Commit Graph

862 Commits

Author SHA1 Message Date
Bagatur
576574c82c fmt 2024-09-04 11:05:36 -07:00
ccurme
be7cd0756f ollama[major]: upgrade pydantic (#26044) 2024-09-04 13:54:52 -04:00
ccurme
51c6899850 groq[major]: upgrade pydantic (#26036) 2024-09-04 13:41:40 -04:00
ccurme
163d6fe8ef anthropic: update pydantic (#26000)
Migrated with gritql: https://github.com/eyurtsev/migrate-pydantic
2024-09-04 13:35:51 -04:00
ccurme
7cee7fbfad mistralai: update pydantic (#25995)
Migrated with gritql: https://github.com/eyurtsev/migrate-pydantic
2024-09-04 13:26:17 -04:00
Bagatur
3ec93c2817 standard-tests[patch]: add Ser/Des test 2024-09-04 10:24:06 -07:00
Bagatur
88065d794b fmt 2024-09-04 09:52:01 -07:00
Bagatur
b27bfa6717 pinecone[major]: Update to pydantic v2 2024-09-04 09:50:39 -07:00
Bagatur
5adeaf0732 openai[major]: switch to pydantic v2 (#26001) 2024-09-04 09:18:29 -07:00
Friso H. Kingma
af11fbfbf6 langchain_openai: Make sure the response from the async client in the astream method of ChatOpenAI is properly awaited in case of "include_response_headers=True" (#26031)
- **Description:** This is a **one line change**. the
`self.async_client.with_raw_response.create(**payload)` call is not
properly awaited within the `_astream` method. In `_agenerate` this is
done already, but likely forgotten in the other method.
  - **Issue:** Not applicable
  - **Dependencies:** No dependencies required.

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

---------

Co-authored-by: Chester Curme <chester.curme@gmail.com>
2024-09-04 13:26:48 +00:00
Bagatur
4c7afb0d6c Update libs/partners/openai/langchain_openai/llms/base.py 2024-09-03 23:36:19 -07:00
Bagatur
c1ff61669d Update libs/partners/openai/langchain_openai/llms/base.py 2024-09-03 23:36:14 -07:00
Bagatur
54d6808c1e Update libs/partners/openai/langchain_openai/llms/azure.py 2024-09-03 23:36:08 -07:00
Bagatur
78468de2e5 Update libs/partners/openai/langchain_openai/llms/azure.py 2024-09-03 23:36:02 -07:00
Bagatur
76572f963b Update libs/partners/openai/langchain_openai/embeddings/base.py 2024-09-03 23:35:56 -07:00
Bagatur
c0448f27ba Update libs/partners/openai/langchain_openai/embeddings/base.py 2024-09-03 23:35:51 -07:00
Bagatur
179aaa4007 Update libs/partners/openai/langchain_openai/embeddings/azure.py 2024-09-03 23:35:43 -07:00
Bagatur
d072d592a1 Update libs/partners/openai/langchain_openai/embeddings/azure.py 2024-09-03 23:35:35 -07:00
Bagatur
78c454c130 Update libs/partners/openai/langchain_openai/chat_models/base.py 2024-09-03 23:35:30 -07:00
Bagatur
5199555c0d Update libs/partners/openai/langchain_openai/chat_models/base.py 2024-09-03 23:35:26 -07:00
Bagatur
5e31cd91a7 Update libs/partners/openai/langchain_openai/chat_models/azure.py 2024-09-03 23:35:21 -07:00
Bagatur
49a1f5dd47 Update libs/partners/openai/langchain_openai/chat_models/azure.py 2024-09-03 23:35:15 -07:00
Bagatur
d0cc9b022a Update libs/partners/fireworks/langchain_fireworks/chat_models.py 2024-09-03 23:30:56 -07:00
Bagatur
a91bd2737a Update libs/partners/fireworks/langchain_fireworks/chat_models.py 2024-09-03 23:30:49 -07:00
Bagatur
56163481dd fmt 2024-09-03 17:46:41 -07:00
Bagatur
6aac2eeab5 fmt 2024-09-03 17:42:22 -07:00
Bagatur
559d8a4d13 fireworks[major]: switch to pydantic v2 2024-09-03 17:41:28 -07:00
Bagatur
4b99426a4f openai[patch]: add back azure embeddings api_version alias 2024-09-03 17:25:03 -07:00
Bagatur
ec9e8eb71c fmt 2024-09-03 17:24:24 -07:00
Bagatur
6777106fbe fmt 2024-09-03 16:50:17 -07:00
Bagatur
5f5287c3b0 fmt 2024-09-03 16:48:53 -07:00
Bagatur
615f8b0d47 openai[major]: switch to pydantic v2 2024-09-03 16:33:35 -07:00
Eugene Yurtsev
bc3b851f08 openai[patch]: Upgrade @root_validators in preparation for pydantic 2 migration (#25491)
* Upgrade @root_validator in openai pkg
* Ran notebooks for all but AzureAI embeddings

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2024-09-03 14:42:24 -07:00
Bagatur
bc3b02651c standard-tests[patch]: test init from env vars (#25983) 2024-09-03 19:05:39 +00:00
Bagatur
035d8cf51b milvus[patch]: Release 0.1.5 (#25981) 2024-09-03 18:19:51 +00:00
Bagatur
7457949619 mistralai[patch]: Release 0.1.13 (#25978) 2024-09-03 18:03:15 +00:00
Maximilian Schulz
fdeaff4149 langchain-mistralai - make base URL possible to set via env variable for ChatMistralAI (#25956)
Thank you for contributing to LangChain!


**Description:** 

Similar to other packages (`langchain_openai`, `langchain_anthropic`) it
would be beneficial if that `ChatMistralAI` model could fetch the API
base URL from the environment.

This PR allows this via the following order:
- provided value
- then whatever `MISTRAL_API_URL` is set to
- then whatever `MISTRAL_BASE_URL` is set to
- if `None`, then default is ` "https://api.mistral.com/v1"`


- [x] **Add tests and docs**:

Added unit tests, docs I feel are unnecessary, as this is just aligning
with other packages that do the same?


- [x] **Lint and test**: 

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: Chester Curme <chester.curme@gmail.com>
2024-09-03 14:32:35 +00:00
Bagatur
da113f6363 docs: ChatOpenAI.with_structured_output nits (#25952) 2024-09-03 08:20:58 +00:00
Bagatur
28e2ec7603 ollama[patch]: Release 0.1.3 (#25902) 2024-08-31 00:11:45 +00:00
Ohad Eytan
b5d670498f partners/milvus: allow creating a vectorstore with sparse embeddings (#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](https://github.com/langchain-ai/langchain/discussions/19955),
[here](https://github.com/langchain-ai/langchain/pull/20375), and
[here](https://github.com/langchain-ai/langchain/discussions/22886)
similar needs.

---------

Co-authored-by: Erick Friis <erick@langchain.dev>
2024-08-30 02:30:23 +00:00
Erick Friis
1640872059 together: mv to external repo (#25863) 2024-08-29 16:42:59 -07:00
Kyle Winkelman
09c2d8faca langchain_openai: Cleanup OpenAIEmbeddings validate_environment. (#25855)
**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.
2024-08-29 13:54:43 -04:00
ChengZi
37f5ba416e partners[milvus]: fix issue when metadata_schema is None (#25836)
fix issue when metadata_schema is None

Signed-off-by: ChengZi <chen.zhang@zilliz.com>
2024-08-29 10:11:09 -04:00
Erick Friis
e5ae988505 prompty: bump core version (#25831) 2024-08-28 23:06:13 +00:00
ccurme
ff168aaec0 prompty: release 0.0.3 (#25830) 2024-08-28 15:52:17 -07:00
Matthieu
783397eacb community: avoid double templating in langchain_prompty (#25777)
## Description

In `langchain_prompty`, messages are templated by Prompty. However, a
call to `ChatPromptTemplate` was initiating a second templating. We now
convert parsed messages to `Message` objects before calling
`ChatPromptTemplate`, signifying clearly that they are already
templated.

We also revert #25739 , which applied to this second templating, which
we now avoid, and did not fix the original issue.

## Issue

Closes #25703
2024-08-28 18:18:18 -04:00
Erick Friis
8fb594fd2a ai21: migrate to external repo (#25827) 2024-08-28 14:24:07 -07:00
Erick Friis
095b712a26 ollama: bump core version (#25826) 2024-08-28 12:31:16 -07:00
Erick Friis
5186325bc7 partners/ollama: release 0.1.2 (#25817)
release for #25697
2024-08-28 17:47:32 +00:00
Rohit Gupta
aff50a1e6f milvus: add array data type for collection create (#23219)
Add array data type for milvus vector store collection create


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.

---------

Signed-off-by: ChengZi <chen.zhang@zilliz.com>
Co-authored-by: Rohit Gupta <rohit.gupta2@walmart.com>
Co-authored-by: ChengZi <chen.zhang@zilliz.com>
Co-authored-by: Erick Friis <erick@langchain.dev>
2024-08-28 16:55:57 +00:00