diff options
| author | Gustaf Rydholm <gustaf.rydholm@gmail.com> | 2024-04-12 09:05:22 +0200 |
|---|---|---|
| committer | Gustaf Rydholm <gustaf.rydholm@gmail.com> | 2024-04-12 09:05:22 +0200 |
| commit | 22f8971e6c0ca0abbec8b588ef30a642fb9ec871 (patch) | |
| tree | 823b898bc020e089e12e296e0c5df5ac374cee03 | |
| parent | 3de170ee57fa474846963cfe438f2ef389703ccd (diff) | |
Update README
| -rw-r--r-- | README.md | 26 |
1 files changed, 16 insertions, 10 deletions
@@ -7,7 +7,7 @@ ctrl+f. ### Setup -#### Environment Variables +#### 1. Environment Variables Create a .env file or set the following parameters: @@ -29,7 +29,7 @@ QDRANT_COLLECTION_NAME = <QDRANT_COLLECTION_NAME> COHERE_API_KEY = <COHERE_API_KEY> # OPTIONAL ``` -### Ollama +### 2. Ollama Make sure ollama is running: @@ -44,28 +44,28 @@ ollama pull $GENERATOR_MODEL ollama pull $ENCODER_MODEL ``` -### Qdrant +### 3. Qdrant Qdrant is used to store the embeddings of the chunks from the documents. Download and run qdrant. -### Postgres +### 4. Postgres Postgres is used to save hashes of the document to prevent documents from being added to the vector db more than ones. Download and run qdrant. -### Cohere +### 5. Cohere Get an API from their website. -### Running +### 6. Running -#### Prerequisites +#### 6.1 Prerequisites -##### Python Environment +##### 6.2 Python Environment Activate the poetry shell: @@ -73,13 +73,15 @@ Activate the poetry shell: poetry shell ``` -#### CLI +#### 6.3 CLI + +Run the cli with: ```sh python rag/cli.py ``` -#### UI +#### 6.4 UI Run the web app with streamlit: @@ -87,6 +89,10 @@ Run the web app with streamlit: streamlit run rag/ui.py ``` +#### 6.5 Upload Multiple Documents + +tbc + ### Notes Yes, it is inefficient/dumb to use ollama when you can just load the models with python |