Erick Friis
b7c2029e84
standard-tests: root docstrings ( #28595 )
2024-12-06 15:14:52 -08:00
Erick Friis
925ca75ca5
docs: format ( #28593 )
2024-12-06 15:08:25 -08:00
Erick Friis
f943205ebf
docs: dont document root init ( #28592 )
2024-12-06 15:07:53 -08:00
Erick Friis
9e2abcd152
standard-tests: show right classes in api docs ( #28591 )
2024-12-06 14:48:13 -08:00
Erick Friis
246c10a1cc
standard-tests: private members and tools unit troubleshoot ( #28590 )
2024-12-06 13:52:58 -08:00
Erick Friis
1cedf401a7
docs: enable private docstring submembers sphinx ( #28589 )
2024-12-06 13:36:34 -08:00
Erick Friis
791d7e965e
docs: enable private docstring modules sphinx ( #28588 )
2024-12-06 13:23:06 -08:00
Erick Friis
4f99952129
docs: enable private docstring members sphinx ( #28586 )
2024-12-06 13:19:52 -08:00
Bagatur
221ab03fe4
docs: readme/intro nits ( #28581 )
2024-12-06 12:52:15 -08:00
Erick Friis
e6663b69f3
langchain: release 0.3.10 ( #28585 )
2024-12-06 20:20:24 +00:00
Erick Friis
c38b845d7e
core: fix path test ( #28584 )
2024-12-06 20:05:18 +00:00
ccurme
2c6bc74cb1
multiple: combine sync/async vector store standard test suites ( #28580 )
...
Breaking change in `langchain-tests`.
2024-12-06 14:55:06 -05:00
Bagatur
dda9f90047
core[patch]: Release 0.3.22 ( #28582 )
2024-12-06 19:36:53 +00:00
ccurme
15cbc36a23
docs[patch]: update contributor docs for integrations ( #28576 )
...
- Reformat tabs
- Add code snippets inline
- Add embeddings content
2024-12-06 13:33:24 -05:00
ccurme
f3dc142d3c
cli[patch]: implement minimal starter vector store ( #28577 )
...
Basically the same as core's in-memory vector store. Removed some
optional methods.
2024-12-06 13:10:22 -05:00
Erick Friis
5277a021c1
docs: raw loader codeblock ( #28548 )
...
Co-authored-by: Chester Curme <chester.curme@gmail.com >
2024-12-06 09:26:34 -08:00
Erick Friis
18386c16c7
core, tests: more tolerant _aget_relevant_documents function ( #28462 )
2024-12-06 00:49:30 +00:00
Erick Friis
bc636ccc60
cli: release 0.0.35 ( #28557 )
2024-12-05 16:40:52 -08:00
Erick Friis
7ecf38f4fa
cli: create specific files from template ( #28556 )
2024-12-06 00:32:47 +00:00
Erick Friis
a197e0ba3d
docs: custom deprecated coloring, organize css a bit ( #28555 )
2024-12-05 23:57:54 +00:00
Erick Friis
478def8dcc
core: deprecation doc removal ( #28553 )
...
2024-12-05 15:35:28 -08:00
cinqisap
482e8a7855
community: Add support for SAP HANA Vector hnsw index creation ( #27884 )
...
**Issue:** Added support for creating indexes in the SAP HANA Vector
engine.
**Changes**:
1. Introduced a new function `create_hnsw_index` in `hanavector.py` that
enables the creation of indexes for SAP HANA Vector.
2. Added integration tests for the index creation function to ensure
functionality.
3. Updated the documentation to reflect the new index creation feature,
including examples and output from the notebook.
4. Fix the operator issue in ` _process_filter_object` function and
change the array argument to a placeholder in the similarity search SQL
statement.
---------
Co-authored-by: Erick Friis <erick@langchain.dev >
2024-12-05 23:29:08 +00:00
blaufink
28f8d436f6
mistral: fix of issue #26029 ( #28233 )
...
- Description: Azure AI takes an issue with the safe_mode parameter
being set to False instead of None. Therefore, this PR changes the
default value of safe_mode from False to None. This results in it being
filtered out before the request is sent - avoind the extra-parameter
issue described below.
- Issue: #26029
- Dependencies: /
---------
Co-authored-by: blaufink <sebastian.brueckner@outlook.de >
Co-authored-by: Erick Friis <erick@langchain.dev >
2024-12-05 23:28:12 +00:00
Erick Friis
7a96ce1320
docs: deprecated styling ( #28550 )
2024-12-05 14:05:25 -08:00
ccurme
5519a1c1d3
docs[patch]: improve integration docs ( #28547 )
...
Alternative to https://github.com/langchain-ai/langchain/pull/28426
---------
Co-authored-by: Erick Friis <erick@langchain.dev >
2024-12-05 16:32:09 -05:00
Erick Friis
66f819c59e
infra: run cli tests on test changes ( #28542 )
2024-12-05 13:09:25 -08:00
Erick Friis
3d5493593b
docs: deprecated styling ( #28546 )
...
from
to
2024-12-05 12:41:41 -08:00
ccurme
ecdfc98ef6
tests[patch]: run standard tests for embeddings and populate embeddings API ref ( #28545 )
...
plus minor updates to chat models and vector store API refs
2024-12-05 19:39:03 +00:00
dwelch-spike
1581857e3d
docs: add Aerospike to providers list ( #28066 )
...
**Description:** Adds Aerospike to the list of langchain providers and
points users to documentation for the vector store and Python SDK.
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 <erickfriis@gmail.com >
Co-authored-by: Erick Friis <erick@langchain.dev >
2024-12-05 17:29:00 +00:00
WEIQ-beepbeep
1e285cb5f3
docs: Updated incorrected type used for the multiply_by_max function ( #28042 )
...
In the `multiply_by_max()` tool, `a` is a scale factor but it is
annotated with a string type.
2024-12-05 09:15:59 -08:00
ccurme
b8e861a63b
openai[patch]: add standard tests for embeddings ( #28540 )
2024-12-05 17:00:27 +00:00
ZhangShenao
d26555c682
[VectorStore] Improvement: Improve chroma vector store ( #28524 )
...
- Complete unit test
- Fix spelling error
2024-12-05 11:58:32 -05:00
John
7d44316d92
docs: Add link for how to install extras ( #28537 )
...
**Description:** Add link for how to install extras
2024-12-05 11:57:51 -05:00
ccurme
8f9b3b7498
chroma[patch]: fix bug ( #28538 )
...
Fix bug introduced in
https://github.com/langchain-ai/langchain/pull/27995
If all document IDs are `""`, the chroma SDK will raise
```
DuplicateIDError: Expected IDs to be unique
```
Caught by [docs
tests](https://github.com/langchain-ai/langchain/actions/runs/12180395579/job/33974633950 ),
but added a test to langchain-chroma as well.
2024-12-05 15:37:19 +00:00
Erick Friis
ecff9a01e4
cli: release 0.0.34 ( #28525 )
2024-12-05 15:35:49 +00:00
ccurme
d9e42a1517
langchain[patch]: fix deprecation warning ( #28535 )
2024-12-05 14:49:10 +00:00
Erick Friis
0f539f0246
standard-tests: release 0.3.5 ( #28526 )
2024-12-05 00:41:07 -08:00
Erick Friis
43c35d19d4
cli: standard tests in cli, test that they run, skip vectorstore tests ( #28521 )
2024-12-05 00:38:32 -08:00
Erick Friis
c5acedddc2
anthropic: timeout in tests (10s) ( #28488 )
2024-12-04 16:03:38 -08:00
ccurme
f459754470
tests[patch]: populate API reference for vector stores ( #28520 )
2024-12-05 00:02:31 +00:00
Erick Friis
2b360d6a2f
infra: scheduled test fix ( #28519 )
2024-12-04 15:20:56 -08:00
ccurme
8bc2c912b8
chroma[patch]: (nit) simplify test ( #28517 )
...
Use `self.get_embeddings` on test class instead of importing embeddings
separately.
2024-12-04 20:22:55 +00:00
Tomaz Bratanic
a0130148bc
switch graph semantic layer docs to langgraph ( #28513 )
...
Co-authored-by: Chester Curme <chester.curme@gmail.com >
2024-12-04 14:30:12 -05:00
ccurme
eec55c2550
chroma[patch]: add get_by_ids and fix bug ( #28516 )
...
- Run standard integration tests in Chroma
- Add `get_by_ids` method
- Fix bug in `add_texts`: if a list of `ids` is passed but any of them
are None, Chroma will raise an exception. Here we assign a uuid.
2024-12-04 14:00:36 -05:00
Erick Friis
12d74d5bef
docs: single security doc ( #28515 )
2024-12-04 18:15:34 +00:00
Erick Friis
e6a08355a3
docs: more api ref links, add linting step to prevent more ( #28495 )
2024-12-04 04:19:42 +00:00
wlleiiwang
6151ea78d5
community: implement _select_relevance_score_fn for tencent vectordb ( #28036 )
...
implement _select_relevance_score_fn for tencent vectordb
fix use external embedding for tencent vectordb
Co-authored-by: wlleiiwang <wlleiiwang@tencent.com >
Co-authored-by: Erick Friis <erick@langchain.dev >
2024-12-04 03:03:00 +00:00
Asi Greenholts
d34bf78f3b
community: BM25Retriever preservation of document id ( #27019 )
...
Currently this retriever discards document ids
---------
Co-authored-by: asi-cider <88270351+asi-cider@users.noreply.github.com >
Co-authored-by: Erick Friis <erick@langchain.dev >
2024-12-04 00:36:00 +00:00
Erick Friis
a009249369
infra: release rely on local built in testing ( #28492 )
2024-12-03 16:35:38 -08:00
peterdhp
bc5ec63d67
community : allow using apikey for PubMedAPIWrapper ( #27246 )
...
**Description**:
> Without an API key, any site (IP address) posting more than 3 requests
per second to the E-utilities will receive an error message. By
including an API key, a site can post up to 10 requests per second by
default.
quoted from A General Introduction to the E-utilities,NCBI :
https://www.ncbi.nlm.nih.gov/books/NBK25497/
I have simply added a api_key parameter to the PubMedAPIWrapper that can
be used to increase the number of requests per second from 3 to 10.
**Twitter handle** : @KORmaori
---------
Co-authored-by: Erick Friis <erick@langchain.dev >
2024-12-03 16:21:22 -08:00
