Llama-index

Patch Changes

- 11ae926: feat: add numCandidates setting to MongoDBAtlasVectorStore for tuning queries
- 631f000: feat: DeepInfra LLM implementation
- 1378ec4: feat: set default model to `gpt-4o`
- 6b1ded4: add gpt4o-mode, invalidate cache and skip diagonal text to LlamaParseReader
- 4d4bd85: Show error message if agent tool is called with partial JSON
- 24a9d1e: add json mode and image retrieval to LlamaParseReader
- 45952de: add concurrency management for SimpleDirectoryReader
- 54230f0: feat: Gemini GA release models
- a29d835: setDocumentHash should be async
- 73819bf: Unify metadata and ID handling of documents, allow files to be read by `Buffer`


llamaindex/experimental0.0.33
Patch Changes

- Updated dependencies [11ae926]
- Updated dependencies [631f000]
- Updated dependencies [1378ec4]
- Updated dependencies [6b1ded4]
- Updated dependencies [4d4bd85]
- Updated dependencies [24a9d1e]
- Updated dependencies [45952de]
- Updated dependencies [54230f0]
- Updated dependencies [a29d835]
- Updated dependencies [73819bf]
- llamaindex0.3.16


llamaindex/community0.0.2
Patch Changes

- 8832669: Community bedrock support added
- Updated dependencies [11ae926]
- Updated dependencies [631f000]
- Updated dependencies [1378ec4]
- Updated dependencies [6b1ded4]
- Updated dependencies [4d4bd85]
- Updated dependencies [24a9d1e]
- Updated dependencies [45952de]
- Updated dependencies [54230f0]
- Updated dependencies [a29d835]
- Updated dependencies [73819bf]
- llamaindex0.3.16

Patch Changes

- 6e156ed: Use images in context chat engine
- 265976d: fix bug with node decorator
- 8e26f75: Add retrieval for images using multi-modal messages


llamaindex/experimental0.0.32
Patch Changes

- Updated dependencies [6e156ed]
- Updated dependencies [265976d]
- Updated dependencies [8e26f75]
- llamaindex0.3.15

Patch Changes

- 6ff7576: Added GPT-4o for Azure
- 94543de: Added the latest preview gemini models and multi modal images taken into account


llamaindex/experimental0.0.31
Patch Changes

- Updated dependencies [6ff7576]
- Updated dependencies [94543de]
- llamaindex0.3.14

Patch Changes

- 1b1081b: Add vectorStores to storage context to define vector store per modality
- 37525df: Added support for accessing Gemini via Vertex AI
- 660a2b3: Fix text before heading in markdown reader
- a1f2475: Add system prompt to ContextChatEngine


llamaindex/experimental0.0.30
Patch Changes

- Updated dependencies [1b1081b]
- Updated dependencies [37525df]
- Updated dependencies [660a2b3]
- Updated dependencies [a1f2475]
- llamaindex0.3.13

Patch Changes

- 34fb1d8: fix: cloudflare dev


llamaindex/experimental0.0.29
Patch Changes

- Updated dependencies [34fb1d8]
- llamaindex0.3.12

Patch Changes

- e072c45: fix: remove non-standard API `pipeline`

- 9e133ac: refactor: remove `defaultFS` from parameters

We don't accept passing fs in the parameter since it's unnecessary for a determined JS environment.

This was a polyfill way for the non-Node.js environment, but now we use another way to polyfill APIs.

- 447105a: Improve Gemini message and context preparation

- 320be3f: Force ChromaDB version to 1.7.3 (to prevent NextJS issues)

- Updated dependencies [e072c45]

- Updated dependencies [9e133ac]
- llamaindex/env0.1.3


llamaindex/experimental0.0.28
Patch Changes

- Updated dependencies [e072c45]
- Updated dependencies [9e133ac]
- Updated dependencies [447105a]
- Updated dependencies [320be3f]
- llamaindex0.3.11


llamaindex/env0.1.3
Patch Changes

- e072c45: fix: remove non-standard API `pipeline`
- 9e133ac: refactor: remove `defaultFS` from parameters

We don't accept passing fs in the parameter since it's unnecessary for a determined JS environment.

This was a polyfill way for the non-Node.js environment, but now we use another way to polyfill APIs.