Multiple models support for LLM #3
Open
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
…l field for ChatQnAGateway and LLMParams respectively
…els. Uses load_model_configs method from utils
…or different models
for more information, see https://pre-commit.ci
Signed-off-by: sgurunat <[email protected]>
Signed-off-by: sgurunat <[email protected]>
sgurunat
pushed a commit
that referenced
this pull request
Nov 11, 2024
* Adds an endpoint for image ingestion Signed-off-by: Melanie Buehler <[email protected]> * Combined image and video endpoint Signed-off-by: Melanie Buehler <[email protected]> * Add test and update README Signed-off-by: Melanie Buehler <[email protected]> * fixed variable name for embedding model (#1) Signed-off-by: okhleif-IL <[email protected]> * Fixed test script Signed-off-by: Melanie Buehler <[email protected]> * Remove redundant function Signed-off-by: Melanie Buehler <[email protected]> * get_videos, delete_videos --> get_files, delete_files (#3) Signed-off-by: okhleif-IL <[email protected]> * Updates test per review feedback Signed-off-by: Melanie Buehler <[email protected]> * Fixed test Signed-off-by: Melanie Buehler <[email protected]> * Add support for audio files multimodal data ingestion (#4) * Add support for audio files multimodal data ingestion Signed-off-by: dmsuehir <[email protected]> * Update function name Signed-off-by: dmsuehir <[email protected]> --------- Signed-off-by: dmsuehir <[email protected]> * Change videos_with_transcripts to ingest_with_text Signed-off-by: Melanie Buehler <[email protected]> * Add image support to video ingestion with transcript functionality Signed-off-by: Melanie Buehler <[email protected]> * Update test and README Signed-off-by: Melanie Buehler <[email protected]> * Updated for review suggestions Signed-off-by: Melanie Buehler <[email protected]> * Add two tests for ingest_with_text Signed-off-by: Melanie Buehler <[email protected]> * LVM TGI Gaudi update for prompts without images (opea-project#7) * LVM Gaudi TGI update for prompts without images Signed-off-by: dmsuehir <[email protected]> * Wording Signed-off-by: dmsuehir <[email protected]> * Add a test Signed-off-by: dmsuehir <[email protected]> --------- Signed-off-by: dmsuehir <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Change dummy image to be b64 encoded instead of the url (opea-project#9) Signed-off-by: dmsuehir <[email protected]> * Updates based on review feedback (opea-project#10) Signed-off-by: dmsuehir <[email protected]> * Test fix (opea-project#11) Signed-off-by: dmsuehir <[email protected]> --------- Signed-off-by: Melanie Buehler <[email protected]> Signed-off-by: okhleif-IL <[email protected]> Signed-off-by: dmsuehir <[email protected]> Co-authored-by: dmsuehir <[email protected]> Co-authored-by: Omar Khleif <[email protected]> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Abolfazl Shahbazi <[email protected]>
* added dpo support. Signed-off-by: Ye, Xinyu <[email protected]> * make dpo trainer compatible with newest transformers. Signed-off-by: Ye, Xinyu <[email protected]> * added ut for dpo. Signed-off-by: Ye, Xinyu <[email protected]> * added training successfulness check in finetuning ut. Signed-off-by: Ye, Xinyu <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * updated broken link. Signed-off-by: Ye, Xinyu <[email protected]> --------- Signed-off-by: Ye, Xinyu <[email protected]> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: ZePan110 <[email protected]>
* Combine CI/CD docker compose yaml files. Signed-off-by: ZePan110 <[email protected]> * Fix path issue in script Signed-off-by: ZePan110 <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Combine CI/CD docker compose yaml files. Signed-off-by: ZePan110 <[email protected]> * Fix path issue in script Signed-off-by: ZePan110 <[email protected]> * Fix path Signed-off-by: ZePan110 <[email protected]> * Combine CI/CD for .github/workflows/_comps-workflow.yml and .github/workflows/_get-image-list.yml Signed-off-by: ZePan110 <[email protected]> * Combine compose yaml file Signed-off-by: ZePan110 <[email protected]> * Remove CD file Signed-off-by: ZePan110 <[email protected]> * Add vllm-fork to CI. Signed-off-by: ZePan110 <[email protected]> * Fix issue Signed-off-by: ZePan110 <[email protected]> * Add CICD mode Signed-off-by: ZePan110 <[email protected]> * Add embedding-reranking-local to compose.yaml Signed-off-by: ZePan110 <[email protected]> * Change descriptions Signed-off-by: ZePan110 <[email protected]> * Fix script issue. Signed-off-by: ZePan110 <[email protected]> * Add new image. Signed-off-by: ZePan110 <[email protected]> * remove useless image from llms-compose.yaml Signed-off-by: ZePan110 <[email protected]> * Change folder name. Signed-off-by: ZePan110 <[email protected]> * Standardize the format of image names. Signed-off-by: ZePan110 <[email protected]> * Add commit print Signed-off-by: ZePan110 <[email protected]> * Standardize the format of image names Signed-off-by: ZePan110 <[email protected]> * Add vllm-arc to compose file. Signed-off-by: ZePan110 <[email protected]> * Restore test_agent_langchain_on_intel_hpu.sh Signed-off-by: ZePan110 <[email protected]> * Remove useless comments Signed-off-by: ZePan110 <[email protected]> --------- Signed-off-by: ZePan110 <[email protected]> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
* Add model parameter for CodeGenGateway in gateway.py file Signed-off-by: sgurunat <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Signed-off-by: sgurunat <[email protected]> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
* draft a demo code for memory. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * add agent short-term memory with langgraph checkpoint. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * add save long-term memory func. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * add save long-term memory func. * add timeout for llm response. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * fix ut with adding -e HABANA_VISIBLE_DEVICES=all. --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Signed-off-by: Abolfazl Shahbazi <[email protected]>
Signed-off-by: ZePan110 <[email protected]>
opea-project#864) * Add "megaservice_request_pending" metric Unlike other megaservice ServiceOrchestrator metrics, this covers (can cover) also non-streaming requests, as suggested in PR review. This does not have issues Prometheus-fastapi-instrumentator "inprogress" metric did: * Extra instances which have to be differentiated e.g. for CI * Rely on name -> suffix coming through obscure kwargs calls Signed-off-by: Eero Tamminen <[email protected]> * Remove HTTP "inprogress" gauge as redundant Now that ServiceOrchestrator provides pending metric. Reverts the "inprogress" metric part of commit a6998a1. Signed-off-by: Eero Tamminen <[email protected]> * Document megaservice metrics Signed-off-by: Eero Tamminen <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Signed-off-by: Eero Tamminen <[email protected]> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
for more information, see https://pre-commit.ci
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.
Description
To support multiple llm models for ChatQnA, the changes are incorporated into llms TGI text-generation. Multiple models can be provided in model_configs.json file which will be loaded into MODEL_CONFIGS environment variable.
Type of change
##Changes
To support this the model parameter has been added in the ChatQnAGateway and LLMParams from gateway.py and docarray.py respectively.
Added load_model_configs method in utils.py to validate all the required fields ( 'model_name', 'displayName', 'endpoint', 'minToken', 'maxToken') and then load the configurations. This is added in utils so that it can be reused.
Updated llm.py from llms text-generation tgi to support multiple models and transfer the call to right endpoint.
Updated the template.py file from llms text-generation tgi to have new template for models meta-llama/Meta-Llama-3.1-70B-Instruct" and "meta-llama/Meta-Llama-3.1-8B-Instruct"