Bagatur
f7ae12fa1f
openai[minor]: Release 0.2.0 ( #26464 )
2024-09-13 15:38:10 -07:00
ccurme
d1462badaf
text-splitters: release 0.3 ( #26460 )
...
Co-authored-by: Erick Friis <erick@langchain.dev >
2024-09-13 22:31:06 +00:00
ccurme
9b30bdceb6
mistralai: release 0.2 ( #26458 )
...
Co-authored-by: Bagatur <baskaryan@gmail.com >
2024-09-13 18:27:51 -04:00
Erick Friis
d46ab19954
core: release 0.3.0 ( #26453 )
2024-09-13 21:45:45 +00:00
Erick Friis
c2a3021bb0
multiple: pydantic 2 compatibility, v0.3 ( #26443 )
...
Signed-off-by: ChengZi <chen.zhang@zilliz.com >
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com >
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com >
Co-authored-by: Dan O'Donovan <dan.odonovan@gmail.com >
Co-authored-by: Tom Daniel Grande <tomdgrande@gmail.com >
Co-authored-by: Grande <Tom.Daniel.Grande@statsbygg.no >
Co-authored-by: Bagatur <baskaryan@gmail.com >
Co-authored-by: ccurme <chester.curme@gmail.com >
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com >
Co-authored-by: Tomaz Bratanic <bratanic.tomaz@gmail.com >
Co-authored-by: ZhangShenao <15201440436@163.com >
Co-authored-by: Friso H. Kingma <fhkingma@gmail.com >
Co-authored-by: ChengZi <chen.zhang@zilliz.com >
Co-authored-by: Nuno Campos <nuno@langchain.dev >
Co-authored-by: Morgante Pell <morgantep@google.com >
2024-09-13 14:38:45 -07:00
Bagatur
d9813bdbbc
openai[patch]: Release 0.1.25 ( #26439 )
2024-09-13 12:00:01 -07:00
liuhetian
7fc9e99e21
openai[patch]: get output_type when using with_structured_output ( #26307 )
...
- This allows pydantic to correctly resolve annotations necessary when
using openai new param `json_schema`
Resolves issue: #26250
---------
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com >
Co-authored-by: Bagatur <baskaryan@gmail.com >
2024-09-13 11:42:01 -07:00
Bagatur
0f2b32ffa9
core[patch]: Release 0.2.40 ( #26435 )
2024-09-13 09:57:09 -07:00
Bagatur
e32adad17a
community[patch]: Release 0.2.17 ( #26432 )
2024-09-13 09:56:39 -07:00
langchain-infra
8a02fd9c01
core: add additional import mappings to loads ( #26406 )
...
Support using additional import mapping. This allows users to override
old mappings/add new imports to the loads function.
- [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/
2024-09-13 09:39:58 -07:00
Erick Friis
1d98937e8d
partners/openai: release 0.1.24 ( #26417 )
2024-09-12 21:54:13 -07:00
Harrison Chase
28ad244e77
community, openai: support nested dicts ( #26414 )
...
needed for thinking tokens
---------
Co-authored-by: Erick Friis <erick@langchain.dev >
2024-09-12 21:47:47 -07:00
Erick Friis
c0dd293f10
partners/groq: release 0.1.10 ( #26393 )
2024-09-12 17:41:11 +00:00
Erick Friis
54c85087e2
groq: add back streaming tool calls ( #26391 )
...
api no longer throws an error
https://console.groq.com/docs/tool-use#streaming
2024-09-12 10:29:45 -07:00
Bagatur
feb351737c
core[patch]: fix empty OpenAI tools when strict=True ( #26287 )
...
Fix #26232
---------
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com >
2024-09-11 16:06:03 -07:00
ccurme
398718e1cb
core[patch]: fix regression in convert_to_openai_tool with instances of Tool ( #26327 )
...
```python
from langchain_core.tools import Tool
from langchain_core.utils.function_calling import convert_to_openai_tool
def my_function(x: int) -> int:
return x + 2
tool = Tool(
name="tool_name",
func=my_function,
description="test description",
)
convert_to_openai_tool(tool)
```
Current:
```
{'type': 'function',
'function': {'name': 'tool_name',
'description': 'test description',
'parameters': {'type': 'object',
'properties': {'args': {'type': 'array', 'items': {}},
'config': {'type': 'object',
'properties': {'tags': {'type': 'array', 'items': {'type': 'string'}},
'metadata': {'type': 'object'},
'callbacks': {'anyOf': [{'type': 'array', 'items': {}}, {}]},
'run_name': {'type': 'string'},
'max_concurrency': {'type': 'integer'},
'recursion_limit': {'type': 'integer'},
'configurable': {'type': 'object'},
'run_id': {'type': 'string', 'format': 'uuid'}}},
'kwargs': {'type': 'object'}},
'required': ['config']}}}
```
Here:
```
{'type': 'function',
'function': {'name': 'tool_name',
'description': 'test description',
'parameters': {'properties': {'__arg1': {'title': '__arg1',
'type': 'string'}},
'required': ['__arg1'],
'type': 'object'}}}
```
2024-09-11 15:51:10 -04:00
이규민
7feae62ad7
core[patch]: Support non ASCII characters in tool output if user doesn't output string ( #26319 )
...
### simple modify
core: add supporting non english character
target issue is #26315
same issue on langgraph -
https://github.com/langchain-ai/langgraph/issues/1504
2024-09-11 15:21:00 +00:00
William FH
b993172702
Keyword-like runnable config ( #26295 )
2024-09-11 07:44:47 -07:00
Bagatur
17659ca2cd
core[patch]: Release 0.2.39 ( #26279 )
2024-09-10 20:11:27 +00:00
Nuno Campos
212c688ee0
core[minor]: Remove serialized manifest from tracing requests for non-llm runs ( #26270 )
...
- This takes a long time to compute, isn't used, and currently called on
every invocation of every chain/retriever/etc
2024-09-10 12:58:24 -07:00
ccurme
979232257b
huggingface[patch]: add integration tests for embeddings ( #26272 )
2024-09-10 14:57:16 -04:00
ccurme
4ffd27c4d0
huggingface[patch]: add integration tests ( #26269 )
...
Add standard tests for ChatHuggingFace. About half of these fail
currently.
2024-09-10 18:31:51 +00:00
Christophe Bornet
9cf7ae0a52
community: Add docstring for HtmlLinkExtractor ( #26213 )
...
Co-authored-by: Erick Friis <erick@langchain.dev >
2024-09-10 00:27:37 +00:00
Christophe Bornet
56580b5fff
community: Add docstring for GLiNERLinkExtractor ( #26218 )
...
Co-authored-by: Erick Friis <erick@langchain.dev >
2024-09-10 00:27:23 +00:00
Christophe Bornet
e235a572a0
community: Add docstring for KeybertLinkExtractor ( #26210 )
...
Co-authored-by: Erick Friis <erick@langchain.dev >
2024-09-10 00:26:29 +00:00
Vadym Barda
bab9de581c
core[patch]: wrap mermaid node names w/ markdown in <p> tag ( #26235 )
...
This fixes the issue where `__start__` and `__end__` node labels are
being interpreted as markdown, as of the most recent Mermaid update
2024-09-09 20:11:00 -04:00
Tomaz Bratanic
181e4fc0e0
Add session expired retry to neo4j graph ( #26182 )
...
Co-authored-by: Erick Friis <erick@langchain.dev >
2024-09-08 11:40:43 -07:00
Sebastian Cherny
b3c7ed4913
Adding bind_tools in ChatOctoAI ( #26168 )
...
The object extends from
langchain_community.chat_models.openai.ChatOpenAI which doesn't have
`bind_tools` defined. I tried extending from
`langchain_openai.ChatOpenAI` in
https://github.com/langchain-ai/langchain/pull/25975 but that PR got
closed because this is not correct.
So adding our own `bind_tools` (which for now copying from ChatOpenAI is
good enough) will solve the tool calling issue we are having now.
---------
Co-authored-by: Erick Friis <erick@langchain.dev >
2024-09-08 18:38:43 +00:00
John
97a8e365ec
partners/unstructured: update unstructured client version ( #26105 )
...
Users are having version conflicts with `unstructured-client` as
described here:
https://unstructuredw-kbe4326.slack.com/archives/C06JJHC9G4U/p1725557970546199?thread_ts=1725035247.162819&cid=C06JJHC9G4U
This PR fixes that issue and should update the version to "0.1.3" as
well for a clean-slate version for users to install
Co-authored-by: Erick Friis <erick@langchain.dev >
2024-09-08 18:32:34 +00:00
Vadym Barda
1b3bd52e0e
core[patch]: fix edge labels for mermaid graphs ( #26201 )
2024-09-08 14:35:25 +00:00
Marcelo Machado
9bd4f1dfa8
docs: small improvement ChatOllama setup description ( #26043 )
...
Small improvement on ChatOllama description
---------
Co-authored-by: Marcelo Machado <mmachado@ibm.com >
Co-authored-by: Erick Friis <erick@langchain.dev >
2024-09-08 00:15:05 +00:00
Erick Friis
6e82d2184b
partners/mongodb: release 0.1.9 ( #26193 )
2024-09-07 23:20:25 +00:00
William FH
262e19b15d
infra: Clear cache for env-var checks ( #26073 )
2024-09-06 21:29:29 +00:00
ChengZi
a03141ac51
partners[milvus]: fix integration test issues ( #26136 )
...
fix some integration test issues:
https://github.com/langchain-ai/langchain/actions/runs/10688447230/job/29628412258
Signed-off-by: ChengZi <chen.zhang@zilliz.com >
Co-authored-by: Erick Friis <erick@langchain.dev >
2024-09-06 16:52:36 +00:00
Erick Friis
5c1ebd3086
partners/unstructured: release 0.1.3 ( #26119 )
2024-09-06 16:22:53 +00:00
Bagatur
1241a004cb
fmt
2024-09-04 11:44:59 -07:00
Bagatur
4ba14ae9e5
fmt
2024-09-04 11:34:59 -07:00
Bagatur
dba308447d
fmt
2024-09-04 11:28:04 -07:00
Bagatur
fdf6fbde18
fmt
2024-09-04 11:12:11 -07:00
Bagatur
576574c82c
fmt
2024-09-04 11:05:36 -07:00
Bagatur
7bf54636ff
make
2024-09-04 10:24:42 -07:00
Bagatur
3ec93c2817
standard-tests[patch]: add Ser/Des test
2024-09-04 10:24:06 -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
ZhangShenao
c812237217
Improvement[Community] Improve args description in api doc of DocArrayInMemorySearch
( #26024 )
...
- Add missing arg
- Remove redundant arg
2024-09-04 09:26:26 -04:00
Tomaz Bratanic
c649b449d7
Add the option to ignore structured output method to LLM graph transf… ( #26013 )
...
Open source models like Llama3.1 have function calling, but it's not
that great. Therefore, we introduce the option to ignore model's
function calling and just use the prompt-based approach
2024-09-04 09:15:43 -04:00
Bagatur
4b99426a4f
openai[patch]: add back azure embeddings api_version alias
2024-09-03 17:25:03 -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
Tom Daniel Grande
0207dc1431
community: delta in openai choice can be None, creates handler for that ( #25954 )
...
Thank you for contributing to LangChain!
- [X ] **PR title**
- [X ] **PR message**:
**Description:** adds a handler for when delta choice is None
**Issue:** Fixes #25951
**Dependencies:** Not applicable
- [ X] **Add tests and docs**: Not applicable
- [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: Grande <Tom.Daniel.Grande@statsbygg.no >
Co-authored-by: Erick Friis <erick@langchain.dev >
2024-09-03 20:30:03 +00:00
Bagatur
9eb9ff52c0
experimental[patch]: Release 0.0.65 ( #25987 )
2024-09-03 19:15:48 +00:00
Bagatur
bc3b02651c
standard-tests[patch]: test init from env vars ( #25983 )
2024-09-03 19:05:39 +00:00