Release refs/tags/llamaindex@0.6.12

llamaindex

0.6.12

Patch Changes

• f7b4e94: feat: add filters for pinecone
• 78037a6: fix: bypass service context embed model
• 1d9e3b1: fix: export llama reader in non-nodejs runtime

0.6.11

Patch Changes

• df441e2: fix: consoleLogger is missing from @llamaindex/env
• Updated dependencies [df441e2]
  • @llamaindex/cloud@0.2.9
  • @llamaindex/core@0.2.8
  • @llamaindex/env@0.1.13
  • @llamaindex/ollama@0.0.3
  • @llamaindex/openai@0.1.10
  • @llamaindex/groq@0.0.9

0.6.10

Patch Changes

• ebc5105: feat: support @vercel/postgres
• 6cce3b1: feat: support npm:postgres
• Updated dependencies [96f72ad]
• Updated dependencies [6cce3b1]
  • @llamaindex/openai@0.1.9
  • @llamaindex/core@0.2.7
  • @llamaindex/groq@0.0.8
  • @llamaindex/ollama@0.0.2

0.6.9

Patch Changes

• Updated dependencies [ac41ed3]
  • @llamaindex/cloud@0.2.8

0.6.8

Patch Changes

• 8b7fdba: refactor: move chat engine & retriever into core.

  • chatHistory in BaseChatEngine now returns ChatMessage[] | Promise<ChatMessage[]>, instead of BaseMemory
  • update retrieve-end type

• Updated dependencies [8b7fdba]

  • @llamaindex/core@0.2.6
  • @llamaindex/openai@0.1.8
  • @llamaindex/groq@0.0.7

0.6.7

Patch Changes

• 23bcc37: fix: add serializer in doc store

  PostgresDocumentStore now will not use JSON.stringify for better performance

0.6.6

Patch Changes

• d902cc3: Fix context not being sent using ContextChatEngine
• 025ffe6: fix: update PostgresKVStore constructor params
• a659574: Adds upstash vector store as a storage
• Updated dependencies [d902cc3]
  • @llamaindex/core@0.2.5
  • @llamaindex/openai@0.1.7
  • @llamaindex/groq@0.0.6

0.6.5

Patch Changes

• e9714db: feat: update PGVectorStore

  • move constructor parameter config.user | config.database | config.password | config.connectionString into config.clientConfig
  • if you pass pg.Client or pg.Pool instance to PGVectorStore, move it to config.client, setting config.shouldConnect to false if it's already connected
  • default value of PGVectorStore.collection is now "data" instead of "" (empty string)

0.6.4

Patch Changes

• b48bcc3: feat: add load-transformers event type when loading @xenova/transformers module

  This would benefit user who want to customize the transformer env.

• Updated dependencies [b48bcc3]

  • @llamaindex/core@0.2.4
  • @llamaindex/env@0.1.12
  • @llamaindex/openai@0.1.6
  • @llamaindex/groq@0.0.5

0.6.3

Patch Changes

• 2cd1383: refactor: align response-synthesizers & chat-engine module

  • builtin event system
  • correct class extends
  • aligin APIs, naming with llama-index python
  • move stream out of first parameter to second parameter for the better tyep checking
  • remove JSONQueryEngine in @llamaindex/experimental, as the code quality is not satisify and we will bring it back later

• 5c4badb: Extend JinaAPIEmbedding parameters

• Updated dependencies [fb36eff]

• Updated dependencies [d24d3d1]

• Updated dependencies [2cd1383]

  • @llamaindex/cloud@0.2.7
  • @llamaindex/core@0.2.3
  • @llamaindex/openai@0.1.5
  • @llamaindex/groq@0.0.4

0.6.2

Patch Changes

• 749b43a: fix: clip embedding transform function
• Updated dependencies [b42adeb]
• Updated dependencies [749b43a]
  • @llamaindex/cloud@0.2.6
  • @llamaindex/core@0.2.2
  • @llamaindex/openai@0.1.4
  • @llamaindex/groq@0.0.3

0.6.1

Patch Changes

• fbd5e01: refactor: move groq as llm package

• 6b70c54: feat: update JinaAIEmbedding, support embedding v3

• 1a6137b: feat: experimental support for browser

  If you see bundler issue in next.js edge runtime, please bump to next@14 latest version.

• 85c2e19: feat: @llamaindex/cloud package update

  • Bump to latest openapi schema
  • Move LlamaParse class from llamaindex, this will allow you use llamaparse in more non-node.js environment

• Updated dependencies [ac07e3c]

• Updated dependencies [fbd5e01]

• Updated dependencies [70ccb4a]

• Updated dependencies [1a6137b]

• Updated dependencies [85c2e19]

• Updated dependencies [ac07e3c]

  • @llamaindex/core@0.2.1
  • @llamaindex/env@0.1.11
  • @llamaindex/groq@0.0.2
  • @llamaindex/cloud@0.2.5
  • @llamaindex/openai@0.1.3

0.6.0

Minor Changes

• 11feef8: Add workflows

Patch Changes

• Updated dependencies [11feef8]
  • @llamaindex/core@0.2.0
  • @llamaindex/openai@0.1.2

0.5.27

Patch Changes

• 7edeb1c: feat: decouple openai from llamaindex module

  This should be a non-breaking change, but just you can now only install @llamaindex/openai to reduce the bundle size in the future

• Updated dependencies [7edeb1c]

  • @llamaindex/openai@0.1.1

0.5.26

Patch Changes

• ffe0cd1: faet: add openai o1 support
• ffe0cd1: feat: add PostgreSQL storage

0.5.25

Patch Changes

• 4810364: fix: handle RouterQueryEngine with string query

• d3bc663: refactor: export vector store only in nodejs environment on top level

  If you see some missing modules error, please change vector store related imports to llamaindex/vector-store

• Updated dependencies [4810364]

  • @llamaindex/cloud@0.2.4

0.5.24

Patch Changes

• Updated dependencies [0bf8d80]
  • @llamaindex/cloud@0.2.3

0.5.23

Patch Changes

• Updated dependencies [711c814]
  • @llamaindex/core@0.1.12

0.5.22

Patch Changes

• 4648da6: fix: wrong tiktoken version caused NextJs CL template run fail
• Updated dependencies [4648da6]
  • @llamaindex/env@0.1.10
  • @llamaindex/core@0.1.11

0.5.21

Patch Changes

• ae1149f: feat: add JSON streaming to JSONReader

• 2411c9f: Auto-create index for MongoDB vector store (if not exists)

• e8f229c: Remove logging from MongoDB Atlas Vector Store

• 11b3856: implement filters for MongoDBAtlasVectorSearch

• 83d7f41: Fix database insertion for PGVectorStore

  It will now:

  • throw an error if there is an insertion error.
  • Upsert documents with the same id.
  • add all documents to the database as a single INSERT call (inside a transaction).

• 0148354: refactor: prompt system

  Add PromptTemplate module with strong type check.

• 1711f6d: Export imageToDataUrl for using images in chat

• Updated dependencies [0148354]

  • @llamaindex/core@0.1.10

0.5.20

Patch Changes

• d9d6c56: Add support for MetadataFilters for PostgreSQL
• 22ff486: Add tiktoken WASM to withLlamaIndex
• eed0b04: fix: use LLM metadata mode for generating context of ContextChatEngine

0.5.19

Patch Changes

• fcbf183: implement llamacloud file service

0.5.18

Patch Changes

• 8b66cf4: feat: support organization id in llamacloud index
• Updated dependencies [e27e7dd]
  • @llamaindex/core@0.1.9

0.5.17

Patch Changes

• c654398: Implement Weaviate Vector Store in TS

0.5.16

Patch Changes

• 58abc57: fix: align version
• Updated dependencies [58abc57]
  • @llamaindex/cloud@0.2.2
  • @llamaindex/core@0.1.8
  • @llamaindex/env@0.1.9

0.5.15

Patch Changes

• 01c184c: Add is_empty operator for filtering vector store
• 07a275f: chore: bump openai

0.5.14

Patch Changes

• c825a2f: Add gpt-4o-mini to Azure. Add 2024-06-01 API version for Azure

0.5.13

Patch Changes

• Updated dependencies [04b2f8e]
  • @llamaindex/core@0.1.7

0.5.12

Patch Changes

• 345300f: feat: add splitByPage mode to LlamaParseReader
• da5cfc4: Add metadatafilter options to retriever constructors
• da5cfc4: Fix system prompt not used in ContextChatEngine
• Updated dependencies [0452af9]
  • @llamaindex/core@0.1.6

0.5.11

Patch Changes

• Updated dependencies [1f680d7]
  • @llamaindex/cloud@0.2.1

0.5.10

Patch Changes

• 086b940: feat: add DeepSeek LLM
• 5d5716b: feat: add a reader for JSON data
• 91d02a4: feat: support transform component callable
• fb6db45: feat: add pageSeparator params to LlamaParseReader
• Updated dependencies [91d02a4]
  • @llamaindex/core@0.1.5

0.5.9

Patch Changes

• 15962b3: feat: node parser refactor

  Align the text splitter logic with Python; it has almost the same logic as Python; Zod checks for input and better error messages and event system.

  This change will not be considered a breaking change since it doesn't have a significant output difference from the last version,
  but some edge cases will change, like the page separator and parameter for the constructor.

• Updated dependencies [15962b3]

  • @llamaindex/core@0.1.4

0.5.8

Patch Changes

• 3d5ba08: fix: update user agent in AssemblyAI
• d917cdc: Add azure interpreter tool to tool factory

0.5.7

Patch Changes

• ec59acd: fix: bundling issue with pnpm

0.5.6

Patch Changes

• 2562244: feat: add gpt4o-mini
• 325aa51: Implement Jina embedding through Jina api
• ab700ea: Add missing authentication to LlamaCloudIndex.fromDocuments
• 92f0782: feat: use query bundle
• 6cf6ae6: feat: abstract query type
• b7cfe5b: fix: passing max_token option to replicate's api call
• Updated dependencies [6cf6ae6]
  • @llamaindex/core@0.1.3

0.5.5

Patch Changes

• b974eea: Add support for Metadata filters
• Updated dependencies [b974eea]
  • @llamaindex/core@0.1.2

0.5.4

Patch Changes

• 1a65ead: feat: add vendorMultimodal params to LlamaParseReader

0.5.3

Patch Changes

• 9bbbc67: feat: add a reader for Discord messages
• b3681bf: fix: DataCloneError when using FunctionTool
• Updated dependencies [b3681bf]
  • @llamaindex/core@0.1.1

0.5.2

Patch Changes

• Updated dependencies [3ed6acc]
  • @llamaindex/cloud@0.2.0

0.5.1

Patch Changes

• 2774681: Add mixedbread's embeddings and reranking API
• a0f424e: corrected the regex in the react.ts file in extractToolUse & extractJsonStr functions, as mentioned in run-llama#1019

0.5.0

Minor Changes

• 16ef5dd: refactor: simplify callback manager

  Change event.detail.payload to event.detail

Patch Changes

• 16ef5dd: refactor: move callback manage...

Release refs/tags/llamaindex@0.6.7

llamaindex

0.6.7

Patch Changes

• 23bcc37: fix: add serializer in doc store

  PostgresDocumentStore now will not use JSON.stringify for better performance

0.6.6

Patch Changes

• d902cc3: Fix context not being sent using ContextChatEngine
• 025ffe6: fix: update PostgresKVStore constructor params
• a659574: Adds upstash vector store as a storage
• Updated dependencies [d902cc3]
  • @llamaindex/core@0.2.5
  • @llamaindex/openai@0.1.7
  • @llamaindex/groq@0.0.6

0.6.5

Patch Changes

• e9714db: feat: update PGVectorStore

  • move constructor parameter config.user | config.database | config.password | config.connectionString into config.clientConfig
  • if you pass pg.Client or pg.Pool instance to PGVectorStore, move it to config.client, setting config.shouldConnect to false if it's already connected
  • default value of PGVectorStore.collection is now "data" instead of "" (empty string)

0.6.4

Patch Changes

• b48bcc3: feat: add load-transformers event type when loading @xenova/transformers module

  This would benefit user who want to customize the transformer env.

• Updated dependencies [b48bcc3]

  • @llamaindex/core@0.2.4
  • @llamaindex/env@0.1.12
  • @llamaindex/openai@0.1.6
  • @llamaindex/groq@0.0.5

0.6.3

Patch Changes

• 2cd1383: refactor: align response-synthesizers & chat-engine module

  • builtin event system
  • correct class extends
  • aligin APIs, naming with llama-index python
  • move stream out of first parameter to second parameter for the better tyep checking
  • remove JSONQueryEngine in @llamaindex/experimental, as the code quality is not satisify and we will bring it back later

• 5c4badb: Extend JinaAPIEmbedding parameters

• Updated dependencies [fb36eff]

• Updated dependencies [d24d3d1]

• Updated dependencies [2cd1383]

  • @llamaindex/cloud@0.2.7
  • @llamaindex/core@0.2.3
  • @llamaindex/openai@0.1.5
  • @llamaindex/groq@0.0.4

0.6.2

Patch Changes

• 749b43a: fix: clip embedding transform function
• Updated dependencies [b42adeb]
• Updated dependencies [749b43a]
  • @llamaindex/cloud@0.2.6
  • @llamaindex/core@0.2.2
  • @llamaindex/openai@0.1.4
  • @llamaindex/groq@0.0.3

0.6.1

Patch Changes

• fbd5e01: refactor: move groq as llm package

• 6b70c54: feat: update JinaAIEmbedding, support embedding v3

• 1a6137b: feat: experimental support for browser

  If you see bundler issue in next.js edge runtime, please bump to next@14 latest version.

• 85c2e19: feat: @llamaindex/cloud package update

  • Bump to latest openapi schema
  • Move LlamaParse class from llamaindex, this will allow you use llamaparse in more non-node.js environment

• Updated dependencies [ac07e3c]

• Updated dependencies [fbd5e01]

• Updated dependencies [70ccb4a]

• Updated dependencies [1a6137b]

• Updated dependencies [85c2e19]

• Updated dependencies [ac07e3c]

  • @llamaindex/core@0.2.1
  • @llamaindex/env@0.1.11
  • @llamaindex/groq@0.0.2
  • @llamaindex/cloud@0.2.5
  • @llamaindex/openai@0.1.3

0.6.0

Minor Changes

• 11feef8: Add workflows

Patch Changes

• Updated dependencies [11feef8]
  • @llamaindex/core@0.2.0
  • @llamaindex/openai@0.1.2

0.5.27

Patch Changes

• 7edeb1c: feat: decouple openai from llamaindex module

  This should be a non-breaking change, but just you can now only install @llamaindex/openai to reduce the bundle size in the future

• Updated dependencies [7edeb1c]

  • @llamaindex/openai@0.1.1

0.5.26

Patch Changes

• ffe0cd1: faet: add openai o1 support
• ffe0cd1: feat: add PostgreSQL storage

0.5.25

Patch Changes

• 4810364: fix: handle RouterQueryEngine with string query

• d3bc663: refactor: export vector store only in nodejs environment on top level

  If you see some missing modules error, please change vector store related imports to llamaindex/vector-store

• Updated dependencies [4810364]

  • @llamaindex/cloud@0.2.4

0.5.24

Patch Changes

• Updated dependencies [0bf8d80]
  • @llamaindex/cloud@0.2.3

0.5.23

Patch Changes

• Updated dependencies [711c814]
  • @llamaindex/core@0.1.12

0.5.22

Patch Changes

• 4648da6: fix: wrong tiktoken version caused NextJs CL template run fail
• Updated dependencies [4648da6]
  • @llamaindex/env@0.1.10
  • @llamaindex/core@0.1.11

0.5.21

Patch Changes

• ae1149f: feat: add JSON streaming to JSONReader

• 2411c9f: Auto-create index for MongoDB vector store (if not exists)

• e8f229c: Remove logging from MongoDB Atlas Vector Store

• 11b3856: implement filters for MongoDBAtlasVectorSearch

• 83d7f41: Fix database insertion for PGVectorStore

  It will now:

  • throw an error if there is an insertion error.
  • Upsert documents with the same id.
  • add all documents to the database as a single INSERT call (inside a transaction).

• 0148354: refactor: prompt system

  Add PromptTemplate module with strong type check.

• 1711f6d: Export imageToDataUrl for using images in chat

• Updated dependencies [0148354]

  • @llamaindex/core@0.1.10

0.5.20

Patch Changes

• d9d6c56: Add support for MetadataFilters for PostgreSQL
• 22ff486: Add tiktoken WASM to withLlamaIndex
• eed0b04: fix: use LLM metadata mode for generating context of ContextChatEngine

0.5.19

Patch Changes

• fcbf183: implement llamacloud file service

0.5.18

Patch Changes

• 8b66cf4: feat: support organization id in llamacloud index
• Updated dependencies [e27e7dd]
  • @llamaindex/core@0.1.9

0.5.17

Patch Changes

• c654398: Implement Weaviate Vector Store in TS

0.5.16

Patch Changes

• 58abc57: fix: align version
• Updated dependencies [58abc57]
  • @llamaindex/cloud@0.2.2
  • @llamaindex/core@0.1.8
  • @llamaindex/env@0.1.9

0.5.15

Patch Changes

• 01c184c: Add is_empty operator for filtering vector store
• 07a275f: chore: bump openai

0.5.14

Patch Changes

• c825a2f: Add gpt-4o-mini to Azure. Add 2024-06-01 API version for Azure

0.5.13

Patch Changes

• Updated dependencies [04b2f8e]
  • @llamaindex/core@0.1.7

0.5.12

Patch Changes

• 345300f: feat: add splitByPage mode to LlamaParseReader
• da5cfc4: Add metadatafilter options to retriever constructors
• da5cfc4: Fix system prompt not used in ContextChatEngine
• Updated dependencies [0452af9]
  • @llamaindex/core@0.1.6

0.5.11

Patch Changes

• Updated dependencies [1f680d7]
  • @llamaindex/cloud@0.2.1

0.5.10

Patch Changes

• 086b940: feat: add DeepSeek LLM
• 5d5716b: feat: add a reader for JSON data
• 91d02a4: feat: support transform component callable
• fb6db45: feat: add pageSeparator params to LlamaParseReader
• Updated dependencies [91d02a4]
  • @llamaindex/core@0.1.5

0.5.9

Patch Changes

• 15962b3: feat: node parser refactor

  Align the text splitter logic with Python; it has almost the same logic as Python; Zod checks for input and better error messages and event system.

  This change will not be considered a breaking change since it doesn't have a significant output difference from the last version,
  but some edge cases will change, like the page separator and parameter for the constructor.

• Updated dependencies [15962b3]

  • @llamaindex/core@0.1.4

0.5.8

Patch Changes

• 3d5ba08: fix: update user agent in AssemblyAI
• d917cdc: Add azure interpreter tool to tool factory

0.5.7

Patch Changes

• ec59acd: fix: bundling issue with pnpm

0.5.6

Patch Changes

• 2562244: feat: add gpt4o-mini
• 325aa51: Implement Jina embedding through Jina api
• ab700ea: Add missing authentication to LlamaCloudIndex.fromDocuments
• 92f0782: feat: use query bundle
• 6cf6ae6: feat: abstract query type
• b7cfe5b: fix: passing max_token option to replicate's api call
• Updated dependencies [6cf6ae6]
  • @llamaindex/core@0.1.3

0.5.5

Patch Changes

• b974eea: Add support for Metadata filters
• Updated dependencies [b974eea]
  • @llamaindex/core@0.1.2

0.5.4

Patch Changes

• 1a65ead: feat: add vendorMultimodal params to LlamaParseReader

0.5.3

Patch Changes

• 9bbbc67: feat: add a reader for Discord messages
• b3681bf: fix: DataCloneError when using FunctionTool
• Updated dependencies [b3681bf]
  • @llamaindex/core@0.1.1

0.5.2

Patch Changes

• Updated dependencies [3ed6acc]
  • @llamaindex/cloud@0.2.0

0.5.1

Patch Changes

• 2774681: Add mixedbread's embeddings and reranking API
• a0f424e: corrected the regex in the react.ts file in extractToolUse & extractJsonStr functions, as mentioned in run-llama#1019

0.5.0

Minor Changes

• 16ef5dd: refactor: simplify callback manager

  Change event.detail.payload to event.detail

Patch Changes

• 16ef5dd: refactor: move callback manager & llm to core module

  For people who import llamaindex/llms/base or llamaindex/llms/utils,
  use @llamaindex/core/llms and @llamaindex/core/utils instead.

• 36ddec4: fix: typo in custom page separator parameter for LlamaParse

• Updated dependencies [16ef5dd]

• Updated dependencies [16ef5dd]

• Updated dependencies [36ddec4]

  • @llamaindex/core@0.1.0
  • @llamaindex/cloud@0.1.4

0.4.14

Patch Changes

• Updated dependencies [1c444d5]
  • @llamaindex/cloud@0.1.3

0.4.13

Patch Changes

• e8f8bea: feat: add boundingBox and targetPages to LlamaParseReader
• 304484b: feat: add ignoreErrors flag to LlamaParseReader

0.4.12

Patch Changes

• f326ab8: chore: bump version
• Updated dependencies [f326ab8]
  • @llamaindex/cloud@0.1.2
  • @llamaindex/core@0.0.3
  • @llamaindex/env@0.1.8

0.4.11

Patch Changes

• 8bf5b4a: fix: llama parse input spreadsheet

0.4.10

Patch Changes

• 7dce3d2: fix: disable External Filters for Gemini

0.4.9

Patch Changes

• 3a96a48: fix: anthroipic image input

0.4.8

Patch Changes

• 83ebdfb: fix: next.js build error

0.4.7

Patch Changes

• 41fe871: Add support for azure dynamic session tool
• 321c39d: fix: g...

Release refs/tags/llamaindex@0.6.5

llamaindex

0.6.5

Patch Changes

• e9714db: feat: update PGVectorStore

  • move constructor parameter config.user | config.database | config.password | config.connectionString into config.clientConfig
  • if you pass pg.Client or pg.Pool instance to PGVectorStore, move it to config.client, setting config.shouldConnect to false if it's already connected
  • default value of PGVectorStore.collection is now "data" instead of "" (empty string)

0.6.4

Patch Changes

• b48bcc3: feat: add load-transformers event type when loading @xenova/transformers module

  This would benefit user who want to customize the transformer env.

• Updated dependencies [b48bcc3]

  • @llamaindex/core@0.2.4
  • @llamaindex/env@0.1.12
  • @llamaindex/openai@0.1.6
  • @llamaindex/groq@0.0.5

0.6.3

Patch Changes

• 2cd1383: refactor: align response-synthesizers & chat-engine module

  • builtin event system
  • correct class extends
  • aligin APIs, naming with llama-index python
  • move stream out of first parameter to second parameter for the better tyep checking
  • remove JSONQueryEngine in @llamaindex/experimental, as the code quality is not satisify and we will bring it back later

• 5c4badb: Extend JinaAPIEmbedding parameters

• Updated dependencies [fb36eff]

• Updated dependencies [d24d3d1]

• Updated dependencies [2cd1383]

  • @llamaindex/cloud@0.2.7
  • @llamaindex/core@0.2.3
  • @llamaindex/openai@0.1.5
  • @llamaindex/groq@0.0.4

0.6.2

Patch Changes

• 749b43a: fix: clip embedding transform function
• Updated dependencies [b42adeb]
• Updated dependencies [749b43a]
  • @llamaindex/cloud@0.2.6
  • @llamaindex/core@0.2.2
  • @llamaindex/openai@0.1.4
  • @llamaindex/groq@0.0.3

0.6.1

Patch Changes

• fbd5e01: refactor: move groq as llm package

• 6b70c54: feat: update JinaAIEmbedding, support embedding v3

• 1a6137b: feat: experimental support for browser

  If you see bundler issue in next.js edge runtime, please bump to next@14 latest version.

• 85c2e19: feat: @llamaindex/cloud package update

  • Bump to latest openapi schema
  • Move LlamaParse class from llamaindex, this will allow you use llamaparse in more non-node.js environment

• Updated dependencies [ac07e3c]

• Updated dependencies [fbd5e01]

• Updated dependencies [70ccb4a]

• Updated dependencies [1a6137b]

• Updated dependencies [85c2e19]

• Updated dependencies [ac07e3c]

  • @llamaindex/core@0.2.1
  • @llamaindex/env@0.1.11
  • @llamaindex/groq@0.0.2
  • @llamaindex/cloud@0.2.5
  • @llamaindex/openai@0.1.3

0.6.0

Minor Changes

• 11feef8: Add workflows

Patch Changes

• Updated dependencies [11feef8]
  • @llamaindex/core@0.2.0
  • @llamaindex/openai@0.1.2

0.5.27

Patch Changes

• 7edeb1c: feat: decouple openai from llamaindex module

  This should be a non-breaking change, but just you can now only install @llamaindex/openai to reduce the bundle size in the future

• Updated dependencies [7edeb1c]

  • @llamaindex/openai@0.1.1

0.5.26

Patch Changes

• ffe0cd1: faet: add openai o1 support
• ffe0cd1: feat: add PostgreSQL storage

0.5.25

Patch Changes

• 4810364: fix: handle RouterQueryEngine with string query

• d3bc663: refactor: export vector store only in nodejs environment on top level

  If you see some missing modules error, please change vector store related imports to llamaindex/vector-store

• Updated dependencies [4810364]

  • @llamaindex/cloud@0.2.4

0.5.24

Patch Changes

• Updated dependencies [0bf8d80]
  • @llamaindex/cloud@0.2.3

0.5.23

Patch Changes

• Updated dependencies [711c814]
  • @llamaindex/core@0.1.12

0.5.22

Patch Changes

• 4648da6: fix: wrong tiktoken version caused NextJs CL template run fail
• Updated dependencies [4648da6]
  • @llamaindex/env@0.1.10
  • @llamaindex/core@0.1.11

0.5.21

Patch Changes

• ae1149f: feat: add JSON streaming to JSONReader

• 2411c9f: Auto-create index for MongoDB vector store (if not exists)

• e8f229c: Remove logging from MongoDB Atlas Vector Store

• 11b3856: implement filters for MongoDBAtlasVectorSearch

• 83d7f41: Fix database insertion for PGVectorStore

  It will now:

  • throw an error if there is an insertion error.
  • Upsert documents with the same id.
  • add all documents to the database as a single INSERT call (inside a transaction).

• 0148354: refactor: prompt system

  Add PromptTemplate module with strong type check.

• 1711f6d: Export imageToDataUrl for using images in chat

• Updated dependencies [0148354]

  • @llamaindex/core@0.1.10

0.5.20

Patch Changes

• d9d6c56: Add support for MetadataFilters for PostgreSQL
• 22ff486: Add tiktoken WASM to withLlamaIndex
• eed0b04: fix: use LLM metadata mode for generating context of ContextChatEngine

0.5.19

Patch Changes

• fcbf183: implement llamacloud file service

0.5.18

Patch Changes

• 8b66cf4: feat: support organization id in llamacloud index
• Updated dependencies [e27e7dd]
  • @llamaindex/core@0.1.9

0.5.17

Patch Changes

• c654398: Implement Weaviate Vector Store in TS

0.5.16

Patch Changes

• 58abc57: fix: align version
• Updated dependencies [58abc57]
  • @llamaindex/cloud@0.2.2
  • @llamaindex/core@0.1.8
  • @llamaindex/env@0.1.9

0.5.15

Patch Changes

• 01c184c: Add is_empty operator for filtering vector store
• 07a275f: chore: bump openai

0.5.14

Patch Changes

• c825a2f: Add gpt-4o-mini to Azure. Add 2024-06-01 API version for Azure

0.5.13

Patch Changes

• Updated dependencies [04b2f8e]
  • @llamaindex/core@0.1.7

0.5.12

Patch Changes

• 345300f: feat: add splitByPage mode to LlamaParseReader
• da5cfc4: Add metadatafilter options to retriever constructors
• da5cfc4: Fix system prompt not used in ContextChatEngine
• Updated dependencies [0452af9]
  • @llamaindex/core@0.1.6

0.5.11

Patch Changes

• Updated dependencies [1f680d7]
  • @llamaindex/cloud@0.2.1

0.5.10

Patch Changes

• 086b940: feat: add DeepSeek LLM
• 5d5716b: feat: add a reader for JSON data
• 91d02a4: feat: support transform component callable
• fb6db45: feat: add pageSeparator params to LlamaParseReader
• Updated dependencies [91d02a4]
  • @llamaindex/core@0.1.5

0.5.9

Patch Changes

• 15962b3: feat: node parser refactor

  Align the text splitter logic with Python; it has almost the same logic as Python; Zod checks for input and better error messages and event system.

  This change will not be considered a breaking change since it doesn't have a significant output difference from the last version,
  but some edge cases will change, like the page separator and parameter for the constructor.

• Updated dependencies [15962b3]

  • @llamaindex/core@0.1.4

0.5.8

Patch Changes

• 3d5ba08: fix: update user agent in AssemblyAI
• d917cdc: Add azure interpreter tool to tool factory

0.5.7

Patch Changes

• ec59acd: fix: bundling issue with pnpm

0.5.6

Patch Changes

• 2562244: feat: add gpt4o-mini
• 325aa51: Implement Jina embedding through Jina api
• ab700ea: Add missing authentication to LlamaCloudIndex.fromDocuments
• 92f0782: feat: use query bundle
• 6cf6ae6: feat: abstract query type
• b7cfe5b: fix: passing max_token option to replicate's api call
• Updated dependencies [6cf6ae6]
  • @llamaindex/core@0.1.3

0.5.5

Patch Changes

• b974eea: Add support for Metadata filters
• Updated dependencies [b974eea]
  • @llamaindex/core@0.1.2

0.5.4

Patch Changes

• 1a65ead: feat: add vendorMultimodal params to LlamaParseReader

0.5.3

Patch Changes

• 9bbbc67: feat: add a reader for Discord messages
• b3681bf: fix: DataCloneError when using FunctionTool
• Updated dependencies [b3681bf]
  • @llamaindex/core@0.1.1

0.5.2

Patch Changes

• Updated dependencies [3ed6acc]
  • @llamaindex/cloud@0.2.0

0.5.1

Patch Changes

• 2774681: Add mixedbread's embeddings and reranking API
• a0f424e: corrected the regex in the react.ts file in extractToolUse & extractJsonStr functions, as mentioned in run-llama#1019

0.5.0

Minor Changes

• 16ef5dd: refactor: simplify callback manager

  Change event.detail.payload to event.detail

Patch Changes

• 16ef5dd: refactor: move callback manager & llm to core module

  For people who import llamaindex/llms/base or llamaindex/llms/utils,
  use @llamaindex/core/llms and @llamaindex/core/utils instead.

• 36ddec4: fix: typo in custom page separator parameter for LlamaParse

• Updated dependencies [16ef5dd]

• Updated dependencies [16ef5dd]

• Updated dependencies [36ddec4]

  • @llamaindex/core@0.1.0
  • @llamaindex/cloud@0.1.4

0.4.14

Patch Changes

• Updated dependencies [1c444d5]
  • @llamaindex/cloud@0.1.3

0.4.13

Patch Changes

• e8f8bea: feat: add boundingBox and targetPages to LlamaParseReader
• 304484b: feat: add ignoreErrors flag to LlamaParseReader

0.4.12

Patch Changes

• f326ab8: chore: bump version
• Updated dependencies [f326ab8]
  • @llamaindex/cloud@0.1.2
  • @llamaindex/core@0.0.3
  • @llamaindex/env@0.1.8

0.4.11

Patch Changes

• 8bf5b4a: fix: llama parse input spreadsheet

0.4.10

Patch Changes

• 7dce3d2: fix: disable External Filters for Gemini

0.4.9

Patch Changes

• 3a96a48: fix: anthroipic image input

0.4.8

Patch Changes

• 83ebdfb: fix: next.js build error

0.4.7

Patch Changes

• 41fe871: Add support for azure dynamic session tool
• 321c39d: fix: generate api as class
• f7f1af0: fix: throw error when no pipeline found
• Updated dependencies [41fe871]
• Updated dependencies [f10b41d]
• Updated dependencies [321c39d]
  • @llamaindex/env@0.1.7
  • @llamaindex/core@0.0.2
  • @llamaindex/cloud@0.1.1

0.4.6

Patch Changes

• 1feb23b: feat: Gemini tool calling for agent support
• 08c55ec: Add metadata to PDFs and use Uint8Array for readers content

0.4.5

Patch Changes

• 6c3e5d0: fix: switch to correct refe...

Release refs/tags/llamaindex@0.5.27

llamaindex

0.5.27

Patch Changes

• 7edeb1c: feat: decouple openai from llamaindex module

  This should be a non-breaking change, but just you can now only install @llamaindex/openai to reduce the bundle size in the future

• Updated dependencies [7edeb1c]

  • @llamaindex/openai@0.1.1

0.5.26

Patch Changes

• ffe0cd1: faet: add openai o1 support
• ffe0cd1: feat: add PostgreSQL storage

0.5.25

Patch Changes

• 4810364: fix: handle RouterQueryEngine with string query

• d3bc663: refactor: export vector store only in nodejs environment on top level

  If you see some missing modules error, please change vector store related imports to llamaindex/vector-store

• Updated dependencies [4810364]

  • @llamaindex/cloud@0.2.4

0.5.24

Patch Changes

• Updated dependencies [0bf8d80]
  • @llamaindex/cloud@0.2.3

0.5.23

Patch Changes

• Updated dependencies [711c814]
  • @llamaindex/core@0.1.12

0.5.22

Patch Changes

• 4648da6: fix: wrong tiktoken version caused NextJs CL template run fail
• Updated dependencies [4648da6]
  • @llamaindex/env@0.1.10
  • @llamaindex/core@0.1.11

0.5.21

Patch Changes

• ae1149f: feat: add JSON streaming to JSONReader

• 2411c9f: Auto-create index for MongoDB vector store (if not exists)

• e8f229c: Remove logging from MongoDB Atlas Vector Store

• 11b3856: implement filters for MongoDBAtlasVectorSearch

• 83d7f41: Fix database insertion for PGVectorStore

  It will now:

  • throw an error if there is an insertion error.
  • Upsert documents with the same id.
  • add all documents to the database as a single INSERT call (inside a transaction).

• 0148354: refactor: prompt system

  Add PromptTemplate module with strong type check.

• 1711f6d: Export imageToDataUrl for using images in chat

• Updated dependencies [0148354]

  • @llamaindex/core@0.1.10

0.5.20

Patch Changes

• d9d6c56: Add support for MetadataFilters for PostgreSQL
• 22ff486: Add tiktoken WASM to withLlamaIndex
• eed0b04: fix: use LLM metadata mode for generating context of ContextChatEngine

0.5.19

Patch Changes

• fcbf183: implement llamacloud file service

0.5.18

Patch Changes

• 8b66cf4: feat: support organization id in llamacloud index
• Updated dependencies [e27e7dd]
  • @llamaindex/core@0.1.9

0.5.17

Patch Changes

• c654398: Implement Weaviate Vector Store in TS

0.5.16

Patch Changes

• 58abc57: fix: align version
• Updated dependencies [58abc57]
  • @llamaindex/cloud@0.2.2
  • @llamaindex/core@0.1.8
  • @llamaindex/env@0.1.9

0.5.15

Patch Changes

• 01c184c: Add is_empty operator for filtering vector store
• 07a275f: chore: bump openai

0.5.14

Patch Changes

• c825a2f: Add gpt-4o-mini to Azure. Add 2024-06-01 API version for Azure

0.5.13

Patch Changes

• Updated dependencies [04b2f8e]
  • @llamaindex/core@0.1.7

0.5.12

Patch Changes

• 345300f: feat: add splitByPage mode to LlamaParseReader
• da5cfc4: Add metadatafilter options to retriever constructors
• da5cfc4: Fix system prompt not used in ContextChatEngine
• Updated dependencies [0452af9]
  • @llamaindex/core@0.1.6

0.5.11

Patch Changes

• Updated dependencies [1f680d7]
  • @llamaindex/cloud@0.2.1

0.5.10

Patch Changes

• 086b940: feat: add DeepSeek LLM
• 5d5716b: feat: add a reader for JSON data
• 91d02a4: feat: support transform component callable
• fb6db45: feat: add pageSeparator params to LlamaParseReader
• Updated dependencies [91d02a4]
  • @llamaindex/core@0.1.5

0.5.9

Patch Changes

• 15962b3: feat: node parser refactor

  Align the text splitter logic with Python; it has almost the same logic as Python; Zod checks for input and better error messages and event system.

  This change will not be considered a breaking change since it doesn't have a significant output difference from the last version,
  but some edge cases will change, like the page separator and parameter for the constructor.

• Updated dependencies [15962b3]

  • @llamaindex/core@0.1.4

0.5.8

Patch Changes

• 3d5ba08: fix: update user agent in AssemblyAI
• d917cdc: Add azure interpreter tool to tool factory

0.5.7

Patch Changes

• ec59acd: fix: bundling issue with pnpm

0.5.6

Patch Changes

• 2562244: feat: add gpt4o-mini
• 325aa51: Implement Jina embedding through Jina api
• ab700ea: Add missing authentication to LlamaCloudIndex.fromDocuments
• 92f0782: feat: use query bundle
• 6cf6ae6: feat: abstract query type
• b7cfe5b: fix: passing max_token option to replicate's api call
• Updated dependencies [6cf6ae6]
  • @llamaindex/core@0.1.3

0.5.5

Patch Changes

• b974eea: Add support for Metadata filters
• Updated dependencies [b974eea]
  • @llamaindex/core@0.1.2

0.5.4

Patch Changes

• 1a65ead: feat: add vendorMultimodal params to LlamaParseReader

0.5.3

Patch Changes

• 9bbbc67: feat: add a reader for Discord messages
• b3681bf: fix: DataCloneError when using FunctionTool
• Updated dependencies [b3681bf]
  • @llamaindex/core@0.1.1

0.5.2

Patch Changes

• Updated dependencies [3ed6acc]
  • @llamaindex/cloud@0.2.0

0.5.1

Patch Changes

• 2774681: Add mixedbread's embeddings and reranking API
• a0f424e: corrected the regex in the react.ts file in extractToolUse & extractJsonStr functions, as mentioned in run-llama#1019

0.5.0

Minor Changes

• 16ef5dd: refactor: simplify callback manager

  Change event.detail.payload to event.detail

Patch Changes

• 16ef5dd: refactor: move callback manager & llm to core module

  For people who import llamaindex/llms/base or llamaindex/llms/utils,
  use @llamaindex/core/llms and @llamaindex/core/utils instead.

• 36ddec4: fix: typo in custom page separator parameter for LlamaParse

• Updated dependencies [16ef5dd]

• Updated dependencies [16ef5dd]

• Updated dependencies [36ddec4]

  • @llamaindex/core@0.1.0
  • @llamaindex/cloud@0.1.4

0.4.14

Patch Changes

• Updated dependencies [1c444d5]
  • @llamaindex/cloud@0.1.3

0.4.13

Patch Changes

• e8f8bea: feat: add boundingBox and targetPages to LlamaParseReader
• 304484b: feat: add ignoreErrors flag to LlamaParseReader

0.4.12

Patch Changes

• f326ab8: chore: bump version
• Updated dependencies [f326ab8]
  • @llamaindex/cloud@0.1.2
  • @llamaindex/core@0.0.3
  • @llamaindex/env@0.1.8

0.4.11

Patch Changes

• 8bf5b4a: fix: llama parse input spreadsheet

0.4.10

Patch Changes

• 7dce3d2: fix: disable External Filters for Gemini

0.4.9

Patch Changes

• 3a96a48: fix: anthroipic image input

0.4.8

Patch Changes

• 83ebdfb: fix: next.js build error

0.4.7

Patch Changes

• 41fe871: Add support for azure dynamic session tool
• 321c39d: fix: generate api as class
• f7f1af0: fix: throw error when no pipeline found
• Updated dependencies [41fe871]
• Updated dependencies [f10b41d]
• Updated dependencies [321c39d]
  • @llamaindex/env@0.1.7
  • @llamaindex/core@0.0.2
  • @llamaindex/cloud@0.1.1

0.4.6

Patch Changes

• 1feb23b: feat: Gemini tool calling for agent support
• 08c55ec: Add metadata to PDFs and use Uint8Array for readers content

0.4.5

Patch Changes

• 6c3e5d0: fix: switch to correct reference for a static function

0.4.4

Patch Changes

• 42eb73a: Fix IngestionPipeline not working without vectorStores

0.4.3

Patch Changes

• 2ef62a9: feat: added support for embeddings via HuggingFace Inference API
• Updated dependencies [d4e853c]
• Updated dependencies [a94b8ec]
  • @llamaindex/env@0.1.6

0.4.2

Patch Changes

• a87a4d1: feat: added tool support calling for Bedrock's Calude and general llm support for agents
• 0730140: include node relationships when converting jsonToDoc
• Updated dependencies [f3b34b4]
  • @llamaindex/env@0.1.5

0.4.1

Patch Changes

• 3c47910: fix: groq llm
• ed467a9: Add model ids for Anthropic Claude 3.5 Sonnet model on Anthropic and Bedrock
• cba5406: fix: every Llama Parse job being called "blob"
• Updated dependencies [56fabbb]
  • @llamaindex/env@0.1.4

0.4.0

Minor Changes

• 436bc41: Unify chat engine response and agent response

Patch Changes

• a44e54f: Truncate text to embed for OpenAI if it exceeds maxTokens
• a51ed8d: feat: add support for managed identity for Azure OpenAI
• d3b635b: fix: agents to use chat history

0.3.17

Patch Changes

• 6bc5bdd: feat: add cache disabling, fast mode, do not unroll columns mode and custom page separator to LlamaParseReader
• bf25ff6: fix: polyfill for cloudflare worker
• e6d6576: chore: use unpdf

0.3.16

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

0.3.15

Patch Changes

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

0.3.14

Patch Changes

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

0.3.13

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

0.3.12

Patch Changes

• 34fb1d8: fix: cloudflare dev

0.3.11

Pat...

Release refs/tags/llamaindex@0.5.26

llamaindex

0.5.26

Patch Changes

• ffe0cd1: faet: add openai o1 support
• ffe0cd1: feat: add PostgreSQL storage

0.5.25

Patch Changes

• 4810364: fix: handle RouterQueryEngine with string query

• d3bc663: refactor: export vector store only in nodejs environment on top level

  If you see some missing modules error, please change vector store related imports to llamaindex/vector-store

• Updated dependencies [4810364]

  • @llamaindex/cloud@0.2.4

0.5.24

Patch Changes

• Updated dependencies [0bf8d80]
  • @llamaindex/cloud@0.2.3

0.5.23

Patch Changes

• Updated dependencies [711c814]
  • @llamaindex/core@0.1.12

0.5.22

Patch Changes

• 4648da6: fix: wrong tiktoken version caused NextJs CL template run fail
• Updated dependencies [4648da6]
  • @llamaindex/env@0.1.10
  • @llamaindex/core@0.1.11

0.5.21

Patch Changes

• ae1149f: feat: add JSON streaming to JSONReader

• 2411c9f: Auto-create index for MongoDB vector store (if not exists)

• e8f229c: Remove logging from MongoDB Atlas Vector Store

• 11b3856: implement filters for MongoDBAtlasVectorSearch

• 83d7f41: Fix database insertion for PGVectorStore

  It will now:

  • throw an error if there is an insertion error.
  • Upsert documents with the same id.
  • add all documents to the database as a single INSERT call (inside a transaction).

• 0148354: refactor: prompt system

  Add PromptTemplate module with strong type check.

• 1711f6d: Export imageToDataUrl for using images in chat

• Updated dependencies [0148354]

  • @llamaindex/core@0.1.10

0.5.20

Patch Changes

• d9d6c56: Add support for MetadataFilters for PostgreSQL
• 22ff486: Add tiktoken WASM to withLlamaIndex
• eed0b04: fix: use LLM metadata mode for generating context of ContextChatEngine

0.5.19

Patch Changes

• fcbf183: implement llamacloud file service

0.5.18

Patch Changes

• 8b66cf4: feat: support organization id in llamacloud index
• Updated dependencies [e27e7dd]
  • @llamaindex/core@0.1.9

0.5.17

Patch Changes

• c654398: Implement Weaviate Vector Store in TS

0.5.16

Patch Changes

• 58abc57: fix: align version
• Updated dependencies [58abc57]
  • @llamaindex/cloud@0.2.2
  • @llamaindex/core@0.1.8
  • @llamaindex/env@0.1.9

0.5.15

Patch Changes

• 01c184c: Add is_empty operator for filtering vector store
• 07a275f: chore: bump openai

0.5.14

Patch Changes

• c825a2f: Add gpt-4o-mini to Azure. Add 2024-06-01 API version for Azure

0.5.13

Patch Changes

• Updated dependencies [04b2f8e]
  • @llamaindex/core@0.1.7

0.5.12

Patch Changes

• 345300f: feat: add splitByPage mode to LlamaParseReader
• da5cfc4: Add metadatafilter options to retriever constructors
• da5cfc4: Fix system prompt not used in ContextChatEngine
• Updated dependencies [0452af9]
  • @llamaindex/core@0.1.6

0.5.11

Patch Changes

• Updated dependencies [1f680d7]
  • @llamaindex/cloud@0.2.1

0.5.10

Patch Changes

• 086b940: feat: add DeepSeek LLM
• 5d5716b: feat: add a reader for JSON data
• 91d02a4: feat: support transform component callable
• fb6db45: feat: add pageSeparator params to LlamaParseReader
• Updated dependencies [91d02a4]
  • @llamaindex/core@0.1.5

0.5.9

Patch Changes

• 15962b3: feat: node parser refactor

  Align the text splitter logic with Python; it has almost the same logic as Python; Zod checks for input and better error messages and event system.

  This change will not be considered a breaking change since it doesn't have a significant output difference from the last version,
  but some edge cases will change, like the page separator and parameter for the constructor.

• Updated dependencies [15962b3]

  • @llamaindex/core@0.1.4

0.5.8

Patch Changes

• 3d5ba08: fix: update user agent in AssemblyAI
• d917cdc: Add azure interpreter tool to tool factory

0.5.7

Patch Changes

• ec59acd: fix: bundling issue with pnpm

0.5.6

Patch Changes

• 2562244: feat: add gpt4o-mini
• 325aa51: Implement Jina embedding through Jina api
• ab700ea: Add missing authentication to LlamaCloudIndex.fromDocuments
• 92f0782: feat: use query bundle
• 6cf6ae6: feat: abstract query type
• b7cfe5b: fix: passing max_token option to replicate's api call
• Updated dependencies [6cf6ae6]
  • @llamaindex/core@0.1.3

0.5.5

Patch Changes

• b974eea: Add support for Metadata filters
• Updated dependencies [b974eea]
  • @llamaindex/core@0.1.2

0.5.4

Patch Changes

• 1a65ead: feat: add vendorMultimodal params to LlamaParseReader

0.5.3

Patch Changes

• 9bbbc67: feat: add a reader for Discord messages
• b3681bf: fix: DataCloneError when using FunctionTool
• Updated dependencies [b3681bf]
  • @llamaindex/core@0.1.1

0.5.2

Patch Changes

• Updated dependencies [3ed6acc]
  • @llamaindex/cloud@0.2.0

0.5.1

Patch Changes

• 2774681: Add mixedbread's embeddings and reranking API
• a0f424e: corrected the regex in the react.ts file in extractToolUse & extractJsonStr functions, as mentioned in run-llama#1019

0.5.0

Minor Changes

• 16ef5dd: refactor: simplify callback manager

  Change event.detail.payload to event.detail

Patch Changes

• 16ef5dd: refactor: move callback manager & llm to core module

  For people who import llamaindex/llms/base or llamaindex/llms/utils,
  use @llamaindex/core/llms and @llamaindex/core/utils instead.

• 36ddec4: fix: typo in custom page separator parameter for LlamaParse

• Updated dependencies [16ef5dd]

• Updated dependencies [16ef5dd]

• Updated dependencies [36ddec4]

  • @llamaindex/core@0.1.0
  • @llamaindex/cloud@0.1.4

0.4.14

Patch Changes

• Updated dependencies [1c444d5]
  • @llamaindex/cloud@0.1.3

0.4.13

Patch Changes

• e8f8bea: feat: add boundingBox and targetPages to LlamaParseReader
• 304484b: feat: add ignoreErrors flag to LlamaParseReader

0.4.12

Patch Changes

• f326ab8: chore: bump version
• Updated dependencies [f326ab8]
  • @llamaindex/cloud@0.1.2
  • @llamaindex/core@0.0.3
  • @llamaindex/env@0.1.8

0.4.11

Patch Changes

• 8bf5b4a: fix: llama parse input spreadsheet

0.4.10

Patch Changes

• 7dce3d2: fix: disable External Filters for Gemini

0.4.9

Patch Changes

• 3a96a48: fix: anthroipic image input

0.4.8

Patch Changes

• 83ebdfb: fix: next.js build error

0.4.7

Patch Changes

• 41fe871: Add support for azure dynamic session tool
• 321c39d: fix: generate api as class
• f7f1af0: fix: throw error when no pipeline found
• Updated dependencies [41fe871]
• Updated dependencies [f10b41d]
• Updated dependencies [321c39d]
  • @llamaindex/env@0.1.7
  • @llamaindex/core@0.0.2
  • @llamaindex/cloud@0.1.1

0.4.6

Patch Changes

• 1feb23b: feat: Gemini tool calling for agent support
• 08c55ec: Add metadata to PDFs and use Uint8Array for readers content

0.4.5

Patch Changes

• 6c3e5d0: fix: switch to correct reference for a static function

0.4.4

Patch Changes

• 42eb73a: Fix IngestionPipeline not working without vectorStores

0.4.3

Patch Changes

• 2ef62a9: feat: added support for embeddings via HuggingFace Inference API
• Updated dependencies [d4e853c]
• Updated dependencies [a94b8ec]
  • @llamaindex/env@0.1.6

0.4.2

Patch Changes

• a87a4d1: feat: added tool support calling for Bedrock's Calude and general llm support for agents
• 0730140: include node relationships when converting jsonToDoc
• Updated dependencies [f3b34b4]
  • @llamaindex/env@0.1.5

0.4.1

Patch Changes

• 3c47910: fix: groq llm
• ed467a9: Add model ids for Anthropic Claude 3.5 Sonnet model on Anthropic and Bedrock
• cba5406: fix: every Llama Parse job being called "blob"
• Updated dependencies [56fabbb]
  • @llamaindex/env@0.1.4

0.4.0

Minor Changes

• 436bc41: Unify chat engine response and agent response

Patch Changes

• a44e54f: Truncate text to embed for OpenAI if it exceeds maxTokens
• a51ed8d: feat: add support for managed identity for Azure OpenAI
• d3b635b: fix: agents to use chat history

0.3.17

Patch Changes

• 6bc5bdd: feat: add cache disabling, fast mode, do not unroll columns mode and custom page separator to LlamaParseReader
• bf25ff6: fix: polyfill for cloudflare worker
• e6d6576: chore: use unpdf

0.3.16

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

0.3.15

Patch Changes

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

0.3.14

Patch Changes

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

0.3.13

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

0.3.12

Patch Changes

• 34fb1d8: fix: cloudflare dev

0.3.11

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 no...

Release refs/tags/llamaindex@0.5.25

llamaindex

0.5.25

Patch Changes

• 4810364: fix: handle RouterQueryEngine with string query

• d3bc663: refactor: export vector store only in nodejs environment on top level

  If you see some missing modules error, please change vector store related imports to llamaindex/vector-store

• Updated dependencies [4810364]

  • @llamaindex/cloud@0.2.4

0.5.24

Patch Changes

• Updated dependencies [0bf8d80]
  • @llamaindex/cloud@0.2.3

0.5.23

Patch Changes

• Updated dependencies [711c814]
  • @llamaindex/core@0.1.12

0.5.22

Patch Changes

• 4648da6: fix: wrong tiktoken version caused NextJs CL template run fail
• Updated dependencies [4648da6]
  • @llamaindex/env@0.1.10
  • @llamaindex/core@0.1.11

0.5.21

Patch Changes

• ae1149f: feat: add JSON streaming to JSONReader

• 2411c9f: Auto-create index for MongoDB vector store (if not exists)

• e8f229c: Remove logging from MongoDB Atlas Vector Store

• 11b3856: implement filters for MongoDBAtlasVectorSearch

• 83d7f41: Fix database insertion for PGVectorStore

  It will now:

  • throw an error if there is an insertion error.
  • Upsert documents with the same id.
  • add all documents to the database as a single INSERT call (inside a transaction).

• 0148354: refactor: prompt system

  Add PromptTemplate module with strong type check.

• 1711f6d: Export imageToDataUrl for using images in chat

• Updated dependencies [0148354]

  • @llamaindex/core@0.1.10

0.5.20

Patch Changes

• d9d6c56: Add support for MetadataFilters for PostgreSQL
• 22ff486: Add tiktoken WASM to withLlamaIndex
• eed0b04: fix: use LLM metadata mode for generating context of ContextChatEngine

0.5.19

Patch Changes

• fcbf183: implement llamacloud file service

0.5.18

Patch Changes

• 8b66cf4: feat: support organization id in llamacloud index
• Updated dependencies [e27e7dd]
  • @llamaindex/core@0.1.9

0.5.17

Patch Changes

• c654398: Implement Weaviate Vector Store in TS

0.5.16

Patch Changes

• 58abc57: fix: align version
• Updated dependencies [58abc57]
  • @llamaindex/cloud@0.2.2
  • @llamaindex/core@0.1.8
  • @llamaindex/env@0.1.9

0.5.15

Patch Changes

• 01c184c: Add is_empty operator for filtering vector store
• 07a275f: chore: bump openai

0.5.14

Patch Changes

• c825a2f: Add gpt-4o-mini to Azure. Add 2024-06-01 API version for Azure

0.5.13

Patch Changes

• Updated dependencies [04b2f8e]
  • @llamaindex/core@0.1.7

0.5.12

Patch Changes

• 345300f: feat: add splitByPage mode to LlamaParseReader
• da5cfc4: Add metadatafilter options to retriever constructors
• da5cfc4: Fix system prompt not used in ContextChatEngine
• Updated dependencies [0452af9]
  • @llamaindex/core@0.1.6

0.5.11

Patch Changes

• Updated dependencies [1f680d7]
  • @llamaindex/cloud@0.2.1

0.5.10

Patch Changes

• 086b940: feat: add DeepSeek LLM
• 5d5716b: feat: add a reader for JSON data
• 91d02a4: feat: support transform component callable
• fb6db45: feat: add pageSeparator params to LlamaParseReader
• Updated dependencies [91d02a4]
  • @llamaindex/core@0.1.5

0.5.9

Patch Changes

• 15962b3: feat: node parser refactor

  Align the text splitter logic with Python; it has almost the same logic as Python; Zod checks for input and better error messages and event system.

  This change will not be considered a breaking change since it doesn't have a significant output difference from the last version,
  but some edge cases will change, like the page separator and parameter for the constructor.

• Updated dependencies [15962b3]

  • @llamaindex/core@0.1.4

0.5.8

Patch Changes

• 3d5ba08: fix: update user agent in AssemblyAI
• d917cdc: Add azure interpreter tool to tool factory

0.5.7

Patch Changes

• ec59acd: fix: bundling issue with pnpm

0.5.6

Patch Changes

• 2562244: feat: add gpt4o-mini
• 325aa51: Implement Jina embedding through Jina api
• ab700ea: Add missing authentication to LlamaCloudIndex.fromDocuments
• 92f0782: feat: use query bundle
• 6cf6ae6: feat: abstract query type
• b7cfe5b: fix: passing max_token option to replicate's api call
• Updated dependencies [6cf6ae6]
  • @llamaindex/core@0.1.3

0.5.5

Patch Changes

• b974eea: Add support for Metadata filters
• Updated dependencies [b974eea]
  • @llamaindex/core@0.1.2

0.5.4

Patch Changes

• 1a65ead: feat: add vendorMultimodal params to LlamaParseReader

0.5.3

Patch Changes

• 9bbbc67: feat: add a reader for Discord messages
• b3681bf: fix: DataCloneError when using FunctionTool
• Updated dependencies [b3681bf]
  • @llamaindex/core@0.1.1

0.5.2

Patch Changes

• Updated dependencies [3ed6acc]
  • @llamaindex/cloud@0.2.0

0.5.1

Patch Changes

• 2774681: Add mixedbread's embeddings and reranking API
• a0f424e: corrected the regex in the react.ts file in extractToolUse & extractJsonStr functions, as mentioned in run-llama#1019

0.5.0

Minor Changes

• 16ef5dd: refactor: simplify callback manager

  Change event.detail.payload to event.detail

Patch Changes

• 16ef5dd: refactor: move callback manager & llm to core module

  For people who import llamaindex/llms/base or llamaindex/llms/utils,
  use @llamaindex/core/llms and @llamaindex/core/utils instead.

• 36ddec4: fix: typo in custom page separator parameter for LlamaParse

• Updated dependencies [16ef5dd]

• Updated dependencies [16ef5dd]

• Updated dependencies [36ddec4]

  • @llamaindex/core@0.1.0
  • @llamaindex/cloud@0.1.4

0.4.14

Patch Changes

• Updated dependencies [1c444d5]
  • @llamaindex/cloud@0.1.3

0.4.13

Patch Changes

• e8f8bea: feat: add boundingBox and targetPages to LlamaParseReader
• 304484b: feat: add ignoreErrors flag to LlamaParseReader

0.4.12

Patch Changes

• f326ab8: chore: bump version
• Updated dependencies [f326ab8]
  • @llamaindex/cloud@0.1.2
  • @llamaindex/core@0.0.3
  • @llamaindex/env@0.1.8

0.4.11

Patch Changes

• 8bf5b4a: fix: llama parse input spreadsheet

0.4.10

Patch Changes

• 7dce3d2: fix: disable External Filters for Gemini

0.4.9

Patch Changes

• 3a96a48: fix: anthroipic image input

0.4.8

Patch Changes

• 83ebdfb: fix: next.js build error

0.4.7

Patch Changes

• 41fe871: Add support for azure dynamic session tool
• 321c39d: fix: generate api as class
• f7f1af0: fix: throw error when no pipeline found
• Updated dependencies [41fe871]
• Updated dependencies [f10b41d]
• Updated dependencies [321c39d]
  • @llamaindex/env@0.1.7
  • @llamaindex/core@0.0.2
  • @llamaindex/cloud@0.1.1

0.4.6

Patch Changes

• 1feb23b: feat: Gemini tool calling for agent support
• 08c55ec: Add metadata to PDFs and use Uint8Array for readers content

0.4.5

Patch Changes

• 6c3e5d0: fix: switch to correct reference for a static function

0.4.4

Patch Changes

• 42eb73a: Fix IngestionPipeline not working without vectorStores

0.4.3

Patch Changes

• 2ef62a9: feat: added support for embeddings via HuggingFace Inference API
• Updated dependencies [d4e853c]
• Updated dependencies [a94b8ec]
  • @llamaindex/env@0.1.6

0.4.2

Patch Changes

• a87a4d1: feat: added tool support calling for Bedrock's Calude and general llm support for agents
• 0730140: include node relationships when converting jsonToDoc
• Updated dependencies [f3b34b4]
  • @llamaindex/env@0.1.5

0.4.1

Patch Changes

• 3c47910: fix: groq llm
• ed467a9: Add model ids for Anthropic Claude 3.5 Sonnet model on Anthropic and Bedrock
• cba5406: fix: every Llama Parse job being called "blob"
• Updated dependencies [56fabbb]
  • @llamaindex/env@0.1.4

0.4.0

Minor Changes

• 436bc41: Unify chat engine response and agent response

Patch Changes

• a44e54f: Truncate text to embed for OpenAI if it exceeds maxTokens
• a51ed8d: feat: add support for managed identity for Azure OpenAI
• d3b635b: fix: agents to use chat history

0.3.17

Patch Changes

• 6bc5bdd: feat: add cache disabling, fast mode, do not unroll columns mode and custom page separator to LlamaParseReader
• bf25ff6: fix: polyfill for cloudflare worker
• e6d6576: chore: use unpdf

0.3.16

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

0.3.15

Patch Changes

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

0.3.14

Patch Changes

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

0.3.13

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

0.3.12

Patch Changes

• 34fb1d8: fix: cloudflare dev

0.3.11

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: F...

Release refs/tags/llamaindex@0.5.24

llamaindex

0.5.24

Patch Changes

• Updated dependencies [0bf8d80]
  • @llamaindex/cloud@0.2.3

0.5.23

Patch Changes

• Updated dependencies [711c814]
  • @llamaindex/core@0.1.12

0.5.22

Patch Changes

• 4648da6: fix: wrong tiktoken version caused NextJs CL template run fail
• Updated dependencies [4648da6]
  • @llamaindex/env@0.1.10
  • @llamaindex/core@0.1.11

0.5.21

Patch Changes

• ae1149f: feat: add JSON streaming to JSONReader

• 2411c9f: Auto-create index for MongoDB vector store (if not exists)

• e8f229c: Remove logging from MongoDB Atlas Vector Store

• 11b3856: implement filters for MongoDBAtlasVectorSearch

• 83d7f41: Fix database insertion for PGVectorStore

  It will now:

  • throw an error if there is an insertion error.
  • Upsert documents with the same id.
  • add all documents to the database as a single INSERT call (inside a transaction).

• 0148354: refactor: prompt system

  Add PromptTemplate module with strong type check.

• 1711f6d: Export imageToDataUrl for using images in chat

• Updated dependencies [0148354]

  • @llamaindex/core@0.1.10

0.5.20

Patch Changes

• d9d6c56: Add support for MetadataFilters for PostgreSQL
• 22ff486: Add tiktoken WASM to withLlamaIndex
• eed0b04: fix: use LLM metadata mode for generating context of ContextChatEngine

0.5.19

Patch Changes

• fcbf183: implement llamacloud file service

0.5.18

Patch Changes

• 8b66cf4: feat: support organization id in llamacloud index
• Updated dependencies [e27e7dd]
  • @llamaindex/core@0.1.9

0.5.17

Patch Changes

• c654398: Implement Weaviate Vector Store in TS

0.5.16

Patch Changes

• 58abc57: fix: align version
• Updated dependencies [58abc57]
  • @llamaindex/cloud@0.2.2
  • @llamaindex/core@0.1.8
  • @llamaindex/env@0.1.9

0.5.15

Patch Changes

• 01c184c: Add is_empty operator for filtering vector store
• 07a275f: chore: bump openai

0.5.14

Patch Changes

• c825a2f: Add gpt-4o-mini to Azure. Add 2024-06-01 API version for Azure

0.5.13

Patch Changes

• Updated dependencies [04b2f8e]
  • @llamaindex/core@0.1.7

0.5.12

Patch Changes

• 345300f: feat: add splitByPage mode to LlamaParseReader
• da5cfc4: Add metadatafilter options to retriever constructors
• da5cfc4: Fix system prompt not used in ContextChatEngine
• Updated dependencies [0452af9]
  • @llamaindex/core@0.1.6

0.5.11

Patch Changes

• Updated dependencies [1f680d7]
  • @llamaindex/cloud@0.2.1

0.5.10

Patch Changes

• 086b940: feat: add DeepSeek LLM
• 5d5716b: feat: add a reader for JSON data
• 91d02a4: feat: support transform component callable
• fb6db45: feat: add pageSeparator params to LlamaParseReader
• Updated dependencies [91d02a4]
  • @llamaindex/core@0.1.5

0.5.9

Patch Changes

• 15962b3: feat: node parser refactor

  Align the text splitter logic with Python; it has almost the same logic as Python; Zod checks for input and better error messages and event system.

  This change will not be considered a breaking change since it doesn't have a significant output difference from the last version,
  but some edge cases will change, like the page separator and parameter for the constructor.

• Updated dependencies [15962b3]

  • @llamaindex/core@0.1.4

0.5.8

Patch Changes

• 3d5ba08: fix: update user agent in AssemblyAI
• d917cdc: Add azure interpreter tool to tool factory

0.5.7

Patch Changes

• ec59acd: fix: bundling issue with pnpm

0.5.6

Patch Changes

• 2562244: feat: add gpt4o-mini
• 325aa51: Implement Jina embedding through Jina api
• ab700ea: Add missing authentication to LlamaCloudIndex.fromDocuments
• 92f0782: feat: use query bundle
• 6cf6ae6: feat: abstract query type
• b7cfe5b: fix: passing max_token option to replicate's api call
• Updated dependencies [6cf6ae6]
  • @llamaindex/core@0.1.3

0.5.5

Patch Changes

• b974eea: Add support for Metadata filters
• Updated dependencies [b974eea]
  • @llamaindex/core@0.1.2

0.5.4

Patch Changes

• 1a65ead: feat: add vendorMultimodal params to LlamaParseReader

0.5.3

Patch Changes

• 9bbbc67: feat: add a reader for Discord messages
• b3681bf: fix: DataCloneError when using FunctionTool
• Updated dependencies [b3681bf]
  • @llamaindex/core@0.1.1

0.5.2

Patch Changes

• Updated dependencies [3ed6acc]
  • @llamaindex/cloud@0.2.0

0.5.1

Patch Changes

• 2774681: Add mixedbread's embeddings and reranking API
• a0f424e: corrected the regex in the react.ts file in extractToolUse & extractJsonStr functions, as mentioned in run-llama#1019

0.5.0

Minor Changes

• 16ef5dd: refactor: simplify callback manager

  Change event.detail.payload to event.detail

Patch Changes

• 16ef5dd: refactor: move callback manager & llm to core module

  For people who import llamaindex/llms/base or llamaindex/llms/utils,
  use @llamaindex/core/llms and @llamaindex/core/utils instead.

• 36ddec4: fix: typo in custom page separator parameter for LlamaParse

• Updated dependencies [16ef5dd]

• Updated dependencies [16ef5dd]

• Updated dependencies [36ddec4]

  • @llamaindex/core@0.1.0
  • @llamaindex/cloud@0.1.4

0.4.14

Patch Changes

• Updated dependencies [1c444d5]
  • @llamaindex/cloud@0.1.3

0.4.13

Patch Changes

• e8f8bea: feat: add boundingBox and targetPages to LlamaParseReader
• 304484b: feat: add ignoreErrors flag to LlamaParseReader

0.4.12

Patch Changes

• f326ab8: chore: bump version
• Updated dependencies [f326ab8]
  • @llamaindex/cloud@0.1.2
  • @llamaindex/core@0.0.3
  • @llamaindex/env@0.1.8

0.4.11

Patch Changes

• 8bf5b4a: fix: llama parse input spreadsheet

0.4.10

Patch Changes

• 7dce3d2: fix: disable External Filters for Gemini

0.4.9

Patch Changes

• 3a96a48: fix: anthroipic image input

0.4.8

Patch Changes

• 83ebdfb: fix: next.js build error

0.4.7

Patch Changes

• 41fe871: Add support for azure dynamic session tool
• 321c39d: fix: generate api as class
• f7f1af0: fix: throw error when no pipeline found
• Updated dependencies [41fe871]
• Updated dependencies [f10b41d]
• Updated dependencies [321c39d]
  • @llamaindex/env@0.1.7
  • @llamaindex/core@0.0.2
  • @llamaindex/cloud@0.1.1

0.4.6

Patch Changes

• 1feb23b: feat: Gemini tool calling for agent support
• 08c55ec: Add metadata to PDFs and use Uint8Array for readers content

0.4.5

Patch Changes

• 6c3e5d0: fix: switch to correct reference for a static function

0.4.4

Patch Changes

• 42eb73a: Fix IngestionPipeline not working without vectorStores

0.4.3

Patch Changes

• 2ef62a9: feat: added support for embeddings via HuggingFace Inference API
• Updated dependencies [d4e853c]
• Updated dependencies [a94b8ec]
  • @llamaindex/env@0.1.6

0.4.2

Patch Changes

• a87a4d1: feat: added tool support calling for Bedrock's Calude and general llm support for agents
• 0730140: include node relationships when converting jsonToDoc
• Updated dependencies [f3b34b4]
  • @llamaindex/env@0.1.5

0.4.1

Patch Changes

• 3c47910: fix: groq llm
• ed467a9: Add model ids for Anthropic Claude 3.5 Sonnet model on Anthropic and Bedrock
• cba5406: fix: every Llama Parse job being called "blob"
• Updated dependencies [56fabbb]
  • @llamaindex/env@0.1.4

0.4.0

Minor Changes

• 436bc41: Unify chat engine response and agent response

Patch Changes

• a44e54f: Truncate text to embed for OpenAI if it exceeds maxTokens
• a51ed8d: feat: add support for managed identity for Azure OpenAI
• d3b635b: fix: agents to use chat history

0.3.17

Patch Changes

• 6bc5bdd: feat: add cache disabling, fast mode, do not unroll columns mode and custom page separator to LlamaParseReader
• bf25ff6: fix: polyfill for cloudflare worker
• e6d6576: chore: use unpdf

0.3.16

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

0.3.15

Patch Changes

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

0.3.14

Patch Changes

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

0.3.13

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

0.3.12

Patch Changes

• 34fb1d8: fix: cloudflare dev

0.3.11

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/env@0.1.3

0.3.10

Patch Changes

• 4aba02e: feat: support gpt4-o

0.3.9

Patch Changes

• c3747d0: fix: import @xenova/transformers

  For now, if you use llamaindex in next.js, you need to ad...

Release refs/tags/llamaindex@0.5.7

llamaindex

0.5.7

Patch Changes

• ec59acd: fix: bundling issue with pnpm

0.5.6

Patch Changes

• 2562244: feat: add gpt4o-mini
• 325aa51: Implement Jina embedding through Jina api
• ab700ea: Add missing authentication to LlamaCloudIndex.fromDocuments
• 92f0782: feat: use query bundle
• 6cf6ae6: feat: abstract query type
• b7cfe5b: fix: passing max_token option to replicate's api call
• Updated dependencies [6cf6ae6]
  • @llamaindex/core@0.1.3

0.5.5

Patch Changes

• b974eea: Add support for Metadata filters
• Updated dependencies [b974eea]
  • @llamaindex/core@0.1.2

0.5.4

Patch Changes

• 1a65ead: feat: add vendorMultimodal params to LlamaParseReader

0.5.3

Patch Changes

• 9bbbc67: feat: add a reader for Discord messages
• b3681bf: fix: DataCloneError when using FunctionTool
• Updated dependencies [b3681bf]
  • @llamaindex/core@0.1.1

0.5.2

Patch Changes

• Updated dependencies [3ed6acc]
  • @llamaindex/cloud@0.2.0

0.5.1

Patch Changes

• 2774681: Add mixedbread's embeddings and reranking API
• a0f424e: corrected the regex in the react.ts file in extractToolUse & extractJsonStr functions, as mentioned in run-llama#1019

0.5.0

Minor Changes

• 16ef5dd: refactor: simplify callback manager

  Change event.detail.payload to event.detail

Patch Changes

• 16ef5dd: refactor: move callback manager & llm to core module

  For people who import llamaindex/llms/base or llamaindex/llms/utils,
  use @llamaindex/core/llms and @llamaindex/core/utils instead.

• 36ddec4: fix: typo in custom page separator parameter for LlamaParse

• Updated dependencies [16ef5dd]

• Updated dependencies [16ef5dd]

• Updated dependencies [36ddec4]

  • @llamaindex/core@0.1.0
  • @llamaindex/cloud@0.1.4

0.4.14

Patch Changes

• Updated dependencies [1c444d5]
  • @llamaindex/cloud@0.1.3

0.4.13

Patch Changes

• e8f8bea: feat: add boundingBox and targetPages to LlamaParseReader
• 304484b: feat: add ignoreErrors flag to LlamaParseReader

0.4.12

Patch Changes

• f326ab8: chore: bump version
• Updated dependencies [f326ab8]
  • @llamaindex/cloud@0.1.2
  • @llamaindex/core@0.0.3
  • @llamaindex/env@0.1.8

0.4.11

Patch Changes

• 8bf5b4a: fix: llama parse input spreadsheet

0.4.10

Patch Changes

• 7dce3d2: fix: disable External Filters for Gemini

0.4.9

Patch Changes

• 3a96a48: fix: anthroipic image input

0.4.8

Patch Changes

• 83ebdfb: fix: next.js build error

0.4.7

Patch Changes

• 41fe871: Add support for azure dynamic session tool
• 321c39d: fix: generate api as class
• f7f1af0: fix: throw error when no pipeline found
• Updated dependencies [41fe871]
• Updated dependencies [f10b41d]
• Updated dependencies [321c39d]
  • @llamaindex/env@0.1.7
  • @llamaindex/core@0.0.2
  • @llamaindex/cloud@0.1.1

0.4.6

Patch Changes

• 1feb23b: feat: Gemini tool calling for agent support
• 08c55ec: Add metadata to PDFs and use Uint8Array for readers content

0.4.5

Patch Changes

• 6c3e5d0: fix: switch to correct reference for a static function

0.4.4

Patch Changes

• 42eb73a: Fix IngestionPipeline not working without vectorStores

0.4.3

Patch Changes

• 2ef62a9: feat: added support for embeddings via HuggingFace Inference API
• Updated dependencies [d4e853c]
• Updated dependencies [a94b8ec]
  • @llamaindex/env@0.1.6

0.4.2

Patch Changes

• a87a4d1: feat: added tool support calling for Bedrock's Calude and general llm support for agents
• 0730140: include node relationships when converting jsonToDoc
• Updated dependencies [f3b34b4]
  • @llamaindex/env@0.1.5

0.4.1

Patch Changes

• 3c47910: fix: groq llm
• ed467a9: Add model ids for Anthropic Claude 3.5 Sonnet model on Anthropic and Bedrock
• cba5406: fix: every Llama Parse job being called "blob"
• Updated dependencies [56fabbb]
  • @llamaindex/env@0.1.4

0.4.0

Minor Changes

• 436bc41: Unify chat engine response and agent response

Patch Changes

• a44e54f: Truncate text to embed for OpenAI if it exceeds maxTokens
• a51ed8d: feat: add support for managed identity for Azure OpenAI
• d3b635b: fix: agents to use chat history

0.3.17

Patch Changes

• 6bc5bdd: feat: add cache disabling, fast mode, do not unroll columns mode and custom page separator to LlamaParseReader
• bf25ff6: fix: polyfill for cloudflare worker
• e6d6576: chore: use unpdf

0.3.16

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

0.3.15

Patch Changes

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

0.3.14

Patch Changes

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

0.3.13

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

0.3.12

Patch Changes

• 34fb1d8: fix: cloudflare dev

0.3.11

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/env@0.1.3

0.3.10

Patch Changes

• 4aba02e: feat: support gpt4-o

0.3.9

Patch Changes

• c3747d0: fix: import @xenova/transformers

  For now, if you use llamaindex in next.js, you need to add a plugin from llamaindex/next to ensure some module resolutions are correct.

0.3.8

Patch Changes

• ce94780: Add page number to read PDFs and use generated IDs for PDF and markdown content

0.3.7

Patch Changes

• b6a6606: feat: allow change host of ollama
• b6a6606: chore: export ollama in default js runtime

0.3.6

Patch Changes

• efa326a: chore: update package.json
• Updated dependencies [efa326a]
• Updated dependencies [efa326a]
  • @llamaindex/env@0.1.2

0.3.5

Patch Changes

• bc7a11c: fix: inline ollama build
• 2fe2b81: fix: filter with multiple filters in ChromaDB
• 5596e31: feat: improve @llamaindex/env
• e74fe88: fix: change <-> to <=> in the SELECT query
• be5df5b: fix: anthropic agent on multiple chat
• Updated dependencies [5596e31]
  • @llamaindex/env@0.1.1

0.3.4

Patch Changes

• 1dce275: fix: export StorageContext on edge runtime
• d10533e: feat: add hugging face llm
• 2008efe: feat: add verbose mode to Agent
• 5e61934: fix: remove clone object in CallbackManager.dispatchEvent
• 9e74a43: feat: add top k to asQueryEngine
• ee719a1: fix: streaming for ReAct Agent

0.3.3

Patch Changes

• e8c41c5: fix: wrong gemini streaming chat response

0.3.2

Patch Changes

• 61103b6: fix: streaming for Agent.createTask API

0.3.1

Patch Changes

• 46227f2: fix: build error on next.js nodejs runtime

0.3.0

Minor Changes

• 5016f21: feat: improve next.js/cloudflare/vite support

Patch Changes

• Updated dependencies [5016f21]
  • @llamaindex/env@0.1.0

0.2.13

Patch Changes

• 6277105: fix: allow passing empty tools to llms

0.2.12

Patch Changes

• d8d952d: feat: add gemini llm and embedding

0.2.11

Patch Changes

• 87142b2: refactor: use ollama official sdk
• 5a6cc0e: feat: support jina ai embedding and reranker
• 87142b2: feat: support output to json format

0.2.10

Patch Changes

• cf70edb: Llama 3 support

0.2.9

Patch Changes

• 76c3fd6: Add score to source nodes response

• 208282d: feat: init anthropic agent

  remove the tool | function type in MessageType. Replace with assistant instead.
  This is because these two types are only available for OpenAI.
  Since OpenAI deprecates the function type, we support the Claude 3 tool call.

0.2.8

Patch Changes

• Add ToolsFactory to generate agent tools

0.2.7

Patch Changes

• 96f8f40: fix: agent stream
• Updated dependencies
  • @llamaindex/env@0.0.7

0.2.6

Patch Changes

• a3b4409: Fix agent streaming with new OpenAI models

0.2.5

Patch Changes

• 7d56cdf: Allow OpenAIAgent to be called without tools

0.2.4

Patch Changes

• 3bc77f7: gpt-4-turbo GA
• 8d2b21e: Mistral 0.1.3

0.2.3

Patch Changes

• f0704ec: Support streaming for OpenAI agent (and OpenAI tool calls)
• Removed 'parentEvent' - Use 'event.reason?.computedCallers' instead
• 3cbfa98: Added LlamaCloudIndex.fromDocuments

0.2.2

Patch Changes

• 3f8407c: Add pipeline.register to create a managed index in LlamaCloud
• 60a1603: fix: make edge run build after core
• fececd8: feat: add tool factory
• 1115f83: fix: throw error when no pipelines exist for the retriever
• 7a23cc6: feat: improve CallbackManager
• ea467fa: Update the list of supported Azure OpenAI API versions as of 2024-04-02.
• 6d9e015: feat: use claude3 with react agent
• 0b665bd: feat: add wikip...

Release refs/tags/llamaindex@0.5.1

llamaindex

0.5.1

Patch Changes

• 2774681: Add mixedbread's embeddings and reranking API
• a0f424e: corrected the regex in the react.ts file in extractToolUse & extractJsonStr functions, as mentioned in run-llama#1019

0.5.0

Minor Changes

• 16ef5dd: refactor: simplify callback manager

  Change event.detail.payload to event.detail

Patch Changes

• 16ef5dd: refactor: move callback manager & llm to core module

  For people who import llamaindex/llms/base or llamaindex/llms/utils,
  use @llamaindex/core/llms and @llamaindex/core/utils instead.

• 36ddec4: fix: typo in custom page separator parameter for LlamaParse

• Updated dependencies [16ef5dd]

• Updated dependencies [16ef5dd]

• Updated dependencies [36ddec4]

  • @llamaindex/core@0.1.0
  • @llamaindex/cloud@0.1.4

0.4.14

Patch Changes

• Updated dependencies [1c444d5]
  • @llamaindex/cloud@0.1.3

0.4.13

Patch Changes

• e8f8bea: feat: add boundingBox and targetPages to LlamaParseReader
• 304484b: feat: add ignoreErrors flag to LlamaParseReader

0.4.12

Patch Changes

• f326ab8: chore: bump version
• Updated dependencies [f326ab8]
  • @llamaindex/cloud@0.1.2
  • @llamaindex/core@0.0.3
  • @llamaindex/env@0.1.8

0.4.11

Patch Changes

• 8bf5b4a: fix: llama parse input spreadsheet

0.4.10

Patch Changes

• 7dce3d2: fix: disable External Filters for Gemini

0.4.9

Patch Changes

• 3a96a48: fix: anthroipic image input

0.4.8

Patch Changes

• 83ebdfb: fix: next.js build error

0.4.7

Patch Changes

• 41fe871: Add support for azure dynamic session tool
• 321c39d: fix: generate api as class
• f7f1af0: fix: throw error when no pipeline found
• Updated dependencies [41fe871]
• Updated dependencies [f10b41d]
• Updated dependencies [321c39d]
  • @llamaindex/env@0.1.7
  • @llamaindex/core@0.0.2
  • @llamaindex/cloud@0.1.1

0.4.6

Patch Changes

• 1feb23b: feat: Gemini tool calling for agent support
• 08c55ec: Add metadata to PDFs and use Uint8Array for readers content

0.4.5

Patch Changes

• 6c3e5d0: fix: switch to correct reference for a static function

0.4.4

Patch Changes

• 42eb73a: Fix IngestionPipeline not working without vectorStores

0.4.3

Patch Changes

• 2ef62a9: feat: added support for embeddings via HuggingFace Inference API
• Updated dependencies [d4e853c]
• Updated dependencies [a94b8ec]
  • @llamaindex/env@0.1.6

0.4.2

Patch Changes

• a87a4d1: feat: added tool support calling for Bedrock's Calude and general llm support for agents
• 0730140: include node relationships when converting jsonToDoc
• Updated dependencies [f3b34b4]
  • @llamaindex/env@0.1.5

0.4.1

Patch Changes

• 3c47910: fix: groq llm
• ed467a9: Add model ids for Anthropic Claude 3.5 Sonnet model on Anthropic and Bedrock
• cba5406: fix: every Llama Parse job being called "blob"
• Updated dependencies [56fabbb]
  • @llamaindex/env@0.1.4

0.4.0

Minor Changes

• 436bc41: Unify chat engine response and agent response

Patch Changes

• a44e54f: Truncate text to embed for OpenAI if it exceeds maxTokens
• a51ed8d: feat: add support for managed identity for Azure OpenAI
• d3b635b: fix: agents to use chat history

0.3.17

Patch Changes

• 6bc5bdd: feat: add cache disabling, fast mode, do not unroll columns mode and custom page separator to LlamaParseReader
• bf25ff6: fix: polyfill for cloudflare worker
• e6d6576: chore: use unpdf

0.3.16

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

0.3.15

Patch Changes

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

0.3.14

Patch Changes

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

0.3.13

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

0.3.12

Patch Changes

• 34fb1d8: fix: cloudflare dev

0.3.11

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/env@0.1.3

0.3.10

Patch Changes

• 4aba02e: feat: support gpt4-o

0.3.9

Patch Changes

• c3747d0: fix: import @xenova/transformers

  For now, if you use llamaindex in next.js, you need to add a plugin from llamaindex/next to ensure some module resolutions are correct.

0.3.8

Patch Changes

• ce94780: Add page number to read PDFs and use generated IDs for PDF and markdown content

0.3.7

Patch Changes

• b6a6606: feat: allow change host of ollama
• b6a6606: chore: export ollama in default js runtime

0.3.6

Patch Changes

• efa326a: chore: update package.json
• Updated dependencies [efa326a]
• Updated dependencies [efa326a]
  • @llamaindex/env@0.1.2

0.3.5

Patch Changes

• bc7a11c: fix: inline ollama build
• 2fe2b81: fix: filter with multiple filters in ChromaDB
• 5596e31: feat: improve @llamaindex/env
• e74fe88: fix: change <-> to <=> in the SELECT query
• be5df5b: fix: anthropic agent on multiple chat
• Updated dependencies [5596e31]
  • @llamaindex/env@0.1.1

0.3.4

Patch Changes

• 1dce275: fix: export StorageContext on edge runtime
• d10533e: feat: add hugging face llm
• 2008efe: feat: add verbose mode to Agent
• 5e61934: fix: remove clone object in CallbackManager.dispatchEvent
• 9e74a43: feat: add top k to asQueryEngine
• ee719a1: fix: streaming for ReAct Agent

0.3.3

Patch Changes

• e8c41c5: fix: wrong gemini streaming chat response

0.3.2

Patch Changes

• 61103b6: fix: streaming for Agent.createTask API

0.3.1

Patch Changes

• 46227f2: fix: build error on next.js nodejs runtime

0.3.0

Minor Changes

• 5016f21: feat: improve next.js/cloudflare/vite support

Patch Changes

• Updated dependencies [5016f21]
  • @llamaindex/env@0.1.0

0.2.13

Patch Changes

• 6277105: fix: allow passing empty tools to llms

0.2.12

Patch Changes

• d8d952d: feat: add gemini llm and embedding

0.2.11

Patch Changes

• 87142b2: refactor: use ollama official sdk
• 5a6cc0e: feat: support jina ai embedding and reranker
• 87142b2: feat: support output to json format

0.2.10

Patch Changes

• cf70edb: Llama 3 support

0.2.9

Patch Changes

• 76c3fd6: Add score to source nodes response

• 208282d: feat: init anthropic agent

  remove the tool | function type in MessageType. Replace with assistant instead.
  This is because these two types are only available for OpenAI.
  Since OpenAI deprecates the function type, we support the Claude 3 tool call.

0.2.8

Patch Changes

• Add ToolsFactory to generate agent tools

0.2.7

Patch Changes

• 96f8f40: fix: agent stream
• Updated dependencies
  • @llamaindex/env@0.0.7

0.2.6

Patch Changes

• a3b4409: Fix agent streaming with new OpenAI models

0.2.5

Patch Changes

• 7d56cdf: Allow OpenAIAgent to be called without tools

0.2.4

Patch Changes

• 3bc77f7: gpt-4-turbo GA
• 8d2b21e: Mistral 0.1.3

0.2.3

Patch Changes

• f0704ec: Support streaming for OpenAI agent (and OpenAI tool calls)
• Removed 'parentEvent' - Use 'event.reason?.computedCallers' instead
• 3cbfa98: Added LlamaCloudIndex.fromDocuments

0.2.2

Patch Changes

• 3f8407c: Add pipeline.register to create a managed index in LlamaCloud
• 60a1603: fix: make edge run build after core
• fececd8: feat: add tool factory
• 1115f83: fix: throw error when no pipelines exist for the retriever
• 7a23cc6: feat: improve CallbackManager
• ea467fa: Update the list of supported Azure OpenAI API versions as of 2024-04-02.
• 6d9e015: feat: use claude3 with react agent
• 0b665bd: feat: add wikipedia tool
• 24b4033: feat: add result type json
• 8b28092: Add support for doc store strategies to VectorStoreIndex.fromDocuments
• Updated dependencies [7a23cc6]
  • @llamaindex/env@0.0.6

0.2.1

Patch Changes

• 41210df: Add auto create milvus collection and add milvus node metadata
• 137cf67: Use Pinecone namespaces for all operations
• 259c842: Add support for edge runtime by using @llamaindex/edge

0.2.0

Minor Changes

• bf583a7: Use parameter object for retrieve function of Retriever (to align usage with query function of QueryEngine)

Patch Changes

• d2e8d0c: add support for Milvus vector store
• aefc326: feat: experimental package + json query engine
• 484a710: - Add missing exports:
  • IndexStructType,
  • IndexDict,
  • jsonToIndexStruct,
  • IndexList,
  • IndexStruct
  • Fix IndexDict.toJson() method
• d766bd0: Add streaming to agents
• dd95927: add Claude Haiku support and update anthropic SDK

0.1.21

...

Release refs/tags/llamaindex@0.4.13

llamaindex

0.4.13

Patch Changes

• e8f8bea: feat: add boundingBox and targetPages to LlamaParseReader
• 304484b: feat: add ignoreErrors flag to LlamaParseReader

0.4.12

Patch Changes

• f326ab8: chore: bump version
• Updated dependencies [f326ab8]
  • @llamaindex/cloud@0.1.2
  • @llamaindex/core@0.0.3
  • @llamaindex/env@0.1.8

0.4.11

Patch Changes

• 8bf5b4a: fix: llama parse input spreadsheet

0.4.10

Patch Changes

• 7dce3d2: fix: disable External Filters for Gemini

0.4.9

Patch Changes

• 3a96a48: fix: anthroipic image input

0.4.8

Patch Changes

• 83ebdfb: fix: next.js build error

0.4.7

Patch Changes

• 41fe871: Add support for azure dynamic session tool
• 321c39d: fix: generate api as class
• f7f1af0: fix: throw error when no pipeline found
• Updated dependencies [41fe871]
• Updated dependencies [f10b41d]
• Updated dependencies [321c39d]
  • @llamaindex/env@0.1.7
  • @llamaindex/core@0.0.2
  • @llamaindex/cloud@0.1.1

0.4.6

Patch Changes

• 1feb23b: feat: Gemini tool calling for agent support
• 08c55ec: Add metadata to PDFs and use Uint8Array for readers content

0.4.5

Patch Changes

• 6c3e5d0: fix: switch to correct reference for a static function

0.4.4

Patch Changes

• 42eb73a: Fix IngestionPipeline not working without vectorStores

0.4.3

Patch Changes

• 2ef62a9: feat: added support for embeddings via HuggingFace Inference API
• Updated dependencies [d4e853c]
• Updated dependencies [a94b8ec]
  • @llamaindex/env@0.1.6

0.4.2

Patch Changes

• a87a4d1: feat: added tool support calling for Bedrock's Calude and general llm support for agents
• 0730140: include node relationships when converting jsonToDoc
• Updated dependencies [f3b34b4]
  • @llamaindex/env@0.1.5

0.4.1

Patch Changes

• 3c47910: fix: groq llm
• ed467a9: Add model ids for Anthropic Claude 3.5 Sonnet model on Anthropic and Bedrock
• cba5406: fix: every Llama Parse job being called "blob"
• Updated dependencies [56fabbb]
  • @llamaindex/env@0.1.4

0.4.0

Minor Changes

• 436bc41: Unify chat engine response and agent response

Patch Changes

• a44e54f: Truncate text to embed for OpenAI if it exceeds maxTokens
• a51ed8d: feat: add support for managed identity for Azure OpenAI
• d3b635b: fix: agents to use chat history

0.3.17

Patch Changes

• 6bc5bdd: feat: add cache disabling, fast mode, do not unroll columns mode and custom page seperator to LlamaParseReader
• bf25ff6: fix: polyfill for cloudflare worker
• e6d6576: chore: use unpdf

0.3.16

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

0.3.15

Patch Changes

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

0.3.14

Patch Changes

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

0.3.13

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

0.3.12

Patch Changes

• 34fb1d8: fix: cloudflare dev

0.3.11

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/env@0.1.3

0.3.10

Patch Changes

• 4aba02e: feat: support gpt4-o

0.3.9

Patch Changes

• c3747d0: fix: import @xenova/transformers

  For now, if you use llamaindex in next.js, you need to add a plugin from llamaindex/next to ensure some module resolutions are correct.

0.3.8

Patch Changes

• ce94780: Add page number to read PDFs and use generated IDs for PDF and markdown content

0.3.7

Patch Changes

• b6a6606: feat: allow change host of ollama
• b6a6606: chore: export ollama in default js runtime

0.3.6

Patch Changes

• efa326a: chore: update package.json
• Updated dependencies [efa326a]
• Updated dependencies [efa326a]
  • @llamaindex/env@0.1.2

0.3.5

Patch Changes

• bc7a11c: fix: inline ollama build
• 2fe2b81: fix: filter with multiple filters in ChromaDB
• 5596e31: feat: improve @llamaindex/env
• e74fe88: fix: change <-> to <=> in the SELECT query
• be5df5b: fix: anthropic agent on multiple chat
• Updated dependencies [5596e31]
  • @llamaindex/env@0.1.1

0.3.4

Patch Changes

• 1dce275: fix: export StorageContext on edge runtime
• d10533e: feat: add hugging face llm
• 2008efe: feat: add verbose mode to Agent
• 5e61934: fix: remove clone object in CallbackManager.dispatchEvent
• 9e74a43: feat: add top k to asQueryEngine
• ee719a1: fix: streaming for ReAct Agent

0.3.3

Patch Changes

• e8c41c5: fix: wrong gemini streaming chat response

0.3.2

Patch Changes

• 61103b6: fix: streaming for Agent.createTask API

0.3.1

Patch Changes

• 46227f2: fix: build error on next.js nodejs runtime

0.3.0

Minor Changes

• 5016f21: feat: improve next.js/cloudflare/vite support

Patch Changes

• Updated dependencies [5016f21]
  • @llamaindex/env@0.1.0

0.2.13

Patch Changes

• 6277105: fix: allow passing empty tools to llms

0.2.12

Patch Changes

• d8d952d: feat: add gemini llm and embedding

0.2.11

Patch Changes

• 87142b2: refactor: use ollama official sdk
• 5a6cc0e: feat: support jina ai embedding and reranker
• 87142b2: feat: support output to json format

0.2.10

Patch Changes

• cf70edb: Llama 3 support

0.2.9

Patch Changes

• 76c3fd6: Add score to source nodes response

• 208282d: feat: init anthropic agent

  remove the tool | function type in MessageType. Replace with assistant instead.
  This is because these two types are only available for OpenAI.
  Since OpenAI deprecates the function type, we support the Claude 3 tool call.

0.2.8

Patch Changes

• Add ToolsFactory to generate agent tools

0.2.7

Patch Changes

• 96f8f40: fix: agent stream
• Updated dependencies
  • @llamaindex/env@0.0.7

0.2.6

Patch Changes

• a3b4409: Fix agent streaming with new OpenAI models

0.2.5

Patch Changes

• 7d56cdf: Allow OpenAIAgent to be called without tools

0.2.4

Patch Changes

• 3bc77f7: gpt-4-turbo GA
• 8d2b21e: Mistral 0.1.3

0.2.3

Patch Changes

• f0704ec: Support streaming for OpenAI agent (and OpenAI tool calls)
• Removed 'parentEvent' - Use 'event.reason?.computedCallers' instead
• 3cbfa98: Added LlamaCloudIndex.fromDocuments

0.2.2

Patch Changes

• 3f8407c: Add pipeline.register to create a managed index in LlamaCloud
• 60a1603: fix: make edge run build after core
• fececd8: feat: add tool factory
• 1115f83: fix: throw error when no pipelines exist for the retriever
• 7a23cc6: feat: improve CallbackManager
• ea467fa: Update the list of supported Azure OpenAI API versions as of 2024-04-02.
• 6d9e015: feat: use claude3 with react agent
• 0b665bd: feat: add wikipedia tool
• 24b4033: feat: add result type json
• 8b28092: Add support for doc store strategies to VectorStoreIndex.fromDocuments
• Updated dependencies [7a23cc6]
  • @llamaindex/env@0.0.6

0.2.1

Patch Changes

• 41210df: Add auto create milvus collection and add milvus node metadata
• 137cf67: Use Pinecone namespaces for all operations
• 259c842: Add support for edge runtime by using @llamaindex/edge

0.2.0

Minor Changes

• bf583a7: Use parameter object for retrieve function of Retriever (to align usage with query function of QueryEngine)

Patch Changes

• d2e8d0c: add support for Milvus vector store
• aefc326: feat: experimental package + json query engine
• 484a710: - Add missing exports:
  • IndexStructType,
  • IndexDict,
  • jsonToIndexStruct,
  • IndexList,
  • IndexStruct
  • Fix IndexDict.toJson() method
• d766bd0: Add streaming to agents
• dd95927: add Claude Haiku support and update anthropic SDK

0.1.21

Patch Changes

• 552a61a: Add quantized parameter to HuggingFaceEmbedding
• d824876: Add support for Claude 3

0.1.20

Patch Changes

• 64683a5: fix: prefix messages always true
• 698cd9c: fix: step wise agent + examples
• 7257751: fixed removeRefDocNode and persist store on delete
• 5116ad8: fix: compatibility issue with Deno
• Updated dependencies [5116ad8]
  • @llamaindex/env@0.0.5

0.1.19

Patch Changes

• 026d068: feat: enhance pinecone usage

0.1.18

Patch Changes

• 90027a7: Add splitLongSentences option to SimpleNodeParser
• c57bd11: feat: update and refactor title extractor

0.1.17

Patch Changes

• c8396c5: feat: add base evaluator and correctness evaluator
• c8396c5: feat: add base evaluator and correctness evaluator
• cf87f84: fix: type backward compatibility
• 09bf27a: Add Groq LLM to LlamaIndex
• Updated dependencies [cf87f84]
  • @llamaindex/env@0.0.4

0.1.16

Patch ...