github/node-DeepResearch
1
0
Fork 0
mirror of https://github.com/jina-ai/node-DeepResearch.git synced 2026-03-22 07:29:35 +08:00
Code Issues Packages Projects Releases Wiki Activity

chore: add local ollama lmstudio support

Browse Source
This commit is contained in:
Han Xiao
2025-02-06 16:20:22 +08:00
parent e7d7a03f50
commit aee5598f3e
1 changed files with 4 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
README.md
View File

@@ -34,7 +34,7 @@ npm install
## Usage ## Usage
We use Gemini/OpenAI/[LocalLLM] for reasoning, [Jina Reader](https://jina.ai/reader) for searching and reading webpages, you can get a free API key with 1M tokens from jina.ai. We use Gemini/OpenAI/[LocalLLM](#use-local-llm) for reasoning, [Jina Reader](https://jina.ai/reader) for searching and reading webpages, you can get a free API key with 1M tokens from jina.ai.
```bash ```bash
export GEMINI_API_KEY=... # for gemini export GEMINI_API_KEY=... # for gemini
@@ -88,9 +88,9 @@ npm run dev "what should be jina ai strategy for 2025?"
If you use Ollama or LMStudio, you can redirect the reasoning request to your local LLM by setting the following environment variables: If you use Ollama or LMStudio, you can redirect the reasoning request to your local LLM by setting the following environment variables:
```bash ```bash
export LLM_PROVIDER=openai export LLM_PROVIDER=openai # yes, that's right - for local llm we still use openai client
export OPENAI_BASE_URL=http://127.0.0.1:1234/v1 export OPENAI_BASE_URL=http://127.0.0.1:1234/v1 # your local llm endpoint
export DEFAULT_MODEL_NAME=qwen2.5-7b export DEFAULT_MODEL_NAME=qwen2.5-7b # your local llm model name
``` ```
Not every LLM works with our reasoning flow, but you can test it out. Not every LLM works with our reasoning flow, but you can test it out.