Comments (5)
annamalaiarunachalam
commented on July 29, 2024
Hello, I tried with 1.5-pro, I get a different error.
ValueError Traceback (most recent call last).....................................................
...............................
GoogleGenerativeAIError: Error embedding content: content must not be empty
if I use 1.0 I get the above error raised by the original thread. If I change to 1.5, get this error. But I didnt get any error when I used OpenAI's chat model. Why is Google's API's so annoying. You guys keen to gain more adoption, but the experience sucks. Just the other day, Google Architect, almost forced me to move away from openAi models, how can I do that? how to trust these unreliable google models.
even the embedding model is not good. Please reply to the error msg reported above.
from generative-ai-python.
singhniraj08
commented on July 29, 2024
System Instructions are introduced in Gemini 1.5 pro and will not work with Gemini 1.0 pro model. I tried running my attached gist with system instructions and it works without any issues. Please try running the gist and share with us the colab gist or code to reproduce the error you are facing on our end. Thank you!
from generative-ai-python.
annamalaiarunachalam
commented on July 29, 2024
you know what, I closed my notebook, spent sometime off, then restarted the
same notebook, same code, same 1.0 model, and RAG worked - basically the
prompt has detailed instructions for the LLM and it also does interleaved
question & answer.
I did not make any change to the code, but it worked fine with
gemin-1.0-pro.
I will try again tomorrow - if it throws error, I will post the code, the
error message in the issue that I created.
thanks
…On Wed, 8 May 2024 at 18:05, Niraj Singh ***@***.***> wrote:
@annamalaiarunachalam <https://github.com/annamalaiarunachalam>,
System Instructions are introduced in Gemini 1.5 pro and will not work
with Gemini 1.0 pro model. I tried running my attached gist
<https://colab.research.google.com/gist/singhniraj08/3aca51edf1e069c2955d4eb5cba2b9d8/genai_systemsettings_278.ipynb>
with system instructions and it works without any issues. Please try
running the gist and share with us the colab gist or code to reproduce the
error you are facing on our end. Thank you!
—
Reply to this email directly, view it on GitHub
<#328 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/ALS6KGFNCTXFC6G5JCAR2M3ZBH2FTAVCNFSM6AAAAABHMTFNNGVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDCMBQGIZDGNJQHA>
.
You are receiving this because you were mentioned.Message ID:
***@***.***>
from generative-ai-python.
singhniraj08
commented on July 29, 2024
@annamalaiarunachalam, The error might be an intermittent issue. Requesting you to close this issue, it it's resolved for you. Thank you!
from generative-ai-python.
MarkDaoust
commented on July 29, 2024
The new gemini-1.5-flash model is cheaper and faster than gemini-1.5-pro, flash supports system instructions. Use flash.
from generative-ai-python.
Related Issues (20)
- Problem no attribute 'GenerativeModel' HOT 5
- [Bugs] protobuf bugs when importing generativeai module. HOT 3
- Unclear finish_reason HOT 3
- Can’t pip install python package in NVIDIA Omniverse
- The count tokens function generates an `google.api_core.exceptions.PermissionDenied` error when using an uploaded file in the prompt using the files api HOT 2
- Allow to modify multiple request options in Python SDK (similar to JavaScript SDK) HOT 1
- langchain_google_genai._common.GoogleGenerativeAIError: Error embedding content: 504 Deadline Exceeded HOT 5
- Tuned models return no content! HOT 4
- Finish reason should be text not a number HOT 3
- Can I live stream my web cam or live video ( HLS, RTSP and RTMP) to gemini vision api? HOT 3
- The `response.text` quick accessor only works when the response contains a valid `Part`, but none was returned. Check the `candidate.safety_ratings` to see if the response was blocked. HOT 10
- Google Gemini does not provide response if tools are given
- GenerativeModel does not support multiple grounding tools
- No PDF support for files API. HOT 7
- TypeError Could not create `Blob`, expected `Blob`, `dict` or an `Image` type(`PIL.Image.Image` or `IPython.display.Image`) HOT 1
- [Bug]: SQLTalk demo is using VertexAI SDK, not Gemini SDK but is branded as GeminiAI HOT 1
- No reference docs for semantic retreiver or generate_answer.
- google.generativeai.types.generation_types.StopCandidateException: index: 0 HOT 2
- Unable to intercept requests to generativelanguages.google HOT 4
- Fix custom endpoint with file uploads and colab.
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 generative-ai-python.