Comments (2)
gpy1234
commented on July 21, 2024
@vikas25538 Did you solve the issue? I'm also facing the same challenge.
from python-aiplatform.
vikas25538
commented on July 21, 2024
what worked for me was the reduction of chunk size. Earlier, I was using 1024 as chunk size and 256 as overlap. I reduced it to 250 and 20 respectively.
So, basically you reduce the chunk size while storing the data in vector DB and then when it uses those chunks during chat, the Vertext API does not run into the internal server error.
from python-aiplatform.
Related Issues (20)
- tests.system.aiplatform.test_model_upload.TestModelUploadAndUpdate: test_upload_and_deploy_xgboost_model failed HOT 1
- tests.system.aiplatform.test_experiments.TestExperiments: test_get_time_series_data_frame_batch_read_success failed HOT 1
- tests.system.vertex_ray.test_cluster_management.TestClusterManagement: test_cluster_management[2.9] failed HOT 2
- tests.system.vertexai.test_reasoning_engines.TestReasoningEngines: test_langchain_template failed HOT 4
- Gemini Batch Prediction API throws "INTERNAL" error HOT 3
- Getting AttributeError when importing cloud_profiler from google cloud aiplatform HOT 2
- tests.system.vertex_ray.test_ray_data.TestRayData: test_ray_data[2.9] failed HOT 2
- 401 Deadline exception using Imagen Python API
- tests.system.aiplatform.test_language_models.TestLanguageModels: test_text_generation[grpc] failed HOT 1
- tests.system.aiplatform.test_language_models.TestLanguageModels: test_chat_model_async[grpc] failed HOT 1
- tests.unit.aiplatform.test_metadata.TestExperiments: test_get_experiment_df failed HOT 4
- tests.system.vertex_ray.test_job_submission_dashboard.TestJobSubmissionDashboard: test_job_submission_dashboard[2.9] failed HOT 6
- vertex-aiplatform 1.54 throwing runtime exception: Gapic client context issue . This can occur due to parallelization HOT 2
- tests.system.vertexai.test_batch_prediction.TestBatchPrediction: test_batch_prediction_with_gcs_input failed HOT 1
- Allow overwrite_table to be set in vertex_ray.data.write_bigquery()
- Batch prediction for Gemini: Failed to import data
- Palm2 TextGeneration parameter logit_bias not working
- Gemini Batch Prediction Request Job failed: code: 3
- tests.unit.aiplatform.test_model_evaluation.TestModelEvaluationJob: test_model_evaluation_job_submit[{"pipelineInfo": {"name": "evaluation-default-pipeline"}, "root": {"dag": {"tasks": {}}, "inputDefinitions": {"parameters": {"batch_predict_gcs_source_uris": {"type": "STRING"}, "dataflow_service_account": {"type": "STRING"}, "batch_predict_instances_format": {"type": "STRING"}, "batch_predict_machine_type": {"type": "STRING"}, "evaluation_class_labels": {"type": "STRING"}, "location": {"type": "STRING"}, "model_name": {"type": "STRING"}, "project": {"type": "STRING"}, "batch_predict_gcs_destination_output_uri": {"type": "STRING"}, "target_field_name": {"type": "STRING"}}}}, "schemaVersion": "2.0.0", "sdkVersion": "kfp-1.8.12", "components": {}}] failed
- tests.unit.aiplatform.test_model_evaluation.TestModelEvaluationJob: test_model_evaluation_job_submit_with_experiment[{"pipelineInfo": {"name": "evaluation-default-pipeline"}, "root": {"dag": {"tasks": {}}, "inputDefinitions": {"parameters": {"batch_predict_gcs_source_uris": {"type": "STRING"}, "dataflow_service_account": {"type": "STRING"}, "batch_predict_instances_format": {"type": "STRING"}, "batch_predict_machine_type": {"type": "STRING"}, "evaluation_class_labels": {"type": "STRING"}, "location": {"type": "STRING"}, "model_name": {"type": "STRING"}, "project": {"type": "STRING"}, "batch_predict_gcs_destination_output_uri": {"type": "STRING"}, "target_field_name": {"type": "STRING"}}}}, "schemaVersion": "2.0.0", "sdkVersion": "kfp-1.8.12", "components": {}}] failed
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from python-aiplatform.