XThomasBU commited on
Commit
1ed8d55
1 Parent(s): db6b619
Files changed (2) hide show
  1. README.md +2 -1
  2. docs/README.md +1 -0
README.md CHANGED
@@ -20,7 +20,8 @@ Clone the repository from: https://github.com/DL4DS/dl4ds_tutor
20
  Put your data under the `storage/data` directory. Note: You can add urls in the urls.txt file, and other pdf files in the `storage/data` directory.
21
 
22
  To create the Vector Database, run the following command:
23
- ```python code/modules/vector_db.py```
 
24
 
25
  To run the chainlit app, run the following command:
26
  ```chainlit run code/main.py```
 
20
  Put your data under the `storage/data` directory. Note: You can add urls in the urls.txt file, and other pdf files in the `storage/data` directory.
21
 
22
  To create the Vector Database, run the following command:
23
+ ```python code/modules/vector_db.py```
24
+ (Note: You would need to run the above when you add new data to the `storage/data` directory, or if the ``storage/data/urls.txt`` file is updated. Or you can set ``["embedding_options"]["embedd_files"]`` to True in the `code/config.yaml` file, which would embed files from the storage directory everytime you run the below chainlit command.)
25
 
26
  To run the chainlit app, run the following command:
27
  ```chainlit run code/main.py```
docs/README.md CHANGED
@@ -37,6 +37,7 @@
37
 
38
  ## Useful Configurations
39
  set these in `code/config.yaml`:
 
40
  * ``["embedding_options"]["expand_urls"]`` - If set to True, gets and reads the data from all the links under the url provided. If set to False, only reads the data in the url provided.
41
  * ``["embedding_options"]["search_top_k"]`` - Number of sources that the retriever returns
42
  * ``["llm_params]["use_history"]`` - Whether to use history in the prompt or not
 
37
 
38
  ## Useful Configurations
39
  set these in `code/config.yaml`:
40
+ * ``["embedding_options"]["embedd_files"]`` - If set to True, embeds the files from the storage directory everytime you run the chainlit command. If set to False, uses the stored vector database.
41
  * ``["embedding_options"]["expand_urls"]`` - If set to True, gets and reads the data from all the links under the url provided. If set to False, only reads the data in the url provided.
42
  * ``["embedding_options"]["search_top_k"]`` - Number of sources that the retriever returns
43
  * ``["llm_params]["use_history"]`` - Whether to use history in the prompt or not