Archives
/
talk-codebase
mirror of https://github.com/rsaryev/talk-codebase
2
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
120 Commits
8 Branches
0 Tags
565 KiB
dependabot/pip/urllib3-1.26.19
dependabot/pip/scikit-learn-1.5.0
dependabot/pip/requests-2.32.0
dependabot/pip/jinja2-3.1.4
dependabot/pip/tqdm-4.66.3
dependabot/pip/pydantic-1.10.13
dependabot/pip/aiohttp-3.9.4
main
Branches Tags
${ item.name }
Create tag ${ searchTerm }
Create branch ${ searchTerm }
from 'main'
${ noResults }
Commit Graph

15 Commits (main)

Author SHA1 Message Date
rsaryev b978a76402
Refactor get_repo() and load_files() functions to use Repo() without root_dir.Refactored `load_files` added a delay when creating vector store. 10 months ago
rsaryev 3d3e2dabd5
Add check for Python version. 
Add remove_model_name_local
 10 months ago
Saryev Rustam e8d7b542ea update version, refactor README.md content, config.py and cli.py for improved code readability 11 months ago
Saryev Rustam 136c09c971 Update 12 months ago
Saryev Rustam 70fee6d501 implement embedding_search method, and modify send_query and add temperature config 12 months ago
Saryev Rustam 703b98ea82 use default gpt-3.5-turbo-0613 1 year ago
Saryev Rustam 25b00a4aa0 fix(cli): update config_path variable 1 year ago
Saryev Rustam 572ee1bf4e Merge pull request #1 from rsaryev/feat/local 
GPT4All
 1 year ago
Saryev Rustam f9a31937bb Refactored CLI and LLM classes 
- Refactored the CLI and LLM classes to improve code organization and readability.
- Added a  function to create an LLM instance based on the config.
- Moved the  function to the  and  classes.
- Added a  function to handle loading an existing vector store.
- Added a  function to estimate the cost of creating a vector store for OpenAI models.
- Updated the  function to prompt for the model type and path or API key depending on the type.
- Updated the  function to use the  function and  method of the LLM instance.
- Updated the default config to include default values for  and .
- Added a  constant to store the default config values.
- Added a  constant to store the default model path.
 1 year ago
Saryev Rustam df0fc45330 Refactor file loading logic for better performance 
- Refactored the file loading logic in  function to use  instead of  which should improve performance
- Removed unnecessary checks for empty directories and ignored files
- Simplified the logic for checking allowed and excluded files
 1 year ago
Saryev Rustam ff4dc0d005 fix: calculation cost 1 year ago
Saryev Rustam 11185c079f refactor: simplify chat loop 
- Simplify the chat loop by moving it to a separate function called 'loop'.
- This improves code readability and makes it easier to test the chat function without needing to mock user input.
 1 year ago
Saryev Rustam 5f08927c76 Refactor text loader and add repo check 
- Refactored the text loader in utils.py to improve readability and maintainability.
- Added a new function called  in utils.py to check if the current directory is a git repository.
- Modified the  function in utils.py to ignore files and directories ignored by git.
- Added error handling to  function in utils.py to return  if the current directory is not a git repository.
 1 year ago
Saryev Rustam 589a419391 refactor: update function names and remove unused imports 
- Refactor cli.py and llm.py to use new function names for create_vector_store and send_question respectively
- Remove unused imports in utils.py
 1 year ago
Saryev Rustam 226203e4d9 Add CLI for chatting with OpenAI model 
- Add CLI functionality for chatting with OpenAI model
- Implement  function to allow users to input OpenAI API key and model name
- Implement  function to allow users to chat with OpenAI model using retrieved documents
- Add  module to handle sending questions to OpenAI model
- Add  module to load and split text documents, create retriever, and define StreamStdOut callback class
 1 year ago