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>
