v0.1.8

Patch Changes

• cd50a33: Add interpreter tool for TS using e2b.dev

v0.1.7

Patch Changes

• 260d37a: Add system prompt env variable for TS
• bbd5b8d: Fix postgres connection leaking issue
• bb53425: Support HTTP proxies by setting the GLOBAL_AGENT_HTTP_PROXY env variable
• 69c2e16: Fix streaming for Express
• 7873bfb: Update Ollama provider to run with the base URL from the environment variable

v0.1.6

Patch Changes

• 56537a1: Display PDF files in source nodes

v0.1.5

Patch Changes

• 84db798: feat: support display latex in chat markdown

v0.1.4

Patch Changes

• 0bc8e75: Use ingestion pipeline for dedicated vector stores (Python only)
• cb1001d: Add ChromaDB vector store

v0.1.3

Patch Changes

• 416073d: Directly import vector stores to work with NextJS

v0.1.2

Patch Changes

• 056e376: Add support for displaying tool outputs (including weather widget as example)

v0.1.1

Patch Changes

• 7bd3ed5: Support Anthropic and Gemini as model providers
• 7bd3ed5: Support new agents from LITS 0.3
• cfb5257: Display events (e.g. retrieving nodes) per chat message

v0.1.0

Minor Changes

• f1c3e8d: Add Llama3 and Phi3 support using Ollama

Patch Changes

• a0dec80: Use gpt-4-turbo model as default. Upgrade Python llama-index to 0.10.28
• 753229d: Remove asking for AI models and use defaults instead (OpenAIs GPT-4 Vision Preview and Embeddings v3). Use --ask-models CLI parameter to select models.
• 1d78202: Add observability for Python
• 6acccd2: Use poetry run generate to generate embeddings for FastAPI
• 9efcffe: Use Settings object for LlamaIndex configuration
• 418bf9b: refactor: use tsx instead of ts-node
• 1be69a5: Add Qdrant support