Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Wrong Ollama endpoint #929

Open
blakkd opened this issue Oct 19, 2024 · 0 comments
Open

Wrong Ollama endpoint #929

blakkd opened this issue Oct 19, 2024 · 0 comments

Comments

@blakkd
Copy link

blakkd commented Oct 19, 2024

Describe the bug

From 3.1.0, ollama endpoint seems to be set to [OLLAMA_BASE_URL]/chat/completions instead of /api/chat or /api/generate, resulting in a 404 error.

Rolling back to 3.0.8 with the same .env file restores the correct behavior (connecting to /api/chat).

Doesn't seem related to dd94598.

To Reproduce

git clone https://github.com/assafelovic/gpt-researcher
cd gpt-researcher
pip -r install requirements.txt
python -m uvicorn main:app --reload

Ollama logs

3.1.0 [GIN] 2024/10/19 - 13:55:00 | 404 | 22.452µs | 127.0.0.1 | POST "/chat/completions"

3.0.8 [GIN] 2024/10/19 - 14:11:28 | 200 | 1.322965182s | 127.0.0.1 | POST "/api/chat"

.env

RETRIEVER=tavily
TAVILY_API_KEY="tvly-xxxxxxxxxxx"

LLM_PROVIDER=ollama
EMBEDDING_PROVIDER=ollama
OLLAMA_BASE_URL=http://localhost:11434

FAST_LLM_MODEL=qwen2.5:32b-instruct-q4_K_M_11k
SMART_LLM_MODEL=qwen2.5:32b-instruct-q4_K_M_11k

TEMPERATURE=0.55

OLLAMA_EMBEDDING_MODEL=bge-m3_gpu
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant