search

GoogleCloudPlatform / genai-databases-retrieval-app

Apache License 2.0
212 stars 72 forks source link

deps: Update langchain - abandoned #387

Closed renovate-bot closed 5 months ago

renovate-bot commented 6 months ago

Mend Renovate

This PR contains the following updates:

Package Change Age Adoption Passing Confidence
google-cloud-aiplatform ==1.47.0 -> ==1.51.0 age adoption passing confidence
langchain ==0.1.16 -> ==0.2.0 age adoption passing confidence
langchain-core ==0.1.43 -> ==0.2.0 age adoption passing confidence
langchain-google-vertexai ==1.0.1 -> ==1.0.4 age adoption passing confidence

Release Notes

googleapis/python-aiplatform (google-cloud-aiplatform) ### [`v1.51.0`](https://togithub.com/googleapis/python-aiplatform/blob/HEAD/CHANGELOG.md#1510-2024-05-10) [Compare Source](https://togithub.com/googleapis/python-aiplatform/compare/v1.50.0...v1.51.0) ##### Features - Add FeatureGroup create function ([3938107](https://togithub.com/googleapis/python-aiplatform/commit/393810728b6b940e4cc8e1ac7f55875e3b750beb)) - Add FeatureGroup init/get ([e47d436](https://togithub.com/googleapis/python-aiplatform/commit/e47d436f24cc718e378a28c4a80293778e8c183a)) - Add support for BaseModels in LangChain templates ([5eb885e](https://togithub.com/googleapis/python-aiplatform/commit/5eb885ee7e01eece15679ce400f222930da1ac16)) - Added the `vision_models.Image._mime_type` property to make `vision_models.Image` compatible with `generative_models.Image` ([6557d88](https://togithub.com/googleapis/python-aiplatform/commit/6557d88eb73624c8dbc7da33db129f7cbdae8a06)) - AutoSxS Pairwise Metric in Rapid Evaluation SDK ([b0c5eda](https://togithub.com/googleapis/python-aiplatform/commit/b0c5eda79489d4b32972b2acea647e3c8cdc3ce9)) - GenAI - Grounding - Released Google Web Search retriever to GA ([32b030a](https://togithub.com/googleapis/python-aiplatform/commit/32b030a629a20d0557dba011df2658f46c199820)) - GenAI - Tuning - Supervised - Added support for the `adapter_size` parameter ([88188d2](https://togithub.com/googleapis/python-aiplatform/commit/88188d294fc2ec55ec0b05640dc791a1a3a88255)) - LLM - Made the tuning location parameters truly optional ([bae8429](https://togithub.com/googleapis/python-aiplatform/commit/bae8429ae078c69574d86280ae6c784aaa9b13b5)) - LLM - Support tuning of new text embedding models by migrating to the new v1.1.3 pipeline. ([7fea754](https://togithub.com/googleapis/python-aiplatform/commit/7fea7547084277dc974cbacc517ca1e95629a034)) - LLM - Text embedding - Added the `output_dimensionality` and `learning_rate_multiplier` parameters to text embedding tuning (Preview only) ([cc8bc96](https://togithub.com/googleapis/python-aiplatform/commit/cc8bc965932efb68a30db9decb5a24cf597b0d8b)) - LLM - Text Embedding - Added validation for text embedding tuning parameters. ([5a300c1](https://togithub.com/googleapis/python-aiplatform/commit/5a300c1071fa1492502cfde95700e1b171cdfbfc)) - Release Ray on Vertex SDK to GA ([f7c5132](https://togithub.com/googleapis/python-aiplatform/commit/f7c51327c49d000cc79d56bb5333ed7fea28fa01)) - Support custom service account for Ray cluster creation and Ray Client connection ([e0c6227](https://togithub.com/googleapis/python-aiplatform/commit/e0c6227d0dd92d83c98cc3c7e7607fd252e74a32)) - Support vector_distance_threshold filtering and file-based retrieval for RAG ([cd85d8f](https://togithub.com/googleapis/python-aiplatform/commit/cd85d8f74d3922de3f871415bacf77c594f0c547)) ##### Bug Fixes - A bug in the evaluation library where the job crashes if only custom metrics are specified. ([c528b6f](https://togithub.com/googleapis/python-aiplatform/commit/c528b6ff44e2347797336db800ca01240e670d32)) - Add DeprecationWarning to vertexai.preview predictive models SDK ([3c3727b](https://togithub.com/googleapis/python-aiplatform/commit/3c3727b48ce4ba12bdaf36806cda4907a788d38e)) - Add MAX_TOKENS to the list of successful finish reasons for Rapid Evaluation SDK ([195c77e](https://togithub.com/googleapis/python-aiplatform/commit/195c77ed7320aea3ab5899427a922d606ed78997)) - AttributeError for TorchModelSerializer.deserialize in torch >=2.3.0 ([20b1866](https://togithub.com/googleapis/python-aiplatform/commit/20b18668f15c448813aad4f58f2a4d470d6da2ec)) - GenAI - Fixed handling of multiple tools in `AutomaticFunctionCallingResponder` ([58e6ac9](https://togithub.com/googleapis/python-aiplatform/commit/58e6ac9b14daa42dc64d787156070c22bd7a1655)) - Remove InternalServerError and Unknown evaluation service error from retriable exceptions ([12c147b](https://togithub.com/googleapis/python-aiplatform/commit/12c147b1f3e127c925b6c42b7dbbd4e949ff8e98)) - Upload the reference model in model registry ([510c833](https://togithub.com/googleapis/python-aiplatform/commit/510c8334961cdb6f801863ecbd8fe49bf69b6c68)) ### [`v1.50.0`](https://togithub.com/googleapis/python-aiplatform/blob/HEAD/CHANGELOG.md#1500-2024-05-02) [Compare Source](https://togithub.com/googleapis/python-aiplatform/compare/v1.49.0...v1.50.0) ##### Features - Add `Candidate.grounding_metadata` property ([b22a8b8](https://togithub.com/googleapis/python-aiplatform/commit/b22a8b847e3b299b828e37405e3678093486de28)) - Add option to not include time_series_metrics in get_experiment_df call. This will improve execution time for Experiments with large number of runs. ([78a95c5](https://togithub.com/googleapis/python-aiplatform/commit/78a95c52d0e7bd9ec5b656ce67044b2f01677156)) - Add tune_model and deploy_tuned_model for TextEmbeddingModel. ([42f5d6f](https://togithub.com/googleapis/python-aiplatform/commit/42f5d6f7cd13d51c4a73113c59e8b3c728cfc08b)) - Automatically populate parents for full resource name in Vertex RAG SDK ([26657ff](https://togithub.com/googleapis/python-aiplatform/commit/26657ffd25ecb91882ca764e513c2e952833257f)) - Deploy a tuned text embedding model -- it doesn't matter, if it's tuned using Node.js, or curl. ([8ca9cdf](https://togithub.com/googleapis/python-aiplatform/commit/8ca9cdf3576e3ce3b373ace4cd6ab0e9c54aa9f2)) - Make get_embeddings work both for foundational & tuned models. ([b8b589c](https://togithub.com/googleapis/python-aiplatform/commit/b8b589ce9fff29d1721450d32b4a84a7f69413c3)) - Python SDK for Vertex Model Monitoring V2. ([021d59f](https://togithub.com/googleapis/python-aiplatform/commit/021d59f1487e4e16c847d4135899d6845c0210aa)) - Support public endpoint for Ray Client ([57a5f78](https://togithub.com/googleapis/python-aiplatform/commit/57a5f7815ffb8523e91d900da4ff7cfd0c344fe4)) ##### Bug Fixes - Add deprecation warnings when using Ray v2.4 ([3a36784](https://togithub.com/googleapis/python-aiplatform/commit/3a367843840513e3257610c8ab38e9f79d3bcea0)) - Append allowed_plugins in tb-gcp-uploader to default allowed plugins ([aab9c3e](https://togithub.com/googleapis/python-aiplatform/commit/aab9c3e41b92a1d60090e3d1d594390a5e9f3ff6)) - LLM - Added missing parameters to the no-op `_TunableTextEmbeddingModelMixin.get_tuned_model` method ([eb05ac4](https://togithub.com/googleapis/python-aiplatform/commit/eb05ac421f186441a92c6e3b6a010d74caf14782)) - LVM - Fixed the typo in the VisionModel aspect ratio type annotation ([2d19137](https://togithub.com/googleapis/python-aiplatform/commit/2d1913773cf9f4a4f8a2c8c8f45680c3ea97f68e)) - Move torch import ([e6d34df](https://togithub.com/googleapis/python-aiplatform/commit/e6d34df7da7508c655eb17ee694e1ab2160fc8aa)) - Ray - Fixed exception when using Ray 2.4 ([2661f52](https://togithub.com/googleapis/python-aiplatform/commit/2661f52fd08169e5d29b58f2afce9702b30101ae)) ### [`v1.49.0`](https://togithub.com/googleapis/python-aiplatform/blob/HEAD/CHANGELOG.md#1490-2024-04-27) [Compare Source](https://togithub.com/googleapis/python-aiplatform/compare/v1.48.0...v1.49.0) ##### Features - Add additional parameters for `GenerationConfig` ([0599ca1](https://togithub.com/googleapis/python-aiplatform/commit/0599ca18342aece9d8b9b35534294de541593ef9)) - Add FeatureNormType to `MatchingEngineIndexConfig`. ([c0e7acc](https://togithub.com/googleapis/python-aiplatform/commit/c0e7acc27e67ef1a951bb4bd97f489164dda14f9)) - Add mappings to pipeline templates for text-embedding models. ([6279924](https://togithub.com/googleapis/python-aiplatform/commit/627992484ec16fbf7fdfc9c963046e10e3d7c6bf)) - Add support for TPU v5 lite pod(v5e) for custom training jobs. Custom training jobs now accept the v5e machine types as listed in https://cloud.google.com/tpu/docs/tpus-in-gke#v5e. ([415912e](https://togithub.com/googleapis/python-aiplatform/commit/415912e9258d2b960c7da730902d7f15116cc474)) - Fix typo in Vertex Feature Store SDK. ([b5404e7](https://togithub.com/googleapis/python-aiplatform/commit/b5404e7106059358dd7fcd21d487e5e31ed4d128)) - GenAI - Improved the exception messages when candidates, parts or text are not available ([e82264d](https://togithub.com/googleapis/python-aiplatform/commit/e82264d273e35d3b305d434181badfb63a37c79c)) - Support PreflightValidation in Preview PipelineJob submit function. ([e88dc0d](https://togithub.com/googleapis/python-aiplatform/commit/e88dc0d65ffaed3de9850e8eaadbfa41eb769e06)) - Tune_model method for class TextEmbeddingModel. ([3eda55d](https://togithub.com/googleapis/python-aiplatform/commit/3eda55d25a8e3816eec0fb3c43f7c16c8a2d9b32)) - Vertex RAG for enhanced generative AI ([39b5149](https://togithub.com/googleapis/python-aiplatform/commit/39b5149c18355a233dae7ada2f18c8072a6b59f1)) ##### Bug Fixes - GCS Bucket subdirectory not being creating while using ReasoningEngine create method ([3d22a18](https://togithub.com/googleapis/python-aiplatform/commit/3d22a18abdacc7cb53d4b5fef941fa1a34caec08)) - GenAI - Fixed the `Part.mime_type` property ([819a44e](https://togithub.com/googleapis/python-aiplatform/commit/819a44ea9b624912c31843881fd6130febb8ec57)) - Handle missing import for RunnableConfig when generating schema for LangChain templates ([76c5d6d](https://togithub.com/googleapis/python-aiplatform/commit/76c5d6d6e99be5e7a8ec81e85aa383b1a39fef66)) - Parse intermediate steps from LangChain into JSON. ([754c89d](https://togithub.com/googleapis/python-aiplatform/commit/754c89d8514dde707255bf0e3602dfddff49f268)) - Register TensorFlow models from Ray checkpoints for more recent TensorFlow version, addressing the deprecation of SavedModel format in keras 3 ([1341e2c](https://togithub.com/googleapis/python-aiplatform/commit/1341e2c57907f7867d4237e84c5bb9b77e5dd5f5)) - Tensorboard uploader - move remaining tensorboard uploader code to aiplatform ([f34094b](https://togithub.com/googleapis/python-aiplatform/commit/f34094b50ea161c2b9f0653be8b5931e922bb8f6)) ### [`v1.48.0`](https://togithub.com/googleapis/python-aiplatform/blob/HEAD/CHANGELOG.md#1480-2024-04-17) [Compare Source](https://togithub.com/googleapis/python-aiplatform/compare/v1.47.0...v1.48.0) ##### Features - Add support for reading requirements from a file. ([80db7a0](https://togithub.com/googleapis/python-aiplatform/commit/80db7a0960b80ae0d78182687c1e99db696943f7)) - Adding tpu_topology to Vertex SDK ([423c764](https://togithub.com/googleapis/python-aiplatform/commit/423c7646185b4df19985fb41f5776557d572dd9f)) - Enable continuous upload for profile logs. ([f05924d](https://togithub.com/googleapis/python-aiplatform/commit/f05924d6bbd9e609f4ca98cdef7ab5a504672e58)) - GenAI - Added the `GenerationResponse.prompt_feedback` property ([efd5a72](https://togithub.com/googleapis/python-aiplatform/commit/efd5a72c1856a6767bdbbba9ea83f366518bdac2)) - GenAI - Added the `GenerationResponse.usage_metadata` property ([0654c35](https://togithub.com/googleapis/python-aiplatform/commit/0654c3504425d9f9bba6e3be919026229b616ec0)) - Support `NOT_EQUAL` for `MatchingEngineIndexEndpoint` `numeric_restricts`. ([aa918e3](https://togithub.com/googleapis/python-aiplatform/commit/aa918e31fcc40878e9f29affa02a4527d90188aa)) - Support referenced models in SDK. ([c9b6b8b](https://togithub.com/googleapis/python-aiplatform/commit/c9b6b8b3433854afd95a27065a052393768ceca8)) ##### Bug Fixes - Add validation check for extra_packages when creating a reasoning engine. ([255dabc](https://togithub.com/googleapis/python-aiplatform/commit/255dabc77c647ef3ac33a10b06b3a36db122118a)) - Add validation for langchain tools. ([a821d50](https://togithub.com/googleapis/python-aiplatform/commit/a821d50724da7136c90abd157a7086d6571f2c30)) - Fixed the vertexai.init partial initialization issues ([636a654](https://togithub.com/googleapis/python-aiplatform/commit/636a654590919048f84baf343d291711f28eb03e)) - GenAI - Workaround for streaming when content role is missing in service responses ([fa35b91](https://togithub.com/googleapis/python-aiplatform/commit/fa35b9169677c62a5f0fa746dc9db9a5296f44a3)) ##### Documentation - Add Reasoning Engine reference documentation ([496fc4b](https://togithub.com/googleapis/python-aiplatform/commit/496fc4b96768c872c9e7312bacf9989ea6e979f5)) - GenAI - Add Rapid Evaluation SDK reference documentation ([40b728b](https://togithub.com/googleapis/python-aiplatform/commit/40b728b28210f2bc57374c6c6d507cf3fa0be038))

Configuration

📅 Schedule: Branch creation - At any time (no schedule defined), Automerge - At any time (no schedule defined).

🚦 Automerge: Disabled by config. Please merge this manually once you are satisfied.

♻ Rebasing: Never, or you tick the rebase/retry checkbox.

👻 Immortal: This PR will be recreated if closed unmerged. Get config help if that's undesired.

This PR has been generated by Mend Renovate. View repository job log here.

dpebot commented 5 months ago

/gcbrun

Yuan325 commented 5 months ago

/gcbrun

forking-renovate[bot] commented 5 months ago

Edited/Blocked Notification

Renovate will not automatically rebase this PR, because it does not recognize the last commit author and assumes somebody else may have edited the PR.

You can manually request rebase by checking the rebase/retry box above.

⚠️ Warning: custom changes will be lost.

forking-renovate[bot] commented 5 months ago

Autoclosing Skipped

This PR has been flagged for autoclosing. However, it is being skipped due to the branch being already modified. Please close/delete it manually or report a bug if you think this is in error.