Releases: mindsdb/mindsdb
v24.6.1.1
What's Changed
- SQL Completions Hotfixes by @tmichaeldb in #9246
- migrate rag handler to pydantic v2 by @dusvyat in #9292
- Fixed Dremo Get Methods and Query Process by @MinuraPunchihewa in #9291
- updated commands to install deps by @martyna-mindsdb in #9290
- Mindsdb optimizations by @ea-rus in #9243
- Fix add database via form by @ea-rus in #9296
- Fix: select from native query with no data by @ea-rus in #9302
- Release fixes by @ea-rus in #9303
- Copy code over to permit local handler installs in docker containers by @hamishfagg in #9287
- Add Langfuse Traces for LLM Chains & Tool Usage by @tmichaeldb in #9297
- Improve SQL Completion Latency by 5s by @tmichaeldb in #9304
Full Changelog: v24.6.1.0...v24.6.1.1
v24.6.1.0
This release includes a variety of updates and fixes. The existing integrations were updated, including LangChain, OpenAI, and Anyscale. Issues related to the Pydantic version have been resolved. And, the documentation for REST API endpoints supporting file uploads has been added.
What's Changed
- Fix dependency installs for tests by @hamishfagg in #9239
- Upgraded Flask Version by @MinuraPunchihewa in #9232
- Fixed Pydantic Import for field_validator in RAG and Writer by @MinuraPunchihewa in #9244
- Update Langchain Community Chat Model Name Params by @tmichaeldb in #9237
- Update references to sample databases by @lucas-koontz in #9248
- Remove handler discovery by @ZoranPandovski in #9251
- added docs for rest api for files by @martyna-mindsdb in #9253
- Check for domain in allowed list by @ZoranPandovski in #9252
- updated mongodb sdk to api by @martyna-mindsdb in #9258
- Default http_error messages by @ZoranPandovski in #9268
- OpenAI Integration Improvements by @MinuraPunchihewa in #9225
- Added Anyscale Unit Tests to the Workflow by @MinuraPunchihewa in #9279
- Mongo updates by @ZoranPandovski in #9274
- Upgrade requests by @ZoranPandovski in #9280
- Update about.py by @ZoranPandovski in #9288
Full Changelog: v24.5.4.0...v24.6.1.0
v24.5.4.0
This release includes several important updates and improvements:
- Updates and fixes to existing integrations, including LangChain, Vertex AI, ChromaDB, MindsDB Inference, and more.
- Enhanced test coverage for greater reliability.
- A schema refactor that includes changes to the structure for storing metadata of all objects like models, views, tables, etc.
- Bug fixes to the SQL API, including improvements to the LAST keyword.
All relevant updates have been accompanied by corresponding documentation updates.
What's Changed
- removing redundant package lists and sentence-transformers library by @QuantumPlumber in #8971
- Safe extraction for all tar files by @StpMax in #8928
- Fix tarfile safe extract by @StpMax in #9000
- Refactor Langchain Handler by @tmichaeldb in #8998
- Tests for sql features by @ea-rus in #8952
- Update query format in quickstart-tutorial.mdx by @vlad-ro in #9011
- [404] fix url in huggingface_inference_api.mdx by @ArnavK-09 in #9016
- Fix hardcoded API base by @ZoranPandovski in #9019
- Added Check for Import Errors When Running CREATE MODEL Statement by @MinuraPunchihewa in #9020
- updated hostname of sample dbs by @martyna-mindsdb in #9025
- Fixed Installation of Dependencies for Integrations That Refer to Other requirements.txt Files by @MinuraPunchihewa in #9022
- fixed slack chatbot tutorial by @martyna-mindsdb in #9026
- Fix delete from table in database by @ea-rus in #9017
- Added File Path and URL Support to the Vertex AI Integration by @MinuraPunchihewa in #9007
- clean up handler install log messages by @hamishfagg in #8720
- Docker build improvements by @hamishfagg in #8999
- Add 'seed db' function to MSSQL tests by @hamishfagg in #8742
- Fixed Installation of Dependencies for Integrations That Refer to requirements.txt Files (Docker-supported) by @MinuraPunchihewa in #9034
- Fixed Installation of Dependencies When requirements.txt Files Contain Comments by @MinuraPunchihewa in #9038
- Fixed the Initializer for the EventStoreDB Integration by @MinuraPunchihewa in #9029
- Fixed Unused Imports and Dependencies in Rockset Integration by @MinuraPunchihewa in #9031
- updated email integration docs by @martyna-mindsdb in #9035
- Make alembic use mindsdb log level by @hamishfagg in #9028
- Bump version for release by @hamishfagg in #9041
- Fix LAST with slack by @ea-rus in #9036
- Updated LightFM Integration Docs with Tip to Install Linux Dev Pakcages by @MinuraPunchihewa in #9042
- updated ollama docs by @martyna-mindsdb in #8995
- Updated Snowflake Integration Docs with Tip to Install Git by @MinuraPunchihewa in #9032
- Add RAG model and utilities for Mindsdb integration by @dusvyat in #8996
- Update requirements.txt by @martyna-mindsdb in #9048
- Update requirements.txt by @martyna-mindsdb in #9050
- update sampledatabases to new k8s server by @lucas-koontz in #8986
- The "database" field in the form is changed to not required. by @alejandrovillegas in #9052
- Fixed Column Structure of chat_messages Table by @MinuraPunchihewa in #9015
- Fix BYOM engine create by @StpMax in #9054
- updated agents docs by @martyna-mindsdb in #9058
- updated broken links in mongo docs by @martyna-mindsdb in #9059
- Bump version to 24.4.2.1 by @StpMax in #9061
- Feature/update dd docs by @MinuraPunchihewa in #9062
- Clear LAST value in editor by @ea-rus in #9049
- bump litellm version by @lucas-koontz in #9064
- Managing knowledge base columns by @ea-rus in #9005
- Fix typo by @vlad-ro in #9065
- Initial RAG 2.0 integration by @dusvyat in #9068
- Mindsdb inference endpoints by @ZoranPandovski in #9044
- Disable storage backup by @StpMax in #9073
- Bump version to 24.4.3.0 by @StpMax in #9074
- Kb updates 04.2024 by @ea-rus in #9069
- 9078-bug-cannot-create-a-langchain-engine by @dusvyat in #9080
- Remove custom GH actions and use shared ones by @hamishfagg in #9072
- updated agent skills in docs by @martyna-mindsdb in #9082
- Сhanged default agent type for supporting conversational history by @ea-rus in #9087
- Switch to new GHA runners by @hamishfagg in #9085
- Remove prometheus dir from dockerfile by @hamishfagg in #9092
- Mysql improvments by @ZoranPandovski in #9081
- Infernece docs by @ZoranPandovski in #9100
- updated mindsdb readme by @martyna-mindsdb in #9055
- Fixed Load Tests and Test Docs (README) by @MinuraPunchihewa in #9094
- use cases docs plus docs updates by @martyna-mindsdb in #9095
- Minor tweaks to retrieval skill and file ingestion by @dusvyat in #9093
- Fixes for RAG Integration to Python SDK by @tmichaeldb in #9098
- mysql and postgres docs + readme updates by @martyna-mindsdb in #9102
- MS SQL Handler Improvements by @MinuraPunchihewa in #9083
- Fix REST API Endpoints URL by @ZoranPandovski in #9108
- docs cleanup by @martyna-mindsdb in #9112
- add bigquery to cloud image by @hamishfagg in #9114
- updated triggers docs by @martyna-mindsdb in #9116
- Mindsdb provider for langchain by @ea-rus in #9046
- Update README.md by @martyna-mindsdb in #9125
- removed mindsdb cloud ref in docs by @martyna-mindsdb in #9118
- openapi docs for agents/skills/chatbots by @martyna-mindsdb in #9113
- updated use cases docs by @martyna-mindsdb in #9110
- [fix] dataframe encode in byom describe by @paxcema in #9124
- Fixed Script for Running Handler Unit Tests in Workflow by @MinuraPunchihewa in #9103
- [docs] Improved readme for anomaly detection handler by @paxcema in #9130
- MindsDB Inference Handler improvements by @MinuraPunchihewa in #9099
- Drop
semaphor
table by @StpMax in #9134 - Support New Retrieval Skill for RAG by @tmichaeldb in #9119
- Update Web Handler README by @ZoranPandovski in #9138
- Schema refactor by @ea-rus in #9001
- Remove permanent ml handlers by @ea-rus in #9128
- Update Avaiability of handlers by @ZoranPandovski in #9117
- updated docs for LAST by @martyna-mindsdb in #9147
- Clickhouse improvments by @ZoranPandovski in #9111
- updated docs links in completed readmes&docs for integrations by @martyna-mindsdb in #9150
- added info to langchain about langfuse support by @martyna-mindsdb in #9153
- updated lightwood docs by @martyna-mindsdb in #9148
- Chromadb: sync handler storage on rw operations by @ea-rus in #9140
- Use SQLDatabaseToolkit for Agent sql Skill by @tmichaeldb in #9132
- Fully Support Agents File & Web Retrieval by @tmichaeldb in #9137
- updated a link in openai finetuning tutorial by @martyna-mindsd...
v24.4.3.0
Major updates of this release include the integration of MindsDB with MindsDB Inference Endpoints, which is a service provided by MindsDB that lets you access various LLMs with a single API key. Besides, MindsDB has been working on updates to AI Agents, including knowledge bases and RAG features.
New handlers:
- Mindsdb inference endpoints #9044
Features, Improvements and Fixes:
- bump litellm version #9064
- Managing knowledge base columns #9005
- Integrate rag with langchain agents #9027
- Initial RAG 2.0 integration #9068
- Option to disable storage backup #9073
- Kb updates 04.2024 #9069
Documentation Updates:
- Fix typo #9065
v24.4.2.1
Features, Improvements and Fixes:
- Add RAG model and utilities for Mindsdb integration #8996
- Update requirements.txt #9048
- Update requirements.txt #9050
- update sampledatabases to new k8s server #8986
- The "database" field in the form is changed to not required. #9052
- Fixed Column Structure of chat_messages Table #9015
- Fix BYOM engine create #9054
- Clear LAST value in editor #9049
Documentation Updates:
v24.4.2.0
What's Changed
- removing redundant package lists and sentence-transformers library by @QuantumPlumber in #8971
- Safe extraction for all tar files by @StpMax in #8928
- Fix tarfile safe extract by @StpMax in #9000
- Refactor Langchain Handler by @tmichaeldb in #8998
- Tests for sql features by @ea-rus in #8952
- Update query format in quickstart-tutorial.mdx by @vlad-ro in #9011
- [404] fix url in huggingface_inference_api.mdx by @ArnavK-09 in #9016
- Fix hardcoded API base by @ZoranPandovski in #9019
- Added Check for Import Errors When Running CREATE MODEL Statement by @MinuraPunchihewa in #9020
- updated hostname of sample dbs by @martyna-mindsdb in #9025
- Fixed Installation of Dependencies for Integrations That Refer to Other requirements.txt Files by @MinuraPunchihewa in #9022
- fixed slack chatbot tutorial by @martyna-mindsdb in #9026
- Fix delete from table in database by @ea-rus in #9017
- Added File Path and URL Support to the Vertex AI Integration by @MinuraPunchihewa in #9007
- clean up handler install log messages by @hamishfagg in #8720
- Docker build improvements by @hamishfagg in #8999
- Add 'seed db' function to MSSQL tests by @hamishfagg in #8742
- Fixed Installation of Dependencies for Integrations That Refer to requirements.txt Files (Docker-supported) by @MinuraPunchihewa in #9034
- Fixed Installation of Dependencies When requirements.txt Files Contain Comments by @MinuraPunchihewa in #9038
- Fixed the Initializer for the EventStoreDB Integration by @MinuraPunchihewa in #9029
- Fixed Unused Imports and Dependencies in Rockset Integration by @MinuraPunchihewa in #9031
- updated email integration docs by @martyna-mindsdb in #9035
- Make alembic use mindsdb log level by @hamishfagg in #9028
- Bump version for release by @hamishfagg in #9041
- Fix LAST with slack by @ea-rus in #9036
- Updated LightFM Integration Docs with Tip to Install Linux Dev Pakcages by @MinuraPunchihewa in #9042
- updated ollama docs by @martyna-mindsdb in #8995
- Updated Snowflake Integration Docs with Tip to Install Git by @MinuraPunchihewa in #9032
New Contributors
- @vlad-ro made their first contribution in #9011
- @ArnavK-09 made their first contribution in #9016
Full Changelog: v24.3.5.0...v24.4.2.0
v24.3.5.0
Features, Improvements and Fixes:
- create prometheus dir if it doesnt exist #8991
- add default handlers to manifest and fix pip install test #8989
- agent behaves as model #8984
- Fix image tags #8979
- Add Local Ollama Model Support to Langchain Handler #8978
- Sets the 'success' Attribute of /<handler_name>/install Endpoint to False Upon Installation Failure #8977
- Add Support for Querying Agents via SQL #8856
- New /tabs routes #8898
- added ollama_serve_url argument to overwrite hardcoded default URL and validated linux compatability #8914
- Updated the Broken Dependencies for the BigQuery Handler #8910
- Github handler: all tables converted to APIResource #8940
- Del stream interface #8967
Documentation Updates:
v24.3.4.2
v24.3.4.0
Features, Improvements and Fixes:
- [ENH] Code and contextual QA formatters for LLM finetuning #8759
- Fixes for Issue #8565 #8567
- Refactor email handler #8794
- clean up docker/docker-compose and comment #8798
- Add 12labs handler to cloud #8804
- Improve email ingestion and handling in MindsDB #8803
- Added insert method for email campaigns table #8698
- Skills updates #8765
- Refactor docker bake file #8763
- Improve error message if model in 'error' status #8827
- Fix create ml engine #8830
- Fix
describe
of broken openai model #8829 - Fix: JOIN model with empty dataframe #8843
- PR for small fixes on hachaton #8833
- Fix
describe
for models with 'broken' ml_engines #8839 - Validate api key during OpenAI or Anyscale-endpoints ml_engine creation #8847
- Validate the timegpt token #8841
- Add multi environment deploy step #8836
- add deploy to staging when mergeing to staging branch #8852
- Fix show command #8849
- Adding icon.svg file for writer handler #8859
- Removed Non-integrations from the /handlers Endpoint #8862
- Fixed Several Unusable Handlers #8864
- Added Support for Summarization to the Twelve Labs Integration #8795
- Make Langchain Handler More Reliable #8844
- Add /completions POST Endpoint for Agent Completions #8850
- [ENH] Updates to langchain: version bump, observability #8785
- Getting anyscale key instead openai #8800
- Skills decoupling #8792
- Updated icons for TPOT and StatsForecast #8872
- Slack list messages updated #8796
- Don't pickle exception, wrap it #8866
- Make
langchain_community
dependency optional #8875 - Mark
files
handler as permanent #8879 - fix
github_tables
filtering #8881 - Make web handler optional #8880
- Twelvelabs Integration fixes #8883
- Fixed the Import of MatrixOneHandler in D0lt Handler #8886
- Fix last: one condition in view #8867
- Add auth flag in the config example #8888
- Anomaly detection process data bug #8897
- Fix warning about flask JSONEncoder deprecation #8869
- Init load tests #8730
- anthropic to use messages api (instead of legacy completions api) #8885
- Removed Icons as Determining Factor for Handler Import Status #8909
- Updated the Broken Dependencies for the BigQuery Handler #8910
- Add Support for Prometheus Metrics & Add New Handler Metrics #8899
- fix for email handler to work in jobs with last #8913
- Fix failing coveralls action #8917
- Fix
select connection_id()
#8920 - Added Improved Logos for Integrations #8854
- Add
jobs_history
tolog
db #8793 - Bump follow-redirects from 1.15.5 to 1.15.6 in /docs #8932
- Fix supported python versions for pip installs #8905
- Json operators support #8895
- fix setup limits #8937
- Add Prometheus Metrics for All API Endpoints #8904
- Include prometheus_metrics Dir in Dockerfile #8944
Documentation Updates:
- Typo "mbd" vs "mdb" #8736
- Update README.md - tweak messaging #8797
- [Docs] update mongo doc: replace
insert
->insertOne
,predictors
->`models #8802 - fixed api_key param names #8809
- added info to finetune commands #8808
- docs for evaluate by #8807
- update to rest api docs #8810
- docs rearranged and modified intro pages #8811
- Cleanup docs #8825
- added a note that create table needs database with write access #8832
- Update Anomaly detection docs #8834
- added eeg forecast tutorial #8835
- tutorial for learning hub #8837
- fixed query in tutorial #8840
- updated tutorials for learning hub #8845
- added data file to openai finetuning tutorial #8853
- update file link #8855
- fixed slack chatbot tutorial #8868
- Less redundant doc example #8873
- fixed github docs #8877
- fixed anthropic model names in docs #8884
- Update README.md #8887
- Update README.md #8889
- Update monkeylearn.mdx #8891
- Update README.md #8901
- updated middleware to platform #8894
- added links to use cases #8912
- update to docker docs #8916
- updated slack docs #8921
- Update MindsDB Installation for Development docs #8908
- updating ai engines doc pages #8799
v24.2.3.0
Features, Improvements and Fixes:
- Fix args in test_predict_text_sentiment_openai_tutorial #8789
- Better error handling if exception can't be pickled #8729
- added rag handler param #8781
- Slack fixex #8782
- Fix getting api key #8786
- Add internal
log
database #8778 - Fix All Tests Under tests/unit #8662
- Stored MS Teams Redirect URI in Handler Storage #8766
- Corrected Use of Logger in LibSQL Handler #8769
- modify get_api_key util function and affected handlers #8245
- Datanode returns list of lists instead of dict #8745
- Fix getting api-key for openai finetune #8762
- Fix Twelve Labs indexing local file #8748
- [ENH] Improved data preparation for LLM finetuning #8692
- Mongodb handler tests #8470
- Save anomaly_detection files to storage #8724
- Minor Fix to the Put Config API Endpoint #8732
- Update APITable docs #8738
- Remove permanent for some ml handlers #8737
- Google_analytics is not permanent #8734
- [refactor] Migrate legacy OpenAI API #8541
- [fix] Minor finetune improvements #8727
- Show content in files by default #8731
- GITHUB handler update #8721
- Fix anyscale-endpoints finetune #8713
- Pass info about model target to planner #8722
- Postgres handler unit tests #8214
- Mssql handler unit tests #8317
- Mysql handler tests #8587
- Move lanchain skills to langchain handler. #8711
- Fixed: Whatsapp logger issue #8717
- Fix RAG post openai changes #8674
- Run all ML handlers methods via queue #8645
- Return tests with last to #8662 #8694
- [fix] Key error when exiting context handler #8710
- Move file test to acceptance tests #8697
- Fix mongodb parsing #8675
- added text-generation support to hf handler #8513
- PostgreSQL Integration improvments #8680
- [fix] Anyscale key getter #8693
Documentation Updates:
- Update Other Clouds Deployment Page #8788
- rag param update in docs #8780
- added anyscale docs #8779
- updated last keyword docs #8776
- updated intro docs #8775
- updated slack chatbot tutorial #8772
- Update twitter-chatbot.mdx to use LAST #8750
- updated mindsdb intro #8770
- Update README.md with the new messaging #8768
- updates to integrations doc pages #8758
- updated neuralforecast parameters in docs #7336
- sql api updates #8756
- updated deprecated openai models #8755
- added d0lt.mdx #5383
- youtube docs for connecting #8744
- youtube docs #8741
- updates to postgres docs #8740
- updated ai tables doc page #8706
- installation docs updates #8705
- PostgreSQL Updates docs #8707
- youtube documentation update #8682
- Fix: Typo in documentation #8703
- sql syntax document page #8676
- fix_query #8683