Karthik Rajan

Eaton Corporation Southfield, MI, USA I explore, develop applications/tools, and write about things at the intersection of computational mechanics, material science, and generative AI.

Results 8 comments of


                                            Karthik Rajan

affinity.py script indicate that there are invalid values

I have the same issue!

[Bug] Incomplete PDF Conversion When Processing Multiple Files

I get incomplete conversions. When I use single file conversion, it captures all the texts and tables. However, when I try multiple file conversions on similar PDFs, I get partial...

Use local embedding run local search

The local search with embeddings from Ollama now works. You can read full guide here: https://medium.com/@karthik.codex/microsofts-graphrag-autogen-ollama-chainlit-fully-local-free-multi-agent-rag-superbot-61ad3759f06f Here is the link to the repo: https://github.com/karthik-codex/autogen_graphRAG

[Local Embeddings] Community Support thread

The local search with embeddings from Ollama now works. You can read full guide here: https://medium.com/@karthik.codex/microsofts-graphrag-autogen-ollama-chainlit-fully-local-free-multi-agent-rag-superbot-61ad3759f06f Here is the link to the repo: https://github.com/karthik-codex/autogen_graphRAG

[Feature Request]: Local LLM and embedding

The local search with embeddings from Ollama now works. You can read full guide here: https://medium.com/@karthik.codex/microsofts-graphrag-autogen-ollama-chainlit-fully-local-free-multi-agent-rag-superbot-61ad3759f06f Here is the link to the repo: https://github.com/karthik-codex/autogen_graphRAG

[Bug]: <title>Error embedding chunk {'OpenAIEmbedding': "'NoneType' object is not iterable"}

The local search with embeddings from Ollama now works. You can read full guide here: https://medium.com/@karthik.codex/microsofts-graphrag-autogen-ollama-chainlit-fully-local-free-multi-agent-rag-superbot-61ad3759f06f Here is the link to the repo: https://github.com/karthik-codex/autogen_graphRAG

Unable to load unsloth models in just single GPU in a multi GPU system

I still get the same error

[Issue]: <title> Local LLM and Loacl embedding error?

The local search with embeddings from Ollama now works. You can read full guide here: https://medium.com/@karthik.codex/microsofts-graphrag-autogen-ollama-chainlit-fully-local-free-multi-agent-rag-superbot-61ad3759f06f Here is the link to the repo: https://github.com/karthik-codex/autogen_graphRAG