v0.0.1

PySpur v0.1.0 - First Release

Main features supported are:

• Create, save and run spurs (workflows/agents) locally on Linux & MacOS

• Run evals on saved agent workflows

• Trigger runs via REST API

• Trace view of runs

• The following nodes are part of this release:

  • Single LLM Call Node - calls the LLM provider of user's choice in structured output/json mode
  • Best Of N Node - sample the response from LLM n times and pass the best one forward
  • Branch Solve Merge Node - given an input prompt, branch it into parallel steps and then merge the solutions of these steps
  • Router Node - pass the inputs to one of the routes based on conditions defined in the config
  • Coalesce Node - pick the first non-null incoming edge and pass it forward
  • Python Function Node - execute a python function

• Support for the following LLM providers is part of this release:

  • OpenAI
  • Anthropic
  • Gemini
  • Ollama
    • models such as llama3.2, gemma2, deepseek, mistral, etc can be hosted locally using ollama and be used with pyspur

What's Changed

• Refactor: Add text editor component by @preet-bhadra in #1
• Refactor Redux flowSlice and FlowCanvas by @preet-bhadra in #2
• Refactor canvas and text editor components by @preet-bhadra in #3
• Spread sheet by @preet-bhadra in #4
• Llm config by @preet-bhadra in #5
• Dask by @srijanpatel in #6
• Node config by @preet-bhadra in #7
• Node config by @preet-bhadra in #8
• Node config by @preet-bhadra in #9
• Node config by @preet-bhadra in #10
• Node config by @preet-bhadra in #11
• Node config by @preet-bhadra in #12
• Feat/data models by @srijanpatel in #14
• Interactive mode by @preet-bhadra in #15
• Interactive mode by @preet-bhadra in #16
• Interactive mode branch fixes by @srijanpatel in #18
• Interactive mode by @preet-bhadra in #19
• Interactive mode with initial inputs by @preet-bhadra in #20
• Dynamic node types by @preet-bhadra in #21
• Node display by @preet-bhadra in #23
• Feat/sort out schemas by @srijanpatel in #24
• Feat/nginx by @srijanpatel in #25
• Run view by @preet-bhadra in #26
• Refactor WorkflowVersionModel name column to allow duplicate values by @preet-bhadra in #27
• Feat/subworkflows by @srijanpatel in #29
• Evals + European READMEs by @JeanKaddour in #31
• feat: Add Deploy-as-API button modal by @JeanKaddour in #33
• BUGFIX: Update edges on input_schema or output_schema key changes by @putraridho in #34
• Feat: Row-level eval details by @JeanKaddour in #35
• Feat/subworkflows by @srijanpatel in #36
• Run view by @preet-bhadra in #30
• Refactor js to typescript by @JeanKaddour in #37
• Refactor Dockerfile to include package-lock.json by @srijanpatel in #38
• Feat/collapsible node panel by @srijanpatel in #39
• Add IfElseNode and Merge Node by @JeanKaddour in #40
• feat: move system and user messages to top of Node Configuration by @devin-ai-integration in #41
• feat: move message fields to top in remaining LLM nodes by @devin-ai-integration in #42
• feat: add Top-K node for ranking texts by @devin-ai-integration in #43
• Refactor/miso by @srijanpatel in #44
• Refactor/fe types by @srijanpatel in #45
• feat: add API key warning alert to dashboard by @devin-ai-integration in #47
• fix: adjust primary color in dark mode for better button contrast by @devin-ai-integration in #50
• Add ollama models support via litellm by @devin-ai-integration in #51
• Edges bug fix by @preet-bhadra in #53
• feat: add welcome modal for first-time users by @devin-ai-integration in #49
• Feat/ollama integration by @srijanpatel in #55
• fix: directory in quickstart command by @NiloCK in #56
• Test ollama service with model tags instead of a query by @simonwu53 in #61
• Logic node post miso by @preet-bhadra in #58
• Refactor workflow_management.py and remove unused imports and code by @srijanpatel in #65
• Feat/release docker builds by @srijanpatel in #66
• Add Azure OpenAi Support by @pafend in #59
• Feat/merge node by @preet-bhadra in #67
• Bugfix/conditional node by @preet-bhadra in #69
• Performance: Decouple state.flow.nodes into state.flow.nodes and state.flow.nodeConfigs by @JeanKaddour in #68
• Chore/devcontainers by @srijanpatel in #72

New Contributors

• @preet-bhadra made their first contribution in #1
• @srijanpatel made their first contribution in #6
• @JeanKaddour made their first contribution in #31
• @putraridho made their first contribution in #34
• @devin-ai-integration made their first contribution in #41
• @NiloCK made their first contribution in #56
• @simonwu53 made their first contribution in #61
• @pafend made their first contribution in #59

Full Changelog: https://github.com/PySpur-Dev/pyspur/commits/v0.0.1