CHANGELOG.md

create-llama

0.1.26

Patch Changes

• f43399cc: Add metadatafilters to context chat engine (Typescript)

0.1.25

Patch Changes

• c67daeb2: fix: missing set private to false for default generate.py

0.1.24

Patch Changes

• 43474a51: Configure LlamaCloud organization ID for Python
• cf11b233: Add Azure code interpreter for Python and TS
• fd9fb42a: Add Azure OpenAI as model provider
• 5c13646e: Fix starter questions not working in python backend

0.1.23

Patch Changes

• 6bd76fbf: Add template for structured extraction

0.1.22

Patch Changes

• b0becaa8: Add e2e testing for llamacloud datasource
• df9cca5a: Upgrade pdf viewer

0.1.21

Patch Changes

• bd4714ca: Filter private documents for Typescript (Using MetadataFilters) and update to LlamaIndexTS 0.5.7
• 58e6c150: Add using LlamaParse for private file uploader
• 455ab686: Display files in sources using LlamaCloud indexes.
• 23b73571: Use gpt-4o-mini as default model
• 09004136: Add suggestions for next questions.

0.1.20

Patch Changes

• 624c721a: Update to LlamaIndex 0.10.55

0.1.19

Patch Changes

• df96159e: Use Qdrant FastEmbed as local embedding provider
• 32fb32ab: Support upload document files: pdf, docx, txt

0.1.18

Patch Changes

• d1026ea7: support Mistral as llm and embedding
• a221cfc1: Use LlamaParse for all the file types that it supports (if activated)

0.1.17

Patch Changes

• 9ecd0612: Add new template for a multi-agents app

0.1.16

Patch Changes

• a0aab032: Add T-System's LLMHUB as a model provider

0.1.15

Patch Changes

• 64732f05: Fix the issue of images not showing with the sandbox URL from OpenAI's models
• aeb6fef4: use llamacloud for chat

0.1.14

Patch Changes

• f2c33891: chore: update to llamaindex 0.4.3
• 5093b37c: Remove non-working file selectors for Linux

0.1.13

Patch Changes

• b3c969da: Add image generator tool

0.1.12

Patch Changes

• aa69014d: Fix NextJS for TS 5.2

0.1.11

Patch Changes

• 48b96ff1: Add DuckDuckGo search tool
• 9c9decbb: Reuse function tool instances and improve e2b interpreter tool for Python
• 02ed277d: Add Groq as a model provider
• 0748f2e8: Remove hard-coded Gemini supported models

0.1.10

Patch Changes

• 9112d080: Add OpenAPI tool for Typescript
• 8f03f8d4: Add OLLAMA_REQUEST_TIMEOUT variable to config Ollama timeout (Python)
• 8f03f8d4: Apply nest_asyncio for llama parse

0.1.9

Patch Changes

• a42fa53a: Add CSV upload
• 563b51d7: Fix Vercel streaming (python) to stream data events instantly
• d60b3c5a: Add E2B code interpreter tool for FastAPI
• 956538ee: Add OpenAPI action tool for FastAPI

0.1.8

Patch Changes

• cd50a33d: Add interpreter tool for TS using e2b.dev

0.1.7

Patch Changes

• 260d37a3: Add system prompt env variable for TS
• bbd5b8dd: Fix postgres connection leaking issue
• bb53425b: Support HTTP proxies by setting the GLOBAL_AGENT_HTTP_PROXY env variable
• 69c2e16c: Fix streaming for Express
• 7873bfb0: Update Ollama provider to run with the base URL from the environment variable

0.1.6

Patch Changes

• 56537a14: Display PDF files in source nodes

0.1.5

Patch Changes

• 84db7983: feat: support display latex in chat markdown

0.1.4

Patch Changes

• 0bc8e75c: Use ingestion pipeline for dedicated vector stores (Python only)
• cb1001de: Add ChromaDB vector store

0.1.3

Patch Changes

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

0.1.2

Patch Changes

• 056e376e: Add support for displaying tool outputs (including weather widget as example)

0.1.1

Patch Changes

• 7bd3ed55: Support Anthropic and Gemini as model providers
• 7bd3ed55: Support new agents from LITS 0.3
• cfb5257a: Display events (e.g. retrieving nodes) per chat message

0.1.0

Minor Changes

• f1c3e8df: Add Llama3 and Phi3 support using Ollama

Patch Changes

• a0dec80d: Use gpt-4-turbo model as default. Upgrade Python llama-index to 0.10.28
• 753229df: 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.
• 1d78202e: Add observability for Python
• 6acccd2b: Use poetry run generate to generate embeddings for FastAPI
• 9efcffe1: Use Settings object for LlamaIndex configuration
• 418bf9ba: refactor: use tsx instead of ts-node
• 1be69a5a: Add Qdrant support

0.0.32

Patch Changes

• 625ed4d6: Support Astra VectorDB
• 922e0ceb: Remove UI question (use shadcn as default). Use html UI by calling create-llama with --ui html parameter
• ce2f24d7: Update loaders and tools config to yaml format (for Python)
• e8db041d: Let user select multiple datasources (URLs, files and folders)
• c06d4af7: Add nodes to the response (Python)
• 29b17ee3: Allow using agents without any data source
• 665c26cc: Add redirect to documentation page when accessing the base URL (FastAPI)
• 78ded9e2: Add Dockerfile templates for Typescript and Python
• 99e758fc: Merge non-streaming and streaming template to one
• b3f26856: Add support for agent generation for Typescript
• 27397143: Use a database (MySQL or PostgreSQL) as a data source

0.0.31

Patch Changes

• 56faee0b: Added windows e2e tests
• 60ed8fe0: Added missing environment variable config for URL data source
• 60ed8fe0: Fixed tool usage by freezing llama-index package versions

0.0.30

Patch Changes

• 3af63284: Add support for llamaparse using Typescript
• dd92b911: Add fetching llm and embedding models from server
• bac1b43f: Add Milvus vector database

0.0.29

Patch Changes

• edd24c21: Add observability with openllmetry
• 403fc6f3: Minor bug fixes to improve DX (missing .env value and updated error messages)
• 0f797579: Ability to download community submodules

0.0.28

Patch Changes

• 89a49f4: Add more config variables to .env file
• fdf48dd: Add "Start in VSCode" option to postInstallAction
• fdf48dd: Add devcontainers to generated code

0.0.27

Patch Changes

• 2d29350: Add LlamaParse option when selecting a pdf file or a folder (FastAPI only)
• b354f23: Add embedding model option to create-llama (FastAPI only)

0.0.26

Patch Changes

• 09d532e: feat: generate llama pack project from llama index
• cfdd6db: feat: add pinecone support to create llama
• ef25d69: upgrade llama-index package to version v0.10.7 for create-llama app
• 50dfd7b: update fastapi for CVE-2024-24762

0.0.25

Patch Changes

• d06a85b: Add option to create an agent by selecting tools (Google, Wikipedia)
• 7b7329b: Added latest turbo models for GPT-3.5 and GPT 4

0.0.24

Patch Changes

• ba95ca3: Use condense plus context chat engine for FastAPI as default

0.0.23

Patch Changes

• c680af6: Fixed issues with locating templates path

0.0.22

Patch Changes

• 6dd401e: Add an option to provide an URL and chat with the website data (FastAPI only)
• e9b87ef: Select a folder as data source and support more file types (.pdf, .doc, .docx, .xls, .xlsx, .csv)

0.0.20

Patch Changes

• 27d55fd: Add an option to provide an URL and chat with the website data

0.0.19

Patch Changes

• 3a29a80: Add node_modules to gitignore in Express backends
• fe03aaa: feat: generate llama pack example

0.0.18

Patch Changes

• 88d3b41: fix packaging

0.0.17

Patch Changes

• fa17f7e: Add an option that allows the user to run the generated app
• 9e5d8e1: Add an option to select a local PDF file as data source

0.0.16

Patch Changes

• a73942d: Fix: Bundle mongo dependency with NextJS
• 9492cc6: Feat: Added option to automatically install dependencies (for Python and TS)
• f74dea5: Feat: Show images in chat messages using GPT4 Vision (Express and NextJS only)

0.0.15

Patch Changes

• 8e124e5: feat: support showing image on chat message

0.0.14

Patch Changes

• 2e6b36e: fix: re-organize file structure
• 2b356c8: fix: relative path incorrect

0.0.13

Patch Changes

• Added PostgreSQL vector store (for Typescript and Python)
• Improved async handling in FastAPI

0.0.12

Patch Changes

• 9c5e22a: Added cross-env so frontends with Express/FastAPI backends are working under Windows
• 5ab65eb: Bring Python templates with TS templates to feature parity
• 9c5e22a: Added vector DB selector to create-llama (starting with MongoDB support)

0.0.11

Patch Changes

• 2aeb341: - Added option to create a new project based on community templates
  • Added OpenAI model selector for NextJS projects
  • Added GPT4 Vision support (and file upload)

0.0.10

Patch Changes

• Bugfixes (thanks @marcusschiesser)

0.0.9

Patch Changes

• acfe232: Deployment fixes (thanks @seldo)

0.0.8

Patch Changes

• 8cdb07f: Fix Next deployment (thanks @seldo and @marcusschiesser)

0.0.7

Patch Changes

• 9f9f293: Added more to README and made it easier to switch models (thanks @seldo)

0.0.6