PyPI · #5334 most downloaded on PyPI

langchain-nvidia-ai-endpoints

1.4.3532K downloads/molangchain-ai/langchain-nvidia ↗New releases in your daily digest, changelog included.

An integration package connecting NVIDIA AI Endpoints and LangChain

Last release 3 months ago
02 Jul 2026
Release timing varies
gaps range from 8 days to 2 months
Nearly every release is documented
notes for 60 of the last 60 stable releases
Nothing withdrawn
no release was ever pulled
3 years old
66 releases · first in 2023

Release timeline

66 releases since 2023

Releases

1.4.32 Jul 2026Deprecated
docs(ai-endpoints): replace deprecated max_tokens with max_completion_tokens in README example by @GSCSD1 in https://github.com/langchain-ai/langchain…
What's Changed

docs(ai-endpoints): replace deprecated max_tokens with max_completion_tokens in README example by @GSCSD1 in https://github.com/langchain-ai/langchain-nvidia/pull/333

chore(deps): bump the pip group across 2 directories with 8 updates by @dependabot[bot] in https://github.com/langchain-ai/langchain-nvidia/pull/329

chore(deps): bump the pip group across 1 directory with 2 updates by @dependabot[bot] in https://github.com/langchain-ai/langchain-nvidia/pull/331

Release/1.4.3 by @mdrxy in https://github.com/langchain-ai/langchain-nvidia/pull/336

Release/1.4.3 by @mdrxy in https://github.com/langchain-ai/langchain-nvidia/pull/337

chore: swap default integration test model by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/339

chore: xfail integration tests for temporary model swap by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/340

chore: swap default integration test model by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/341

New Contributors

@GSCSD1 made their first contribution in https://github.com/langchain-ai/langchain-nvidia/pull/333

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/openshell/v0.1.0...libs/ai-endpoints/v1.4.3
Open source →

2023202420252026

20232026

One column per month.

chore(deps): bump aiohttp from 3.13.4 to 3.14.0 in /libs/ai-endpoints in the pip group across 1 directory by @dependabot[bot] in https://github.com/la

What's Changed

chore(deps): bump aiohttp from 3.13.4 to 3.14.0 in /libs/ai-endpoints in the pip group across 1 directory by @dependabot[bot] in https://github.com/langchain-ai/langchain-nvidia/pull/316
feat(ai-endpoints): add version metadata to NVIDIA models by @mdrxy in https://github.com/langchain-ai/langchain-nvidia/pull/318
chore(deps): bump aiohttp from 3.14.0 to 3.14.1 in /libs/ai-endpoints in the pip group across 1 directory by @dependabot[bot] in https://github.com/langchain-ai/langchain-nvidia/pull/319
Fix ChatNVIDIA timeout being treated as a model parameter by @0Sh1khar in https://github.com/langchain-ai/langchain-nvidia/pull/317
chore: pin aiohttp below 3.14 for vcrpy compatibility by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/320
fix: use inactivity timeouts for async streaming by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/323
Release/1.4.2 by @soumilinandi in https://github.com/langchain-ai/langchain-nvidia/pull/324

New Contributors

@0Sh1khar made their first contribution in https://github.com/langchain-ai/langchain-nvidia/pull/317

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v1.4.1...libs/ai-endpoints/v1.4.2

Open source →

1.4.13 Jun 2026

add tool support for qwen3.5-122b-a10b by @vidushig-nv in https://github.com/langchain-ai/langchain-nvidia/pull/312

What's Changed

add tool support for qwen3.5-122b-a10b by @vidushig-nv in https://github.com/langchain-ai/langchain-nvidia/pull/312
Keep ChatNVIDIA verify_ssl out of payload by @freshyjmp in https://github.com/langchain-ai/langchain-nvidia/pull/314
bumping version for release by @soumilinandi in https://github.com/langchain-ai/langchain-nvidia/pull/315

New Contributors

@freshyjmp made their first contribution in https://github.com/langchain-ai/langchain-nvidia/pull/314

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v1.4.0...libs/ai-endpoints/v1.4.1

Open source →

1.4.021 May 2026

chore(deps): bump the pip group across 3 directories with 2 updates by @dependabot[bot] in https://github.com/langchain-ai/langchain-nvidia/pull/302

What's Changed

chore(deps): bump the pip group across 3 directories with 2 updates by @dependabot[bot] in https://github.com/langchain-ai/langchain-nvidia/pull/302
fix(ai-endpoints): report per-invocation model in traces by @mdrxy in https://github.com/langchain-ai/langchain-nvidia/pull/305
chore(deps): bump the pip group across 3 directories with 1 update by @dependabot[bot] in https://github.com/langchain-ai/langchain-nvidia/pull/304
Fix Feature/nvidia retriever support for RAG v2.6.0 by @shubhadeepd in https://github.com/langchain-ai/langchain-nvidia/pull/306
chore(deps): bump the pip group across 3 directories with 1 update by @dependabot[bot] in https://github.com/langchain-ai/langchain-nvidia/pull/308
release: langchain-nvidia-ai-endpoints 1.4.0 by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/309

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v1.3.0...libs/ai-endpoints/v1.4.0

Open source →

1.3.07 May 2026Deprecated

chore: add deprecation warnings for deprecated models by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/291

What's Changed

chore(deps): bump the pip group across 2 directories with 1 update by @dependabot[bot] in https://github.com/langchain-ai/langchain-nvidia/pull/277
chore(deps): bump the pip group across 2 directories with 1 update by @dependabot[bot] in https://github.com/langchain-ai/langchain-nvidia/pull/279
Fix 3 Dependabot security alerts (Pygments, orjson, requests) by @jkennedyvz in https://github.com/langchain-ai/langchain-nvidia/pull/280
chore(deps): bump aiohttp from 3.13.3 to 3.13.4 in /libs/ai-endpoints in the pip group across 1 directory by @dependabot[bot] in https://github.com/langchain-ai/langchain-nvidia/pull/281
fix: Deduplicate models from /v1/models API response by @bbednarski9 in https://github.com/langchain-ai/langchain-nvidia/pull/282
chore(deps): bump the pip group across 2 directories with 1 update by @dependabot[bot] in https://github.com/langchain-ai/langchain-nvidia/pull/283
adding glm models by @soumilinandi in https://github.com/langchain-ai/langchain-nvidia/pull/276
Support qwen/qwen3.5-122b-a10b and mistralai/mistral-small-4-119b-2603 by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/285
fix: xfail unsupported thinking-mode case on self-hosted NIM by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/286
chore(deps): bump the pip group across 3 directories with 2 updates by @dependabot[bot] in https://github.com/langchain-ai/langchain-nvidia/pull/287
chore(deps): bump the pip group across 1 directory with 3 updates by @dependabot[bot] in https://github.com/langchain-ai/langchain-nvidia/pull/288
chore(deps): bump the pip group across 1 directory with 3 updates by @dependabot[bot] in https://github.com/langchain-ai/langchain-nvidia/pull/289
chore: Add support for new models by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/292
chore: support deepseek-ai/deepseek-v4-pro and deepseek-ai/deepseek-v4-flash by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/294
feat: Support reranking VLM by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/290
chore: add deprecation warnings for deprecated models by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/291
refactor: split _NVIDIAClient into sync and async clients by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/293
bump CI poetry version and relax langchain core constraint by @soumilinandi in https://github.com/langchain-ai/langchain-nvidia/pull/295
test: fix integration tests after model deprecations and async client refactor by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/296
fix: include 'message' field in error response parsing by @vidushig-nv in https://github.com/langchain-ai/langchain-nvidia/pull/299
fix: add mistralai/ministral-3-14b-instruct-2512 to _statics.py by @vidushig-nv in https://github.com/langchain-ai/langchain-nvidia/pull/298
fix tests for ci by @soumilinandi in https://github.com/langchain-ai/langchain-nvidia/pull/297
fix package description in readme by @soumilinandi in https://github.com/langchain-ai/langchain-nvidia/pull/300

New Contributors

@bbednarski9 made their first contribution in https://github.com/langchain-ai/langchain-nvidia/pull/282
@vidushig-nv made their first contribution in https://github.com/langchain-ai/langchain-nvidia/pull/299

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v1.2.1...libs/ai-endpoints/v1.3.0

Open source →

1.2.116 Mar 2026

chore: Support nvidia/nemotron-3-super-120b-a12b by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/271

What's Changed

chore: Support nvidia/nemotron-3-super-120b-a12b by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/271
feat(ai-endpoints): add model profiles to ChatNVIDIA by @mdrxy in https://github.com/langchain-ai/langchain-nvidia/pull/261
chore(deps): bump the pip group across 2 directories with 2 updates by @dependabot[bot] in https://github.com/langchain-ai/langchain-nvidia/pull/266
update model name in readme by @soumilinandi in https://github.com/langchain-ai/langchain-nvidia/pull/273
feat: Support models that return only a reasoning field (e.g. kimi-k2.5) by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/262
feat: Support OpenAI response_format for structured output by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/272
fix: Resolve static model config for self-hosted NIMs with explicit model name by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/274
release: langchain-nvidia-ai-endpoints 1.2.1 by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/275

New Contributors

@dependabot[bot] made their first contribution in https://github.com/langchain-ai/langchain-nvidia/pull/266

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v1.2.0...libs/ai-endpoints/v1.2.1

Open source →

1.2.010 Mar 2026

ci: add minimum workflow permissions by @jkennedyvz in https://github.com/langchain-ai/langchain-nvidia/pull/253

What's Changed

ci: add minimum workflow permissions by @jkennedyvz in https://github.com/langchain-ai/langchain-nvidia/pull/253
chore: bump orjson 3.11.4 -> 3.11.7 by @jkennedyvz in https://github.com/langchain-ai/langchain-nvidia/pull/254
Add langchain-nvidia-langgraph with optimized execution strategies by @mpenn in https://github.com/langchain-ai/langchain-nvidia/pull/255
docs: update README with LangSmith development tip by @npentrel in https://github.com/langchain-ai/langchain-nvidia/pull/258
Docs update for SA swarm by @slopp in https://github.com/langchain-ai/langchain-nvidia/pull/257
feat: Add initial support for NvidiaRetriever package by @shubhadeepd in https://github.com/langchain-ai/langchain-nvidia/pull/256
Add Inference Priority Decorator for Dynamo Enabled Models by @pastorsj in https://github.com/langchain-ai/langchain-nvidia/pull/259
fix: Preserve reasoning fields in multi-turn conversation history by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/260
ci: Auto-invalidate mypy cache on version changes by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/265
chore: Support nvidia/llama-nemotron-rerank-1b-v2 by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/267
chore: xfail flaky tests and fix error status codes by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/264
chore: Rename NVIDIARetriever to NVIDIARAGRetriever by @shubhadeepd in https://github.com/langchain-ai/langchain-nvidia/pull/263
chore: Support nvidia/llama-nemotron-embed-1b-v2 by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/268
release: langchain-nvidia-ai-endpoints 1.1.1 by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/269
release: Update langchain-nvidia-ai-endpoints version to 1.2.0 by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/270

New Contributors

@mpenn made their first contribution in https://github.com/langchain-ai/langchain-nvidia/pull/255
@npentrel made their first contribution in https://github.com/langchain-ai/langchain-nvidia/pull/258
@slopp made their first contribution in https://github.com/langchain-ai/langchain-nvidia/pull/257
@shubhadeepd made their first contribution in https://github.com/langchain-ai/langchain-nvidia/pull/256

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v1.1.0...libs/ai-endpoints/v1.2.0

Open source →

1.1.025 Feb 2026

Add ChatNVIDIADynamo with Dynamo Agent Hints by @dnandakumar-nv in https://github.com/langchain-ai/langchain-nvidia/pull/245

What's Changed

Add ChatNVIDIADynamo with Dynamo Agent Hints by @dnandakumar-nv in https://github.com/langchain-ai/langchain-nvidia/pull/245
Add ChatNVIDIADynamo Example Notebook by @pastorsj in https://github.com/langchain-ai/langchain-nvidia/pull/247
fix: patch 7 security alerts (critical + high severity) by @jkennedyvz in https://github.com/langchain-ai/langchain-nvidia/pull/248
fix: patch 10 security alerts (high + medium + low) by @jkennedyvz in https://github.com/langchain-ai/langchain-nvidia/pull/249
ci: Update scheduled test to use Python >= 3.9 for trt by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/250
Refactor and simplify NVIDIA Dynamo notebook by @pastorsj in https://github.com/langchain-ai/langchain-nvidia/pull/251
release: langchain-nvidia-ai-endpoints 1.1.0 by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/252

New Contributors

@dnandakumar-nv made their first contribution in https://github.com/langchain-ai/langchain-nvidia/pull/245
@pastorsj made their first contribution in https://github.com/langchain-ai/langchain-nvidia/pull/247
@jkennedyvz made their first contribution in https://github.com/langchain-ai/langchain-nvidia/pull/248

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v1.0.4...libs/ai-endpoints/v1.1.0

Open source →

1.0.413 Feb 2026

chore: Support `stepfun-ai/step-3.5-flash` by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/240

What's Changed

chore: Support stepfun-ai/step-3.5-flash by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/240
fix: Preserve video content in message normalization by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/242
bump version by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/243
chore: Update integration test model due to temporary model unavailability by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/244

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v1.0.3...libs/ai-endpoints/v1.0.4

Open source →

1.0.328 Jan 2026

feat: Support both direct and nvext format for structured output generation by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull

What's Changed

feat: Support both direct and nvext format for structured output generation by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/238
bump version by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/239

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v1.0.2...libs/ai-endpoints/v1.0.3

Open source →

1.0.217 Jan 2026Deprecated

fix: Make thinking tag parsing backward compatible with deprecation warning by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull…

What's Changed

docs(chat): update nvidia_ai_endpoints.ipynb to match text_embedding notebook style and language by @chenopis in https://github.com/langchain-ai/langchain-nvidia/pull/230
fix: Make thinking tag parsing backward compatible with deprecation warning by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/231
bump version by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/232
fix token usage parsing in streaming mode by @soumilinandi in https://github.com/langchain-ai/langchain-nvidia/pull/234
sn/integration tests by @soumilinandi in https://github.com/langchain-ai/langchain-nvidia/pull/235

New Contributors

@chenopis made their first contribution in https://github.com/langchain-ai/langchain-nvidia/pull/230

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v1.0.1...libs/ai-endpoints/v1.0.2

Open source →

1.0.16 Jan 2026Deprecated

chore: Remove deprecated model, update test models, bump version by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/229

What's Changed

chore: fix ref docs by @mdrxy in https://github.com/langchain-ai/langchain-nvidia/pull/214
fix: resolve some griffe warnings by @mdrxy in https://github.com/langchain-ai/langchain-nvidia/pull/215
fix: lint by @mdrxy in https://github.com/langchain-ai/langchain-nvidia/pull/217
fix: Add named parameters to address Griffe documentation warnings by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/218
feat: Support async embedding/rerank/completion by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/204
docs: Edit and test pass on reranking notebook by @nkmcalli in https://github.com/langchain-ai/langchain-nvidia/pull/209
docs: Edit pass and remove too old example by @nkmcalli in https://github.com/langchain-ai/langchain-nvidia/pull/207
chore: Add support for more chat/vision models by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/220
chore: Update cookbook examples to use langchain/langgraph v1 by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/219
chore: Support moonshotai/kimi-k2-thinking and nvidia/llama-3.2-nemoretriever-300m-embed-v2 by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/222
chore: Support nvidia/nemotron-3-nano-30b-a3b by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/223
chore: Support deepseek-ai/deepseek-v3.2 by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/226
feat: Support model_kwargs to be passed in invocation payload by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/225
feat: Handle different reasoning response formats to be stored in reasoning content block by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/224
feat: Add nemotron model thinking tag mapping by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/221
fix: Update reasoning configuration for other models by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/228
chore: Remove deprecated model, update test models, bump version by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/229

New Contributors

@mdrxy made their first contribution in https://github.com/langchain-ai/langchain-nvidia/pull/214

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v1.0.0...libs/ai-endpoints/v1.0.1

Open source →

1.0.022 Nov 2025

docs: Edit pass by @nkmcalli in https://github.com/langchain-ai/langchain-nvidia/pull/203

What's Changed

docs: Edit pass by @nkmcalli in https://github.com/langchain-ai/langchain-nvidia/pull/203
Remove upper bound for a dependency by @qbarrand in https://github.com/langchain-ai/langchain-nvidia/pull/205
ci: Upgrade CI Python version for LangChain NVIDIA AI Endpoints by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/211
chore: Upgrade langchain-core to v1.0 by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/208
bump version to 1.0.0 by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/212
chore: Update integration test model due to endpoint hanging for meta/llama-3.1-8b-instruct by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/213

New Contributors

@qbarrand made their first contribution in https://github.com/langchain-ai/langchain-nvidia/pull/205

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v0.3.19...libs/ai-endpoints/v1.0.0

Open source →

0.3.1931 Oct 2025

chore: Support more chat models by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/193

What's Changed

chore: Support more chat models by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/193
fix: Fix vlm test case to not allow detail to be None by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/197
fix: Add supports_tool to meta/llama-3.2-1b-instruct by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/198
fix: Catch error object in streaming responses instead of returning empty chunks by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/201
adding default header support in chat, embedding, rerank models by @soumilinandi in https://github.com/langchain-ai/langchain-nvidia/pull/200
feat: Support async API by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/194
bump version by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/202

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v0.3.18...libs/ai-endpoints/v0.3.19

Open source →

0.3.1810 Sept 2025

feat: Support `min_tokens and ignore_eos` parameters by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/190

What's Changed

feat: Support min_tokens and ignore_eos parameters by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/190
chore: Switch structured output integration test model by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/191

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v0.3.17...libs/ai-endpoints/v0.3.18

Open source →

0.3.172 Sept 2025

remove models from list by @dglogo in https://github.com/langchain-ai/langchain-nvidia/pull/182

What's Changed

remove models from list by @dglogo in https://github.com/langchain-ai/langchain-nvidia/pull/182
fix: remove thinking content from structured output for reasoning models by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/181
fix: add structured output support to nvidia/llama-3.3-nemotron-super-49b-v1 and v1.5 by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/184
move model to vlm list by @soumilinandi in https://github.com/langchain-ai/langchain-nvidia/pull/185
docs: Edit pass and minor reorg by @nkmcalli in https://github.com/langchain-ai/langchain-nvidia/pull/187
swapping vlm model and reasoning test prompt by @soumilinandi in https://github.com/langchain-ai/langchain-nvidia/pull/188
add header for app by @soumilinandi in https://github.com/langchain-ai/langchain-nvidia/pull/186

New Contributors

@nkmcalli made their first contribution in https://github.com/langchain-ai/langchain-nvidia/pull/187

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v0.3.16...libs/ai-endpoints/v0.3.17

Open source →

0.3.168 Aug 2025

adding parsing for reasoning_content in additional_kwargs with integr… by @soumilinandi in https://github.com/langchain-ai/langchain-nvidia/pull/180

What's Changed

adding parsing for reasoning_content in additional_kwargs with integr… by @soumilinandi in https://github.com/langchain-ai/langchain-nvidia/pull/180

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v0.3.15...libs/ai-endpoints/v0.3.16

Open source →

0.3.158 Aug 2025

feat: support openai/gpt-oss-20b and openai/gpt-oss-120b by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/177

What's Changed

feat: support openai/gpt-oss-20b and openai/gpt-oss-120b by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/177
feat: backfill gaps to support more models on the api catalog by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/176

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v0.3.14...libs/ai-endpoints/v0.3.15

Open source →

0.3.145 Aug 2025

Feature/add-option-to-disable-ssl by @soumilinandi in https://github.com/langchain-ai/langchain-nvidia/pull/170

What's Changed

Feature/add-option-to-disable-ssl by @soumilinandi in https://github.com/langchain-ai/langchain-nvidia/pull/170
Add support for Llama 3.3 Nemotron Super 49b v1.5 NIM by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/171
Revert version bump by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/172
Fix/integration tests by @soumilinandi in https://github.com/langchain-ai/langchain-nvidia/pull/173
Add tool call support to llama-3.3-nemotron-super-49b v1 and v1.5 by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/174
model switch for integration tests to fix rate limit errors by @soumilinandi in https://github.com/langchain-ai/langchain-nvidia/pull/175

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v0.3.13...libs/ai-endpoints/v0.3.14

Open source →

0.3.1328 Jul 2025

feat: add support for kimi-k2-instruct by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/169

What's Changed

feat: add support for kimi-k2-instruct by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/169

New Contributors

@jiayin-nvidia made their first contribution in https://github.com/langchain-ai/langchain-nvidia/pull/169

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v0.3.12...libs/ai-endpoints/v0.3.13

Open source →

0.3.1217 Jul 2025

relax nemotron thinking warning for nvdev models by @soumilinandi in https://github.com/langchain-ai/langchain-nvidia/pull/166

What's Changed

relax nemotron thinking warning for nvdev models by @soumilinandi in https://github.com/langchain-ai/langchain-nvidia/pull/166
adding an optional param stream_options to let user disable stream_op… by @soumilinandi in https://github.com/langchain-ai/langchain-nvidia/pull/168

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v0.3.11...libs/ai-endpoints/v0.3.12

Open source →

0.3.1114 Jul 2025

Relaxed model checks by @rmkraus in https://github.com/langchain-ai/langchain-nvidia/pull/154

What's Changed

Relaxed model checks by @rmkraus in https://github.com/langchain-ai/langchain-nvidia/pull/154
Added option to skip api url checking. by @rmkraus in https://github.com/langchain-ai/langchain-nvidia/pull/153
changing raise exception to warning in test by @soumilinandi in https://github.com/langchain-ai/langchain-nvidia/pull/155
adding nvdev llama 4 model support by @soumilinandi in https://github.com/langchain-ai/langchain-nvidia/pull/157
openai spec updates by @soumilinandi in https://github.com/langchain-ai/langchain-nvidia/pull/156
fixing alias config to be able to use both field names by @soumilinandi in https://github.com/langchain-ai/langchain-nvidia/pull/159
Soumilin/max token unit tests by @soumilinandi in https://github.com/langchain-ai/langchain-nvidia/pull/161
detailed thinking/reasoning support for nemotron models by @soumilinandi in https://github.com/langchain-ai/langchain-nvidia/pull/162

New Contributors

@soumilinandi made their first contribution in https://github.com/langchain-ai/langchain-nvidia/pull/155

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v0.3.10...libs/ai-endpoints/v0.3.11

Open source →

0.3.105 May 2025

update the standard test model from llama 3.1 8b to 3.3 70b by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/135

What's Changed

update the standard test model from llama 3.1 8b to 3.3 70b by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/135
set standard test temperature to 0, address accuracy failures by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/136
Add standard imgmdr as dependency by @raspawar in https://github.com/langchain-ai/langchain-nvidia/pull/140
Scheduled CI test vlm case fix by @raspawar in https://github.com/langchain-ai/langchain-nvidia/pull/142
nvidia[patch]: support extra headers in NVIDIARerank by @ccurme in https://github.com/langchain-ai/langchain-nvidia/pull/143
Drop stream_options for qa models too. by @rmkraus in https://github.com/langchain-ai/langchain-nvidia/pull/147
add support for llama-4 models by @raspawar in https://github.com/langchain-ai/langchain-nvidia/pull/149
fix: structured_output_parsing scheduled test cases by @raspawar in https://github.com/langchain-ai/langchain-nvidia/pull/151
Updated warnings for api version check. by @rmkraus in https://github.com/langchain-ai/langchain-nvidia/pull/150
Structured Report Generation -- Structured LLM calls sometimes fail, add retry mechanism by @guilherme-pombo in https://github.com/langchain-ai/langchain-nvidia/pull/145
Structured Report Generation Elastic by @zlapp in https://github.com/langchain-ai/langchain-nvidia/pull/144

New Contributors

@rmkraus made their first contribution in https://github.com/langchain-ai/langchain-nvidia/pull/147
@guilherme-pombo made their first contribution in https://github.com/langchain-ai/langchain-nvidia/pull/145
@zlapp made their first contribution in https://github.com/langchain-ai/langchain-nvidia/pull/144

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v0.3.9...libs/ai-endpoints/v0.3.10

Open source →

0.3.94 Feb 2025

add deepseek-r1 model by @raspawar in https://github.com/langchain-ai/langchain-nvidia/pull/134

What's Changed

add deepseek-r1 model by @raspawar in https://github.com/langchain-ai/langchain-nvidia/pull/134

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v0.3.8...libs/ai-endpoints/v0.3.9

Open source →

0.3.828 Jan 2025

added NVIDIA edits by @adi0106 in https://github.com/langchain-ai/langchain-nvidia/pull/127

What's Changed

added NVIDIA edits by @adi0106 in https://github.com/langchain-ai/langchain-nvidia/pull/127
Add report-mAIstro by @rlancemartin in https://github.com/langchain-ai/langchain-nvidia/pull/123
add support for nvidia/llama-3.2-nv-embedqa-1b-v2's dimensions param by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/126
use starcoder2-15b for register_model test by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/129
record meta/llama-3.3-70b-instruct's support for tools by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/130
use llama 3.3 for tool tests to address accuracy failures from 3.1 by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/131
add chat models: qwen/qwen2.5-coder-32b-instruct, qwen/qwen2.5-coder-7b-instruct, nvidia/llama-3.1-nemotron-70b-reward by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/128
cookbook: update nims notebook to use 70b by @efriis in https://github.com/langchain-ai/langchain-nvidia/pull/119
Update agentic RAG ntbk, update README, add Studio by @rlancemartin in https://github.com/langchain-ai/langchain-nvidia/pull/120
use llama 3.3 for structured output tests to address accuracy failures from 3.1 by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/132
Remove Pillow as main dependency by @raspawar in https://github.com/langchain-ai/langchain-nvidia/pull/133

New Contributors

@adi0106 made their first contribution in https://github.com/langchain-ai/langchain-nvidia/pull/127
@rlancemartin made their first contribution in https://github.com/langchain-ai/langchain-nvidia/pull/123

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v0.3.7...libs/ai-endpoints/v0.3.8

Open source →

0.3.716 Dec 2024

add support for nvidia/llama-3.2-nv-embedqa-1b-v2 and nvidia/llama-3.2-nv-rerankqa-1b-v2 by @mattf in https://github.com/langchain-ai/langchain-nvidia

What's Changed

add support for nvidia/llama-3.2-nv-embedqa-1b-v2 and nvidia/llama-3.2-nv-rerankqa-1b-v2 by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/125

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v0.3.6...libs/ai-endpoints/v0.3.7

Open source →

0.3.614 Dec 2024

langchain-standard-tests -> langchain-tests by @efriis in https://github.com/langchain-ai/langchain-nvidia/pull/117

What's Changed

langchain-standard-tests -> langchain-tests by @efriis in https://github.com/langchain-ai/langchain-nvidia/pull/117
no more git dependencies by @efriis in https://github.com/langchain-ai/langchain-nvidia/pull/118
CI fixes by @raspawar in https://github.com/langchain-ai/langchain-nvidia/pull/124
add chat support for nvidia/usdcode-llama-3.1-70b-instruct and meta/llama-3.3-70b-instruct by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/122

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v0.3.5...libs/ai-endpoints/v0.3.6

Open source →

0.3.58 Nov 2024

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v0.3.4...libs/ai-endpoints/v0.3.5

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v0.3.4...libs/ai-endpoints/v0.3.5

Open source →

0.3.48 Nov 2024

add NVIDIARerank example to README by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/114

What's Changed

add NVIDIARerank example to README by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/114
Test cases for NIM metadata by @raspawar in https://github.com/langchain-ai/langchain-nvidia/pull/111
infra: disable pypi release attestations by @efriis in https://github.com/langchain-ai/langchain-nvidia/pull/115
infra: use artifact v4 in release pipeline by @efriis in https://github.com/langchain-ai/langchain-nvidia/pull/116

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v0.3.3...libs/ai-endpoints/v0.3.4

Open source →

0.3.325 Oct 2024

add new retriever models: nvidia/llama-3.2-nv-embedqa-1b-v1 and nvidia/llama-3.2-nv-rerankqa-1b-v1 by @mattf in https://github.com/langchain-ai/langch

What's Changed

add new retriever models: nvidia/llama-3.2-nv-embedqa-1b-v1 and nvidia/llama-3.2-nv-rerankqa-1b-v1 by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/113

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v0.3.2...libs/ai-endpoints/v0.3.3

Open source →

0.3.225 Oct 2024

allow base_url to work with proxies, e.g. http://host/proxy/path/v1 by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/112

What's Changed

allow base_url to work with proxies, e.g. http://host/proxy/path/v1 by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/112

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v0.3.1...libs/ai-endpoints/v0.3.2

Open source →

0.3.122 Oct 2024

update v0.2 to latest docs links by @efriis in https://github.com/langchain-ai/langchain-nvidia/pull/106

What's Changed

update v0.2 to latest docs links by @efriis in https://github.com/langchain-ai/langchain-nvidia/pull/106

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v0.3.0...libs/ai-endpoints/v0.3.1

Open source →

0.3.027 Sept 2024Deprecated

remove deprecated model_type param (embedding) by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/102

What's Changed

add example to rerank docs by @aviolante in https://github.com/langchain-ai/langchain-nvidia/pull/96
add hosted nim in docstring by @aviolante in https://github.com/langchain-ai/langchain-nvidia/pull/98
fix missing auth header on polling requests by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/99
feat: include usage metadata by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/94
migrate to langchain-core 0.3 (langchain_core.pydantic_v1 removal) by @baskaryan in https://github.com/langchain-ai/langchain-nvidia/pull/101
add support for vision-language model endpoints by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/100
ai-endpoints[patch]: standard tests by @efriis in https://github.com/langchain-ai/langchain-nvidia/pull/18
remove deprecated model_type param (embedding) by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/102
remove compatibility mode for nvolveqa_40k embedding model by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/103
add strict support by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/104
allow import langchain_nvidia by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/105

New Contributors

@aviolante made their first contribution in https://github.com/langchain-ai/langchain-nvidia/pull/96
@baskaryan made their first contribution in https://github.com/langchain-ai/langchain-nvidia/pull/101

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v0.2.2...libs/ai-endpoints/v0.3.0

Open source →

0.2.229 Aug 2024

Quick improvement to langgraph example by @haydeniw in https://github.com/langchain-ai/langchain-nvidia/pull/87

What's Changed

Quick improvement to langgraph example by @haydeniw in https://github.com/langchain-ai/langchain-nvidia/pull/87
update default models by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/89
Fix: Raise a warning for known endpoints by @raspawar in https://github.com/langchain-ai/langchain-nvidia/pull/93
add Completions API support by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/88
bug: fix stream collection by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/95
fix failing test cases for base url by @raspawar in https://github.com/langchain-ai/langchain-nvidia/pull/97

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v0.2.1...libs/ai-endpoints/v0.2.2

Open source →

0.2.17 Aug 2024

Added tool calling notebook by @haydeniw in https://github.com/langchain-ai/langchain-nvidia/pull/77

What's Changed

Added tool calling notebook by @haydeniw in https://github.com/langchain-ai/langchain-nvidia/pull/77
ai-endpoints: remove langchain-community dependency by @efriis in https://github.com/langchain-ai/langchain-nvidia/pull/78
chat nb update with tool calling and upstream changes by @dglogo in https://github.com/langchain-ai/langchain-nvidia/pull/80
update nvidia.mdx file for stale links by @dglogo in https://github.com/langchain-ai/langchain-nvidia/pull/83
Validation for base_url by @raspawar in https://github.com/langchain-ai/langchain-nvidia/pull/68
Enable base_url to read from env variables by @kylehh in https://github.com/langchain-ai/langchain-nvidia/pull/65
add with_structured_output support for Pydantic models, dicts and Enum by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/79
Client rejects incompatible models by @raspawar in https://github.com/langchain-ai/langchain-nvidia/pull/81
various internal improvements by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/82
support pydantic v2 and v1 for with_structured_output by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/84
Update min version for langchain-core by @raspawar in https://github.com/langchain-ai/langchain-nvidia/pull/85

New Contributors

@haydeniw made their first contribution in https://github.com/langchain-ai/langchain-nvidia/pull/77
@kylehh made their first contribution in https://github.com/langchain-ai/langchain-nvidia/pull/65

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v0.2.0...libs/ai-endpoints/v0.2.1

Open source →

0.2.023 Jul 2024

add chat tool calling by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/74

What's Changed

add chat tool calling by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/74

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v0.1.7...libs/ai-endpoints/v0.2.0

Open source →

0.1.723 Jul 2024

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v0.1.6...libs/ai-endpoints/v0.1.7

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v0.1.6...libs/ai-endpoints/v0.1.7

Open source →

0.1.619 Jul 2024

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v0.1.5...libs/ai-endpoints/v0.1.6

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v0.1.5...libs/ai-endpoints/v0.1.6

Open source →

0.1.519 Jul 2024

update default chat model to meta/llama3-8b-instruct (most features & deployment options) by @mattf in https://github.com/langchain-ai/langchain-nvidi

What's Changed

update default chat model to meta/llama3-8b-instruct (most features & deployment options) by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/73
add support for reranking api change w/ truncate parameter by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/75

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v0.1.4...libs/ai-endpoints/v0.1.5

Open source →

0.1.416 Jul 2024

skip nvolveqa_40k compat test when run against local nim by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/70

What's Changed

skip nvolveqa_40k compat test when run against local nim by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/70
Scheduled test cases fix by @raspawar in https://github.com/langchain-ai/langchain-nvidia/pull/71
update ranking nim support for nims w/ /v1/models and multiple names by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/69

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v0.1.3...libs/ai-endpoints/v0.1.4

Open source →

0.1.39 Jul 2024

make stop property functional by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/52

What's Changed

make stop property functional by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/52
add scheduled tests by @ccurme in https://github.com/langchain-ai/langchain-nvidia/pull/53
Name scheduled test run by @efriis in https://github.com/langchain-ai/langchain-nvidia/pull/54
nim docs model name update by @dglogo in https://github.com/langchain-ai/langchain-nvidia/pull/55
no models support steerlm params, removing references by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/56
add rerank example using duckduckgo, bm25 and faiss by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/47
Fix for failing lint workflow by @raspawar in https://github.com/langchain-ai/langchain-nvidia/pull/58
Provide default model in local NIM mode by @raspawar in https://github.com/langchain-ai/langchain-nvidia/pull/51
Fix bug in Embedding/Rerank default model by @raspawar in https://github.com/langchain-ai/langchain-nvidia/pull/60
refactor payload preprocessing by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/61
refactor payload preprocessing (continued) by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/62
ai-endpoints[patch]: add mypy overrides by @ccurme in https://github.com/langchain-ai/langchain-nvidia/pull/64
add register_model for users to add their own custom models with endpoints [api change; expansion] by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/57
release permissions by @efriis in https://github.com/langchain-ai/langchain-nvidia/pull/66
remove broken stop word detection, rely on server side implementation by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/63

New Contributors

@ccurme made their first contribution in https://github.com/langchain-ai/langchain-nvidia/pull/53

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v0.1.2...libs/ai-endpoints/v0.1.3

Open source →

0.1.212 Jun 2024

Fix for NVIDIAClient output to redact the api_key by @raspawar in https://github.com/langchain-ai/langchain-nvidia/pull/50

What's Changed

Fix for NVIDIAClient output to redact the api_key by @raspawar in https://github.com/langchain-ai/langchain-nvidia/pull/50

New Contributors

@raspawar made their first contribution in https://github.com/langchain-ai/langchain-nvidia/pull/50

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v0.1.1...libs/ai-endpoints/v0.1.2

Open source →

0.1.14 Jun 2024

make connectors use user provided base_url when the provided model is also hosted by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/4

What's Changed

make connectors use user provided base_url when the provided model is also hosted by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/49

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v0.1.0...libs/ai-endpoints/v0.1.1

Open source →

0.1.031 May 2024

chore(deps): bump the pip group across 3 directories with 3 updates by @dependabot[bot] in https://github.com/langchain-ai/langchain-nvidia/pull/322

What's Changed

chore(deps): bump the pip group across 3 directories with 3 updates by @dependabot[bot] in https://github.com/langchain-ai/langchain-nvidia/pull/322
chore: add more model configs to static list by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/326
Enable OpenShell as a Sandbox Provider by @pastorsj in https://github.com/langchain-ai/langchain-nvidia/pull/303
Revert "Enable OpenShell as a Sandbox Provider" by @pastorsj in https://github.com/langchain-ai/langchain-nvidia/pull/327
Enable OpenShell as a Sandbox Provider by @pastorsj in https://github.com/langchain-ai/langchain-nvidia/pull/330
fix: use Python 3.12 for release workflows by @jiayin-nvidia in https://github.com/langchain-ai/langchain-nvidia/pull/332
fix: publish TestPyPI releases from the parent workflow by @soumilinandi in https://github.com/langchain-ai/langchain-nvidia/pull/335

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v1.4.2...libs/openshell/v0.1.0

Open source →

Additional notes

What's Changed

update to 0.1, remove deprecated functionality and focus on api catalog backend by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/48

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v0.0.20...libs/ai-endpoints/v0.1.0

this is version 0.1.0 of the connectors with two primary changes -

[user visible] deprecated or unavailable functionality removed
[not use visible] use of api catalog (integrate.api.nvidia.com and ai.api.nvidia.com) instead of nvcf (api.nvcf.nvidia.com) for inference

all playground_* model endpoints have been decommissioned.

functionality removed -

models: playground_mamba_chat, playground_smaug_72b, playground_nemotron_qa_8b, playground_nemotron_steerlm_8b, playground_steerlm_llama_70b, playground_yi_34b, playground_nvolveqa_40k
methods: available_functions, get_available_functions, get_model_details, get_binding_model, mode, validate_model, validate_base_url, reset_method_cache, validate_client, aifm_deprecated, aifm_bad_deprecated, aifm_labels_deprecated, custom_preprocess, preprocess_msg, custom_postprocess, get_generation, get_stream, get_astream, get_payload, prep_payload, prep_msg, deprecate_max_length
properties: ChatNVIDIA.bad, ChatNVIDIA.labels, ChatNVIDIA.infer_endpoint, ChatNVIDIA.client, ChatNVIDIA.streaming, NVIDIAEmbeddings.infer_endpoint, NVIDIAEmbeddings.client, NVIDIAEmbeddings.max_length

functionality deprecated -

NVIDIAEmbeddings.model_type, instead of setting model_type="query" or "passage" use NVIDIAEmbeddings.embed_query and NVIDIAEmbeddings.embed_documents

migration guide -

ChatNVIDIA().mode("nim", base_url="http://...") must use ChatNVIDIA(base_url="http://...")
NVIDIAEmbeddings().mode("nim", base_url="http://...") must use NVIDIAEmbeddings(base_url="http://...")
NVIDIARerank().mode("nim", base_url="http://...") must use NVIDIARerank(base_url="http://...")
compatibility for the playground_nvolveqa_40k (aka nvolveqa_40k) model. when specifying model="nvolveqa_40k", the NV-Embed-QA model will be used and truncate="END" will be set. note: the old nvolveqa_40k model endpoint would silently truncated input while all available endpoints raise an error instead of truncating.

model migration, the following models will raise a warning and use an alternative (model changes in italics) -

model	alternative
playground_llama2_13b	meta/llama2-70b
playground_llama2_code_13b	meta/codellama-70b
playground_llama2_code_34b	meta/codellama-70b
playground_nv_llama2_rlhf_70b	meta/llama2-70b
playground_phi2	microsoft/phi-3-mini-4k-instruct
playground_llama2_code_70b	meta/codellama-70b
playground_gemma_2b	google/gemma-2b
playground_gemma_7b	google/gemma-7b
playground_llama2_70b	meta/llama2-70b
playground_mistral_7b	mistralai/mistral-7b-instruct-v0.2
playground_mixtral_8x7b	mistralai/mixtral-8x7b-instruct-v0.1
playground_deplot	google/deplot
playground_fuyu_8b	adept/fuyu-8b
playground_kosmos_2	microsoft/kosmos-2
playground_neva_22b	nvidia/neva-22b
playground_nvolveqa_40k	NV-Embed-QA

Open source →

0.0.2030 May 2024

fix pypi links by @efriis in https://github.com/langchain-ai/langchain-nvidia/pull/45

What's Changed

fix pypi links by @efriis in https://github.com/langchain-ai/langchain-nvidia/pull/45
Dglog/docs updates 2 by @dglogo in https://github.com/langchain-ai/langchain-nvidia/pull/46
cookbook: add langgraph nim demo by @efriis in https://github.com/langchain-ai/langchain-nvidia/pull/42

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v0.0.19...libs/ai-endpoints/v0.0.20

Open source →

0.0.1928 May 2024

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v0.0.18...libs/ai-endpoints/v0.0.19

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v0.0.18...libs/ai-endpoints/v0.0.19

Open source →

0.0.1824 May 2024Deprecated

Deprecate mode() in favor of __init__(base_url=...) by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/43

What's Changed

Deprecate mode() in favor of init(base_url=...) by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/43

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v0.0.17...libs/ai-endpoints/v0.0.18

Open source →

0.0.1721 May 2024

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v0.0.16...libs/ai-endpoints/v0.0.17

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v0.0.16...libs/ai-endpoints/v0.0.17

Open source →

0.0.1617 May 2024

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v0.0.15...libs/ai-endpoints/v0.0.16

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v0.0.15...libs/ai-endpoints/v0.0.16

Open source →

0.0.1514 May 2024

available_models must only return known models by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/39

What's Changed

available_models must only return known models by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/39
loosen core dep to tolerate 0.2 by @efriis in https://github.com/langchain-ai/langchain-nvidia/pull/40

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v0.0.14...libs/ai-endpoints/v0.0.15

Open source →

0.0.149 May 2024

vanity model name support by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/35

What's Changed

vanity model name support by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/35
updated docs by @dglogo in https://github.com/langchain-ai/langchain-nvidia/pull/36
clean nb output by @dglogo in https://github.com/langchain-ai/langchain-nvidia/pull/37
set default max_tokens to 1024 by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/38

New Contributors

@dglogo made their first contribution in https://github.com/langchain-ai/langchain-nvidia/pull/36

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v0.0.13...libs/ai-endpoints/v0.0.14

Open source →

0.0.137 May 2024

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v0.0.12...libs/ai-endpoints/v0.0.13

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v0.0.12...libs/ai-endpoints/v0.0.13

Open source →

0.0.121 May 2024

add NVIDIARerank support for a local NIM by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/23

What's Changed

add NVIDIARerank support for a local NIM by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/23

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v0.0.11...libs/ai-endpoints/v0.0.12

Open source →

0.0.1125 Apr 2024

ai-llama3-8b: meta/llama3-8b -> meta/llama3-8b-instruct

Server-side model changes:

ai-llama3-8b: meta/llama3-8b -> meta/llama3-8b-instruct
ai-llama3-70b: meta/llama3-70b -> meta/llama3-70b-instruct
ai-phi-3-mini: microsoft/phi-3-mini -> microsoft/phi-3-mini-128k-instruct

If you are using any of these models you do not need to change your code, but you must upgrade.

Open source →

0.0.1024 Apr 2024

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v0.0.9...libs/ai-endpoints/v0.0.10

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v0.0.9...libs/ai-endpoints/v0.0.10

Open source →

0.0.923 Apr 2024

add truncate parameter for shortening inputs to match model token length limits by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/22

What's Changed

add truncate parameter for shortening inputs to match model token length limits by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/22
add NVIDIARerank connector, a BaseDocumentCompressor, with support for NVIDIA API Catalog by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/19
allow pickling of NVIDIAEmbeddings by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/25

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v0.0.8...libs/ai-endpoints/v0.0.9

Open source →

0.0.818 Apr 2024

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v0.0.7...libs/ai-endpoints/v0.0.8

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v0.0.7...libs/ai-endpoints/v0.0.8

Open source →

0.0.717 Apr 2024

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v0.0.6...libs/ai-endpoints/v0.0.7

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v0.0.6...libs/ai-endpoints/v0.0.7

Open source →

0.0.610 Apr 2024

ci: add master core install for lint/test/dev by @efriis in https://github.com/langchain-ai/langchain-nvidia/pull/17

What's Changed

ci: add master core install for lint/test/dev by @efriis in https://github.com/langchain-ai/langchain-nvidia/pull/17

New Contributors

@efriis made their first contribution in https://github.com/langchain-ai/langchain-nvidia/pull/17

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v0.0.5...libs/ai-endpoints/v0.0.6

Open source →

0.0.55 Apr 2024

add tests for NVIDIAEmbeddings().mode("nim", base_url="http://.../v1") support by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/16

What's Changed

add tests for NVIDIAEmbeddings().mode("nim", base_url="http://.../v1") support by @mattf in https://github.com/langchain-ai/langchain-nvidia/pull/16

Full Changelog: https://github.com/langchain-ai/langchain-nvidia/compare/libs/ai-endpoints/v0.0.5-rc0...libs/ai-endpoints/v0.0.5

Open source →

Your coding agent can read these notes before it upgrades. Set up the MCP server →