idchlife/rag-solution
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

quick fix to use openai instead of ollama, in vetor_storage.py

Browse Source
This commit is contained in:
idchlife
2026-02-05 00:04:10 +03:00
parent f87f3c0cdd
commit 833aad317a
2 changed files with 40 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
services/rag/langchain/QWEN.md
View File

@@ -105,12 +105,19 @@ The project is organized into 8 development phases as outlined in `PLANNING.md`:
The project uses environment variables for configuration:
```env
# Embedding configuration
OLLAMA_EMBEDDING_MODEL=MODEL # Name of the Ollama model for embeddings
OPENAI_EMBEDDING_MODEL=MODEL # Name of the OpenAI model for embeddings (default: text-embedding-ada-002)
OPENAI_EMBEDDING_BASE_URL=URL # OpenAI-compatible API URL for embeddings
OPENAI_EMBEDDING_API_KEY=KEY # API key for OpenAI-compatible embedding service
EMBEDDING_STRATEGY=ollama # Strategy to use for embeddings: "ollama" (default) or "openai"
# Chat model configuration
OLLAMA_CHAT_MODEL=MODEL # Name of the Ollama model for chat
OPENAI_CHAT_URL=URL # OpenAI-compatible API URL
OPENAI_CHAT_KEY=KEY # Authorization token for OpenAI-compatible API
OPENAI_CHAT_MODEL=MODEL # Name of the OpenAI-compatible model to use
CHAT_MODEL_STRATEGY=ollama # Strategy to use: "ollama" (default) or "openai"
OPENAI_CHAT_URL=URL # OpenAI-compatible API URL for chat
OPENAI_CHAT_KEY=KEY # Authorization token for OpenAI-compatible API for chat
OPENAI_CHAT_MODEL=MODEL # Name of the OpenAI-compatible model to use for chat
CHAT_MODEL_STRATEGY=ollama # Strategy to use for chat: "ollama" (default) or "openai"
```
## Building and Running
@@ -234,4 +241,6 @@ The project is in early development phase. The virtual environment is set up and
### Troubleshooting Notes
- If encountering "No module named 'unstructured_inference'" error, install unstructured-inference
- If seeing OCR-related errors, ensure tesseract is installed at the system level and unstructured-pytesseract is available
- For language detection issues, verify that appropriate spaCy models are downloaded
- For language detection issues, verify that appropriate spaCy models are downloaded
- If getting Ollama connection errors when using OpenAI strategy, ensure EMBEDDING_STRATEGY is set correctly in .env
- When deploying without Ollama, set both CHAT_MODEL_STRATEGY and EMBEDDING_STRATEGY to "openai" in your .env file