Update npm package llamaindex to v0.6.22
#5154
Open
+907
−449
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
![hash-worker[bot]](https://avatars.githubusercontent.com/in/991899?s=60&v=4){kind=small}
hashdotai
previously approved these changes
Sep 15, 2024
github-actions
bot
added
area/deps
hash-worker
bot
force-pushed
the
deps/js/llamaindex-0.x
branch
from
4d02ddc
to
bf347d7
Compare
hash-worker
bot
changed the title
llamaindex to v0.5.25llamaindex to v0.5.26
hashdotai
previously approved these changes
Sep 15, 2024
hash-worker
bot
force-pushed
the
deps/js/llamaindex-0.x
branch
from
bf347d7
to
ef2d2b9
Compare
hash-worker
bot
changed the title
llamaindex to v0.5.26llamaindex to v0.5.27
hashdotai
previously approved these changes
Sep 15, 2024
hash-worker
bot
force-pushed
the
deps/js/llamaindex-0.x
branch
from
ef2d2b9
to
e9add9e
Compare
hash-worker
bot
changed the title
llamaindex to v0.5.27llamaindex to v0.6.0
hashdotai
previously approved these changes
Sep 16, 2024
hash-worker
bot
force-pushed
the
deps/js/llamaindex-0.x
branch
from
0845fcd
to
0715d8c
Compare
hash-worker
bot
changed the title
llamaindex to v0.6.18llamaindex to v0.6.19
hashdotai
previously approved these changes
Oct 13, 2024
hash-worker
bot
force-pushed
the
deps/js/llamaindex-0.x
branch
from
0715d8c
to
b162e49
Compare
hash-worker
bot
changed the title
llamaindex to v0.6.19llamaindex to v0.6.20
hashdotai
previously approved these changes
Oct 14, 2024
hash-worker
bot
force-pushed
the
deps/js/llamaindex-0.x
branch
from
b162e49
to
9995757
Compare
hash-worker
bot
changed the title
llamaindex to v0.6.20llamaindex to v0.6.22
hashdotai
previously approved these changes
Oct 19, 2024
hash-worker
bot
force-pushed
the
deps/js/llamaindex-0.x
branch
from
9995757
to
e2fc330
Compare
hashdotai
approved these changes
Oct 19, 2024
Benchmark results
|
| Function | Value | Mean | Flame graphs |
|---|---|---|---|
| get_entity_type_by_id | Account ID: d4e16033-c281-4cde-aa35-9085bf2e7579
|
Flame Graph |
scaling_read_entity_complete_zero_depth
| Function | Value | Mean | Flame graphs |
|---|---|---|---|
| entity_by_id | 10 entities | Flame Graph | |
| entity_by_id | 50 entities | Flame Graph | |
| entity_by_id | 1 entities | Flame Graph | |
| entity_by_id | 5 entities | Flame Graph | |
| entity_by_id | 25 entities | Flame Graph |
scaling_read_entity_linkless
| Function | Value | Mean | Flame graphs |
|---|---|---|---|
| entity_by_id | 10 entities | Flame Graph | |
| entity_by_id | 1000 entities | Flame Graph | |
| entity_by_id | 1 entities | Flame Graph | |
| entity_by_id | 10000 entities | Flame Graph | |
| entity_by_id | 100 entities | Flame Graph |
representative_read_multiple_entities
| Function | Value | Mean | Flame graphs |
|---|---|---|---|
| entity_by_property | depths: DT=255, PT=255, ET=255, E=255 | Flame Graph | |
| entity_by_property | depths: DT=0, PT=2, ET=2, E=2 | Flame Graph | |
| entity_by_property | depths: DT=0, PT=0, ET=0, E=0 | Flame Graph | |
| entity_by_property | depths: DT=0, PT=0, ET=2, E=2 | Flame Graph | |
| entity_by_property | depths: DT=0, PT=0, ET=0, E=2 | Flame Graph | |
| entity_by_property | depths: DT=2, PT=2, ET=2, E=2 | Flame Graph | |
| link_by_source_by_property | depths: DT=255, PT=255, ET=255, E=255 | Flame Graph | |
| link_by_source_by_property | depths: DT=0, PT=2, ET=2, E=2 | Flame Graph | |
| link_by_source_by_property | depths: DT=0, PT=0, ET=0, E=0 | Flame Graph | |
| link_by_source_by_property | depths: DT=0, PT=0, ET=2, E=2 | Flame Graph | |
| link_by_source_by_property | depths: DT=0, PT=0, ET=0, E=2 | Flame Graph | |
| link_by_source_by_property | depths: DT=2, PT=2, ET=2, E=2 | Flame Graph |
scaling_read_entity_complete_one_depth
| Function | Value | Mean | Flame graphs |
|---|---|---|---|
| entity_by_id | 10 entities | Flame Graph | |
| entity_by_id | 50 entities | Flame Graph | |
| entity_by_id | 1 entities | Flame Graph | |
| entity_by_id | 5 entities | Flame Graph | |
| entity_by_id | 25 entities | Flame Graph |
representative_read_entity
| Function | Value | Mean | Flame graphs |
|---|---|---|---|
| entity_by_id | entity type ID: https://blockprotocol.org/@alice/types/entity-type/uk-address/v/1
|
Flame Graph | |
| entity_by_id | entity type ID: https://blockprotocol.org/@alice/types/entity-type/page/v/2
|
Flame Graph | |
| entity_by_id | entity type ID: https://blockprotocol.org/@alice/types/entity-type/organization/v/1
|
Flame Graph | |
| entity_by_id | entity type ID: https://blockprotocol.org/@alice/types/entity-type/building/v/1
|
Flame Graph | |
| entity_by_id | entity type ID: https://blockprotocol.org/@alice/types/entity-type/person/v/1
|
Flame Graph | |
| entity_by_id | entity type ID: https://blockprotocol.org/@alice/types/entity-type/song/v/1
|
Flame Graph | |
| entity_by_id | entity type ID: https://blockprotocol.org/@alice/types/entity-type/block/v/1
|
Flame Graph | |
| entity_by_id | entity type ID: https://blockprotocol.org/@alice/types/entity-type/book/v/1
|
Flame Graph | |
| entity_by_id | entity type ID: https://blockprotocol.org/@alice/types/entity-type/playlist/v/1
|
Flame Graph |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR contains the following updates:
0.2.10->0.6.220.7.0Release Notes
run-llama/LlamaIndexTS (llamaindex)
v0.6.22Compare Source
Patch Changes
5729bd9: Fix LlamaCloud API calls for ensuring an index and for file uploadsv0.6.21Compare Source
Patch Changes
6f75306: feat: support metadata filters for AstraDB94cb4ad: feat: Add metadata filters to ChromaDb and update to 1.9.2v0.6.20Compare Source
Patch Changes
6a9a7b1: fix: take init api key into account6a9a7b1]v0.6.19Compare Source
Patch Changes
62cba52: Add ensureIndex function to LlamaCloudIndexd265e96: fix: ignore resolving unpdf for nextjsd30bbf7: Convert undefined values to null in LlamaCloud filters53fd00a: Fix getPipelineId in LlamaCloudIndexv0.6.18Compare Source
Patch Changes
5f67820: Fix that node parsers generate nodes with UUIDsfe08d04: Fix LlamaCloud retrieval with multiple pipelines5f67820]v0.6.17Compare Source
Patch Changes
ee697fb: fix: generate uuid when inserting to Qdrantee697fb]v0.6.16Compare Source
Patch Changes
63e9846: fix: preFilters does not work with asQueryEngine6f3a31c: feat: add metadata filters for Qdrant vector store3489e7d]468bda5]v0.6.15Compare Source
Patch Changes
2a82413: fix(core): setSettings.llmto OpenAI by default and support lazy load openai2a82413]0b20ff9]v0.6.14Compare Source
Patch Changes
b17d439]v0.6.13Compare Source
Patch Changes
981811e]v0.6.12Compare Source
Patch Changes
f7b4e94: feat: add filters for pinecone78037a6: fix: bypass service context embed model1d9e3b1: fix: export llama reader in non-nodejs runtimev0.6.11Compare Source
Patch Changes
df441e2: fix: consoleLogger is missing from@llamaindex/envdf441e2]v0.6.10Compare Source
Patch Changes
ebc5105: feat: support@vercel/postgres6cce3b1: feat: supportnpm:postgres96f72ad]6cce3b1]v0.6.9Compare Source
Patch Changes
ac41ed3]v0.6.8Compare Source
Patch Changes
8b7fdba: refactor: move chat engine & retriever into core.chatHistoryin BaseChatEngine now returnsChatMessage[] | Promise<ChatMessage[]>, instead ofBaseMemoryretrieve-endtypeUpdated dependencies [
8b7fdba]v0.6.7Compare Source
Patch Changes
23bcc37: fix: addserializerin doc storePostgresDocumentStorenow will not use JSON.stringify for better performancev0.6.6Compare Source
Patch Changes
d902cc3: Fix context not being sent using ContextChatEngine025ffe6: fix: updatePostgresKVStoreconstructor paramsa659574: Adds upstash vector store as a storaged902cc3]v0.6.5Compare Source
Patch Changes
e9714db: feat: updatePGVectorStoreconfig.user|config.database|config.password|config.connectionStringintoconfig.clientConfigpg.Clientorpg.Poolinstance toPGVectorStore, move it toconfig.client, settingconfig.shouldConnectto false if it's already connectedPGVectorStore.collectionis now"data"instead of""(empty string)v0.6.4Compare Source
Patch Changes
b48bcc3: feat: addload-transformersevent type when loading@xenova/transformersmoduleThis would benefit user who want to customize the transformer env.
Updated dependencies [
b48bcc3]v0.6.3Compare Source
Patch Changes
2cd1383: refactor: alignresponse-synthesizers&chat-enginemodule@llamaindex/experimental, as the code quality is not satisify and we will bring it back later5c4badb: Extend JinaAPIEmbedding parametersUpdated dependencies [
fb36eff]Updated dependencies [
d24d3d1]Updated dependencies [
2cd1383]v0.6.2Compare Source
Patch Changes
5729bd9: Fix LlamaCloud API calls for ensuring an index and for file uploadsv0.6.1Compare Source
Patch Changes
62cba52: Add ensureIndex function to LlamaCloudIndexd265e96: fix: ignore resolving unpdf for nextjsd30bbf7: Convert undefined values to null in LlamaCloud filters53fd00a: Fix getPipelineId in LlamaCloudIndexv0.6.0Compare Source
Minor Changes
11feef8: Add workflowsPatch Changes
11feef8]v0.5.27Compare Source
Patch Changes
7edeb1c: feat: decouple openai fromllamaindexmoduleThis should be a non-breaking change, but just you can now only install
@llamaindex/openaito reduce the bundle size in the futureUpdated dependencies [
7edeb1c]v0.5.26Compare Source
Patch Changes
ffe0cd1: faet: add openai o1 supportffe0cd1: feat: add PostgreSQL storagev0.5.25Compare Source
Patch Changes
4810364: fix: handleRouterQueryEnginewith string queryd3bc663: refactor: export vector store only in nodejs environment on top levelIf you see some missing modules error, please change vector store related imports to
llamaindex/vector-storeUpdated dependencies [
4810364]v0.5.24Compare Source
Patch Changes
0bf8d80]v0.5.23Compare Source
Patch Changes
711c814]v0.5.22Compare Source
Patch Changes
4648da6: fix: wrong tiktoken version caused NextJs CL template run fail4648da6]v0.5.21Compare Source
Patch Changes
ae1149f: feat: add JSON streaming to JSONReader2411c9f: Auto-create index for MongoDB vector store (if not exists)e8f229c: Remove logging from MongoDB Atlas Vector Store11b3856: implement filters for MongoDBAtlasVectorSearch83d7f41: Fix database insertion forPGVectorStoreIt will now:
INSERTcall (inside a transaction).0148354: refactor: prompt systemAdd
PromptTemplatemodule with strong type check.1711f6d: Export imageToDataUrl for using images in chatUpdated dependencies [
0148354]v0.5.20Compare Source
Patch Changes
d9d6c56: Add support for MetadataFilters for PostgreSQL22ff486: Add tiktoken WASM to withLlamaIndexeed0b04: fix: use LLM metadata mode for generating context of ContextChatEnginev0.5.19Compare Source
Patch Changes
fcbf183: implement llamacloud file servicev0.5.18Compare Source
Patch Changes
8b66cf4: feat: support organization id in llamacloud indexe27e7dd]v0.5.17Compare Source
Patch Changes
c654398: Implement Weaviate Vector Store in TSv0.5.16Compare Source
Patch Changes
58abc57: fix: align version58abc57]v0.5.15Compare Source
Patch Changes
01c184c: Add is_empty operator for filtering vector store07a275f: chore: bump openaiv0.5.14Compare Source
Patch Changes
c825a2f: Add gpt-4o-mini to Azure. Add 2024-06-01 API version for Azurev0.5.13Compare Source
Patch Changes
04b2f8e]v0.5.12Compare Source
Patch Changes
345300f: feat: add splitByPage mode to LlamaParseReaderda5cfc4: Add metadatafilter options to retriever constructorsda5cfc4: Fix system prompt not used in ContextChatEngine0452af9]v0.5.11Compare Source
Patch Changes
1f680d7]v0.5.10Compare Source
Patch Changes
086b940: feat: add DeepSeek LLM5d5716b: feat: add a reader for JSON data91d02a4: feat: support transform component callablefb6db45: feat: add pageSeparator params to LlamaParseReader91d02a4]v0.5.9Compare Source
Patch Changes
15962b3: feat: node parser refactorAlign 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]v0.5.8Compare Source
Patch Changes
3d5ba08: fix: update user agent in AssemblyAId917cdc: Add azure interpreter tool to tool factoryv0.5.7Compare Source
Patch Changes
ec59acd: fix: bundling issue with pnpmv0.5.6Compare Source
Patch Changes
2562244: feat: add gpt4o-mini325aa51: Implement Jina embedding through Jina apiab700ea: Add missing authentication to LlamaCloudIndex.fromDocuments92f0782: feat: use query bundle6cf6ae6: feat: abstract query typeb7cfe5b: fix: passing max_token option to replicate's api call6cf6ae6]v0.5.5Compare Source
Patch Changes
b974eea: Add support for Metadata filtersb974eea]v0.5.4Compare Source
Patch Changes
1a65ead: feat: add vendorMultimodal params to LlamaParseReaderv0.5.3Compare Source
Patch Changes
9bbbc67: feat: add a reader for Discord messagesb3681bf: fix: DataCloneError when using FunctionToolb3681bf]v0.5.2Compare Source
Patch Changes
7edeb1c: feat: decouple openai fromllamaindexmoduleThis should be a non-breaking change, but just you can now only install
@llamaindex/openaito reduce the bundle size in the futureUpdated dependencies [
7edeb1c]v0.5.1Compare Source
Patch Changes
fcbf183: implement llamacloud file servicev0.5.0Compare Source
Minor Changes
16ef5dd: refactor: simplify callback managerChange
event.detail.payloadtoevent.detailPatch Changes
16ef5dd: refactor: move callback manager & llm to core moduleFor people who import
llamaindex/llms/baseorllamaindex/llms/utils,use
@llamaindex/core/llmsand@llamaindex/core/utilsinstead.36ddec4: fix: typo in custom page separator parameter for LlamaParseUpdated dependencies [
16ef5dd]Updated dependencies [
16ef5dd]Updated dependencies [
36ddec4]v0.4.14Compare Source
Patch Changes
1c444d5]v0.4.13Compare Source
Patch Changes
e8f8bea: feat: add boundingBox and targetPages to LlamaParseReader304484b: feat: add ignoreErrors flag to LlamaParseReaderv0.4.12Compare Source
Patch Changes
f326ab8: chore: bump versionf326ab8]v0.4.11Compare Source
Patch Changes
8bf5b4a: fix: llama parse input spreadsheetv0.4.10Compare Source
Patch Changes
7dce3d2: fix: disable External Filters for Geminiv0.4.9Compare Source
Patch Changes
3a96a48: fix: anthroipic image inputv0.4.8Compare Source
Patch Changes
83ebdfb: fix: next.js build errorv0.4.6Compare Source
Patch Changes
1feb23b: feat: Gemini tool calling for agent support08c55ec: Add metadata to PDFs and use Uint8Array for readers contentv0.4.5Compare Source
Patch Changes
6c3e5d0: fix: switch to correct reference for a static functionv0.4.4Compare Source
Patch Changes
42eb73a: Fix IngestionPipeline not working without vectorStoresv0.4.3Compare Source
Patch Changes
2ef62a9: feat: added support for embeddings via HuggingFace Inference APId4e853c]a94b8ec]v0.4.1Compare Source
Patch Changes
1c444d5]v0.4.0Compare Source
Minor Changes
436bc41: Unify chat engine response and agent responsePatch Changes
a44e54f: Truncate text to embed for OpenAI if it exceeds maxTokensa51ed8d: feat: add support for managed identity for Azure OpenAId3b635b: fix: agents to use chat historyv0.3.17Compare Source
Patch Changes
6bc5bdd: feat: add cache disabling, fast mode, do not unroll columns mode and custom page separator to LlamaParseReaderbf25ff6: fix: polyfill for cloudflare workere6d6576: chore: useunpdfv0.3.16Compare Source
Patch Changes
11ae926: feat: add numCandidates setting to MongoDBAtlasVectorStore for tuning queries631f000: feat: DeepInfra LLM implementation1378ec4: feat: set default model togpt-4o6b1ded4: add gpt4o-mode, invalidate cache and skip diagonal text to LlamaParseReader4d4bd85: Show error message if agent tool is called with partial JSON24a9d1e: add json mode and image retrieval to LlamaParseReader45952de: add concurrency management for SimpleDirectoryReader54230f0: feat: Gemini GA release modelsa29d835: setDocumentHash should be async73819bf: Unify metadata and ID handling of documents, allow files to be read byBufferv0.3.15Compare Source
Patch Changes
6e156ed: Use images in context chat engine265976d: fix bug with node decorator8e26f75: Add retrieval for images using multi-modal messagesv0.3.14Compare Source
Patch Changes
6ff7576: Added GPT-4o for Azure94543de: Added the latest preview gemini models and multi modal images taken into accountv0.3.13Compare Source
Patch Changes
1b1081b: Add vectorStores to storage context to define vector store per modality37525df: Added support for accessing Gemini via Vertex AI660a2b3: Fix text before heading in markdown readera1f2475: Add system prompt to ContextChatEnginev0.3.12Compare Source
Patch Changes
34fb1d8: fix: cloudflare devv0.3.11Compare Source
Patch Changes
e072c45: fix: remove non-standard APIpipeline9e133ac: refactor: removedefaultFSfrom parametersWe 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 preparation320be3f: Force ChromaDB version to 1.7.3 (to prevent NextJS issues)Updated dependencies [
e072c45]Updated dependencies [
9e133ac]v0.3.10Compare Source
Patch Changes
4aba02e: feat: support gpt4-ov0.3.9Compare Source
Patch Changes
c3747d0: fix: import@xenova/transformersFor now, if you use llamaindex in next.js, you need to add a plugin from
llamaindex/nextto ensure some module resolutions are correct.v0.3.8Compare Source
Patch Changes
ce94780: Add page number to read PDFs and use generated IDs for PDF and markdown contentv0.3.7Compare Source
Patch Changes
b6a6606: feat: allow change host of ollamab6a6606: chore: export ollama in default js runtimev0.3.6Compare Source
Patch Changes
efa326a: chore: update package.jsonefa326a]efa326a]v0.3.5Compare Source
Patch Changes
bc7a11c: fix: inline ollama build2fe2b81: fix: filter with multiple filters in ChromaDB5596e31: feat: improve@llamaindex/enve74fe88: fix: change <-> to <=> in the SELECT querybe5df5b: fix: anthropic agent on multiple chat5596e31]v0.3.4Compare Source
Patch Changes
1dce275: fix: exportStorageContexton edge runtimed10533e: feat: add hugging face llm2008efe: feat: add verbose mode to Agent5e61934: fix: remove clone object inCallbackManager.dispatchEvent9e74a43: feat: add top k toasQueryEngineee719a1: fix: streaming for ReAct Agentv0.3.3Compare Source
Patch Changes
e8c41c5: fix: wrong gemini streaming chat responsev0.3.2Compare Source
Patch Changes
61103b6: fix: streaming forAgent.createTaskAPIv0.3.1Compare Source
Patch Changes
6bc5bdd: feat: add cache disabling, fast mode, do not unroll columns mode and custom page separator to LlamaParseReaderbf25ff6: fix: polyfill for cloudflare workere6d6576: chore: useunpdfv0.3.0Compare Source
Minor Changes
5016f21: feat: improve next.js/cloudflare/vite supportPatch Changes
5016f21]Configuration
📅 Schedule: Branch creation - "before 4am every weekday,every weekend" (UTC), Automerge - At any time (no schedule defined).
🚦 Automerge: Enabled.
♻ Rebasing: Whenever PR becomes conflicted, or you tick the rebase/retry checkbox.
🔕 Ignore: Close this PR and you won't be reminded about this update again.
This PR has been generated by Renovate Bot.