Comments (2)
@tituslhy llm.chat()
does not take a string
Use llm.complete()
, or use llm.chat()
with a list of chat message objects
(This is true across any LLM, not just LiteLLM)
from llama_index.core.llms import ChatMessage
resp = llm.complete("Hello!")
resp = llm.chat([
ChatMessage(role="system", content="Talk like a pirate"),
ChatMessage(role="user", content="Hello!"),
])
from llama_index.
Thank you!
from llama_index.
Related Issues (20)
- [Bug]: Agent responds with accurate SQL query but then throws error HOT 2
- [Question]: llama_index.llms.openai.base.OpenAI._achat raised APIConnectionError: Connection error.. HOT 7
- [Question]: How to avoid reparsing with llama parse on app relaunch using LlamaIndex + Qdrant? HOT 1
- [Bug]: Workflow raise vague error when we don't set pass_context=True in the @step() decorator HOT 1
- [Feature Request]: Relax criteria of workflows validation
- [Bug]: Nvidia NIM Reranker HTTPError: 400 Client Error HOT 6
- [Feature Request]: Revisit `StopEvent` emission to terminate workflows HOT 1
- [Feature Request]: Make all events accessible like mappings
- [Feature Request]: Better API for `Context` HOT 1
- [Feature Request]: Support for google/gemma-2-2b-it Model in LlamaIndex HOT 2
- [Question]: How do I update my Postgres Vector database with the updated documents HOT 5
- [Bug]: Latest versions of `llama-index-multi-modal-llms-gemini` and `llama-index-llms-gemini` are not compatible with each other HOT 1
- [Feature Request]: Create a guide to usa llamaIndex with Ollama, chromaDB and SQLite (or MySql)
- [Question]: Why is PropertyGraphIndex with and use_async=True with OllamaEmbedding errorring out? HOT 6
- [Feature Request]: Allow ChatEngine to use async memory buffer?
- [Question]: OpenAILike chat have a problem. HOT 3
- [Question]: Is there any way to support the deployment of a local embedding API and a reranker API? HOT 4
- How can we pass hybrid_top_k as a parameter to VectorIndexRetriever HOT 3
- [Bug]: Metadata lookup in `SimpleDocumentStore` is insanely slow HOT 5
- [Bug]: googleapiclient.discovery_cache:file_cache is only supported with oauth2client<4.0.0 HOT 2
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 llama_index.