Update for GPT4o #10

keligggg · 2024-05-16T12:18:52Z

Description

Please include a summary of the change and which issue is fixed. Please also include relevant motivation and context. List any dependencies that are required for this change.

Fixes # (issue)

New Package?

Did I fill in the tool.llamahub section in the pyproject.toml and provide a detailed README.md for my new integration or package?

Yes
No

Version Bump?

Did I bump the version in the pyproject.toml file of the package I am updating? (Except for the llama-index-core package)

Yes
No

Type of Change

Please delete options that are not relevant.

Bug fix (non-breaking change which fixes an issue)
New feature (non-breaking change which adds functionality)
Breaking change (fix or feature that would cause existing functionality to not work as expected)
This change requires a documentation update

How Has This Been Tested?

Please describe the tests that you ran to verify your changes. Provide instructions so we can reproduce. Please also list any relevant details for your test configuration

Added new unit/integration tests
Added new notebook (that tests end-to-end)
I stared at the code and made sure it makes sense

Suggested Checklist:

I have performed a self-review of my own code
I have commented my code, particularly in hard-to-understand areas
I have made corresponding changes to the documentation
I have added Google Colab support for the newly added notebooks.
My changes generate no new warnings
I have added tests that prove my fix is effective or that my feature works
New and existing unit tests pass locally with my changes
I ran make format; make lint to appease the lint gods

…lama#12967) * fix sparse query pinecone * none checking

* lats agent worker package * pants * add README * rm lock file * update example nb

* Adding claude 3 opus to BedRock integration * Increment version

…ss in OpenAIPydanticProgram (run-llama#13021) * added function to parse partial JSON * Added stream_partial_objects method in OpenAIPydanticProgram to stream intermediate objects as soon as they're available * updated documentation to add a section on how to stream intermediate objects using OpenAIPydanticProgram * version bump for llama-index-program-openai package * Importing ValidationError from llama_index.core.bridge.pydantic instead * Moved attribution inside docstring * Raising ValueError instead of returning None for malformted partial JSON string * Added unit tests for parse_partial_json function * removed commented code

* Add phi-3 benchmarks * Update with prompt template

…#13060)

…llama#12920)

* fix: qdrant sparse vector backwards compatibility * bump version

cr

Fix nonetype not iterable

Was missed in previous PR.

…ama#13448) * fix: Corrected connection parameters in connections.connect() * bump the version for bug fix

* cr * cr

…-llama#13231)

…file_ids` (run-llama#13341)

run-llama#13439)

)

…ain evaluation schema and dashboard (run-llama#13479)

…ostgres or lantern vector-store integration run-llama#9522 (run-llama#13476)

…lama#13454)

…run-llama#13442)

…m` (run-llama#13467)

* add nb for gpt4o mm program * rm image documents from construction * actually rm image documents from construction

Fix nonyielding stream chat bug Co-authored-by: Logan Markewich <logan.markewich@live.com>

* fix annoying grammar errors * add colab badge

* Update kuzu version for new storage layer * bump version --------- Co-authored-by: Andrei Fajardo <92402603+nerdai@users.noreply.github.com>

…llm` with Intel GPU supports (run-llama#13511)

logan-markewich and others added 30 commits April 22, 2024 09:27

import nit for vllm (run-llama#13027)

018dd87

fix qdrant bug with checking existing collection (run-llama#13009)

236fae0

Fix error querying PineconeVectorStore using sparse query mode (run-l…

521178f

…lama#12967) * fix sparse query pinecone * none checking

Fix: fix query pipeline's arun_with_intermediates (run-llama#13002)

f1cefcb

vbump openai (run-llama#13026)

8b966cc

LATs AgentWorker integration (run-llama#13031)

10c0cd5

* lats agent worker package * pants * add README * rm lock file * update example nb

use collection exists function for qdrant (run-llama#13032)

6947ef6

Fix class in fusion_retriever notebook (run-llama#13034)

1af2ba7

another qdrant fix (run-llama#13036)

6a8a81e

Integrating AWS DocumentDB as a vector storage method (run-llama#12217)

3232a1f

missing async call in qdrant (run-llama#13039)

c0f8321

Adding claude 3 opus to BedRock integration (run-llama#13033)

b767f27

* Adding claude 3 opus to BedRock integration * Increment version

Add phi-3 benchmarks (run-llama#13057)

bc07863

* Add phi-3 benchmarks * Update with prompt template

Add LLMCompiler Agent Integration (run-llama#13044)

efbbdb1

Add COA Agent integration (run-llama#13043)

55f3870

Use voyage-law-2 model in VoyageAI emaple code (run-llama#13029)

1d84e71

Improving Docs for NVIDIA TensorRT and Triton integrations (run-llama…

84b73a6

…#13060)

update docs to fix build (run-llama#13062)

11819dd

docs home page edits (run-llama#13012)

1e93027

Support custom credentials in FirestoreKVStore (run-llama#13018)

60c227d

(Astra DB integrations) Bump astrapy requirement to at-least-v1 (run-…

cb4a95a

…llama#12920)

(Astra db) explicit projection in DB read operations (run-llama#12872)

5c6bd6f

Tools docs update (run-llama#13059)

7693ad2

Enabng more OctoAI models - updated model list (run-llama#13065)

631cb60

fix: qdrant sparse vector backwards compatibility (run-llama#13068)

cf38483

* fix: qdrant sparse vector backwards compatibility * bump version

[FEATURE] Support both Predibase SDK-v1 and SDK-v2 (run-llama#13066)

cee23c9

v0.10.31 (run-llama#13064)

f1ff1eb

LATS nits on llamahub (run-llama#13076)

63a0d4f

cr

Qdrant nonetype fix (run-llama#13088)

cf4d1e7

Fix nonetype not iterable

amindadgar and others added 29 commits May 12, 2024 13:36

update: bump version! (run-llama#13445)

4978499

Was missed in previous PR.

fix: Corrected connection parameters in connections.connect() (run-ll…

6cc46e9

…ama#13448) * fix: Corrected connection parameters in connections.connect() * bump the version for bug fix

edit llama3 notebooks (run-llama#13456)

142552e

* cr * cr

Created an integration to use llms built for Apple's MLX library (run…

b82fe84

…-llama#13231)

Add New Integration for DeepInfra Embedding Model (run-llama#13323)

6e2ac5a

fix: update OpenAIAssistantAgent to use attachments rather than `…

b7180c5

…file_ids` (run-llama#13341)

Fix the RAG fusion pipeline (run-llama#13413)

17edf71

gpt-4o support (run-llama#13463)

2e4b0de

bump rerank versions (run-llama#13465)

133cc30

VectorStore -> BasePydanticVectorStore, also get/delete_nodes, clear() (

b9f8085

run-llama#13439)

Add support for prompt kwarg (run-llama#13405)

caaf43f

Fix RuntimeError by switching to asyncio from threading (run-llama#13486

6ba0404

)

integrations: Update UpTrain Callback Handler to support the new UpTr…

999de64

…ain evaluation schema and dashboard (run-llama#13479)

Update README.md (run-llama#13482)

ab474f7

Fix run-llama#9522 - SQLAlchemy warning when using hybrid search on p…

4adf1f3

…ostgres or lantern vector-store integration run-llama#9522 (run-llama#13476)

Trafilatura kwargs and progress bar for trafilatura web reader (run-l…

7e9d1c6

…lama#13454)

Remove "Truncate" parameter from Bedrock Cohere invoke model request. (…

7abc643

…run-llama#13442)

Add image_documents at call time for `MultiModalLLMCompletionProgra…

fa2639b

…m` (run-llama#13467)

[version] bump version to 0.10.37 (run-llama#13492)

4c2a61c

Example: GPT4o for DataExtraction from PaperCards (run-llama#13489)

662e0f6

* add nb for gpt4o mm program * rm image documents from construction * actually rm image documents from construction

Avoid unexpected error when stream chat doesn't yield (run-llama#13422)

6011233

Fix nonyielding stream chat bug Co-authored-by: Logan Markewich <logan.markewich@live.com>

chore: grammar fixes and add colab badge to nb (run-llama#13501)

4c0a617

* fix annoying grammar errors * add colab badge

Update kuzu version for new storage layer (run-llama#13516)

932b012

* Update kuzu version for new storage layer * bump version --------- Co-authored-by: Andrei Fajardo <92402603+nerdai@users.noreply.github.com>

fix for pydantic tool calling with a single argument (run-llama#13522)

e5ca11f

[Community] Resolve releasing error for `llama-index-embeddings-ipex-…

664d271

…llm` with Intel GPU supports (run-llama#13511)

Integrate VectorStore from Elasticsearch client (run-llama#13291)

07a0c66

ReAct output parser changes (run-llama#13459)

ece8f2d

remove exec from download_integration (run-llama#13523)

bd827c3

Update Milvus & Zilliz Cloud demos for latest release (run-llama#13483)

1bde70b

keligggg merged commit 8630cb0 into prod-scriptit May 16, 2024

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Update for GPT4o #10

Update for GPT4o #10

Uh oh!

keligggg commented May 16, 2024

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

20 participants

Update for GPT4o #10

Update for GPT4o #10

Uh oh!

Conversation

keligggg commented May 16, 2024

Description

New Package?

Version Bump?

Type of Change

How Has This Been Tested?

Suggested Checklist:

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

20 participants