vikarti.anatra/Automated-AI-Web-Researcher-Ollama
1
0
Fork 0
mirror of https://github.com/TheBlewish/Automated-AI-Web-Researcher-Ollama.git synced 2025-09-01 10:10:01 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Update README.md to include checkout

Browse source
This commit is contained in:
Alex Aridgides 2024-11-28 01:10:18 -05:00 • committed by GitHub
parent fd0bbc750c
commit 9930fad0ca
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 10 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

14
README.md
View file

@ -44,20 +44,26 @@ The key distinction is that this isn't just a chatbot—it's an automated resear
cd Automated-AI-Web-Researcher-Ollama cd Automated-AI-Web-Researcher-Ollama
``` ```
2. **Create and activate a virtual environment:** 2. **Checkout the `feature/windows-support` branch:**
```sh
git checkout -b feature/windows-support origin/feature/windows-support
```
3. **Create and activate a virtual environment:**
```sh ```sh
python -m venv venv python -m venv venv
source venv/bin/activate source venv/bin/activate
``` ```
3. **Install dependencies:** 4. **Install dependencies:**
```sh ```sh
pip install -r requirements.txt pip install -r requirements.txt
``` ```
4. **Install and configure Ollama:** 5. **Install and configure Ollama:**
Install Ollama following the instructions at [https://ollama.ai](https://ollama.ai). Install Ollama following the instructions at [https://ollama.ai](https://ollama.ai).
@ -81,7 +87,7 @@ The key distinction is that this isn't just a chatbot—it's an automated resear
**Note:** This specific configuration is necessary as recent Ollama versions have reduced context windows on models like `phi3:3.8b-mini-128k-instruct` despite the name suggesting high context, which is why the `modelfile` step is necessary due to the large amount of information used during the research process. **Note:** This specific configuration is necessary as recent Ollama versions have reduced context windows on models like `phi3:3.8b-mini-128k-instruct` despite the name suggesting high context, which is why the `modelfile` step is necessary due to the large amount of information used during the research process.
5. Go to the llm_config.py file which should hav an ollama section that looks like this: 6. Go to the llm_config.py file which should hav an ollama section that looks like this:
```sh ```sh
LLM_CONFIG_OLLAMA = { LLM_CONFIG_OLLAMA = {