Key industry developments are explained in detail, and critical insights from cutting-edge practitioners offer first-hand information and lessons learned. Coverage includes: · Understanding the AI Portfolio: from machine learning to chatbots, to natural language processing (NLP); a deep dive into the Machine Intelligence Landscape; essentials on core technologies, rethinking enterprise, rethinking industries, rethinking humans; quantum computing and next-generation AI · AI experimentation and embedded usage, and the change in business model, value proposition, organisation, customer and co-worker experiences in today’s Financial Services Industry · The future state of financial services and capital markets – what’s next for the real-world implementation of AITech? · The innovating customer – users are not waiting for the financial services industry to work out how AI can re-shape their sector, profitability and competitiveness · Boardroom issues created and magnified by AI trends, including conduct, regulation & oversight in an algo-driven world, cybersecurity, diversity & inclusion, data privacy, the ‘unbundled corporation’ & the future of work, social responsibility, sustainability, and the new leadership imperatives · Ethical considerations of deploying Al solutions and why explainable Al is so important
Read more at http://books.google.ca/books?id=oE3YDwAAQBAJ&dq=ai&hl=&source=gbs_api
5. "Artificial Intelligence in Society" by OECD: The artificial intelligence (AI) landscape has evolved significantly from 1950 when Alan Turing first posed the question of whether machines can think. Today, AI is transforming societies and economies. It promises to generate productivity gains, improve well-being and help address global challenges, such as climate change, resource scarcity and health crises.
Read more at https://play.google.com/store/books/details?id=eRmdDwAAQBAJ&source=gbs_api
```
## Issue
This closes#27276
## Dependencies
No additional dependencies were added
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
all template installs will now have to declare `--branch v0.2` to make
clear they aren't compatible with langchain 0.3 (most have a pydantic v1
setup). e.g.
```
langchain-cli app add pirate-speak --branch v0.2
```
Thank you for contributing to LangChain!
- [x] **PR title**: "community: chat models wrapper for Cloudflare
Workers AI"
- [x] **PR message**:
- **Description:** Add chat models wrapper for Cloudflare Workers AI.
Enables Langgraph intergration via ChatModel for tool usage, agentic
usage.
- [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>
Co-authored-by: Chester Curme <chester.curme@gmail.com>
