llama-github 0.1.0__tar.gz

llama_github-0.1.0/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [2024] [Jet Xu]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

llama_github-0.1.0/MANIFEST.in

@@ -0,0 +1 @@
+include llama_github/config/config.json

llama_github-0.1.0/PKG-INFO

@@ -0,0 +1,100 @@
+Metadata-Version: 2.1
+Name: llama-github
+Version: 0.1.0
+Summary: Llama-github is an open-source Python library that empowers LLM Chatbots, AI Agents, and Auto-dev Agents to conduct Retrieval from actively selected GitHub public projects. It Augments through LLMs and Generates context for any coding question, in order to streamline the development of sophisticated AI-driven applications.
+Home-page: https://github.com/JetXu-LLM/llama-github
+Author: Jet Xu
+Author-email: Voldemort.xu@foxmail.com
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.6
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: aiohttp
+Requires-Dist: asyncio
+Requires-Dist: dataclasses
+Requires-Dist: PyGithub
+Requires-Dist: langchain
+Requires-Dist: numpy
+Requires-Dist: pydantic
+Requires-Dist: requests
+Requires-Dist: torch
+Requires-Dist: transformers
+Requires-Dist: urllib3
+Provides-Extra: dev
+Requires-Dist: pytest; extra == "dev"
+Requires-Dist: black; extra == "dev"
+Requires-Dist: flake8; extra == "dev"
+
+# llama-github
+
+[![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
+
+Llama-github is an open-source Python library that empowers LLM Chatbots, AI Agents, and Auto-dev Agents to conduct Retrieval from actively selected GitHub public contents (Repository, Issue, Code). It Augments through LLMs and Generates context for any coding question, in order to streamline the development of sophisticated AI-driven applications.
+
+## Installation
+```
+pip install llama-github
+```
+
+## Usage
+
+Here's a simple example of how to use llama-github:
+
+```python
+from llama_github import GithubRAG
+
+# Initialize GithubRAG with your credentials
+github_rag = GithubRAG(
+    github_access_token="your_github_access_token", 
+    openai_api_key="your_openai_api_key", # Optional in Simple Mode
+    jina_api_key="your_jina_api_key" # Optional - unless you want high concurrency production deployment (s.jina.ai API will be used in llama-github)
+)
+
+# Retrieve context for a coding question (simple_mode is default set to False)
+query = "How to create a NumPy array in Python?"
+context = github_rag.retrieve_context(
+    query, # In professional mode, one query will take nearly 1 min to generate final contexts. You could set log level to INFO to monitor the retrieval progress
+    # simple_mode = True
+)
+
+print(context)
+```
+
+For more advanced usage and examples, please refer to the [documentation](docs/usage.md).
+
+## Key Features
+
+- **🔍 Intelligent GitHub Retrieval**: Harness the power of llama-github to retrieve highly relevant code snippets, issues, and repository information from GitHub based on user queries. Our advanced retrieval techniques ensure you find the most pertinent information quickly and efficiently.
+
+- **⚡ Repository Pool Caching**: Llama-github has an innovative repository pool caching mechanism. By caching repositories (including READMEs, structures, code, and issues) across threads, llama-github significantly accelerates GitHub search retrieval efficiency and minimizes the consumption of GitHub API tokens. Deploy llama-github in multi-threaded production environments with confidence, knowing that it will perform optimally and save you valuable resources.
+
+- **🧠 LLM-Powered Question Analysis**: Leverage state-of-the-art language models to analyze user questions and generate highly effective search strategies and criteria. Llama-github intelligently breaks down complex queries, ensuring that you retrieve the most relevant information from GitHub's vast repository network.
+
+- **📚 Comprehensive Context Generation**: Generate rich, contextually relevant answers by seamlessly combining information retrieved from GitHub with the reasoning capabilities of advanced language models. Llama-github excels at handling even the most complex and lengthy questions, providing comprehensive and insightful responses that include extensive context to support your development needs.
+
+- **🚀 Asynchronous Processing Excellence**: Llama-github is built from the ground up to leverage the full potential of asynchronous programming. With meticulously implemented asynchronous mechanisms woven throughout the codebase, llama-github can handle multiple requests concurrently, significantly boosting overall performance. Experience the difference as llama-github efficiently manages high-volume workloads without compromising on speed or quality.
+
+- **🔧 Flexible LLM Integration**: Easily integrate llama-github with various LLM providers, embedding models, and reranking models to tailor the library's capabilities to your specific requirements. Our extensible architecture allows you to customize and enhance llama-github's functionality, ensuring that it adapts seamlessly to your unique development environment.
+
+- **🔒 Robust Authentication Options**: Llama-github supports both personal access tokens and GitHub App authentication, providing you with the flexibility to integrate it into different development setups. Whether you're an individual developer or working within an organizational context, llama-github has you covered with secure and reliable authentication mechanisms.
+
+- **🛠️ Logging and Error Handling**: We understand the importance of smooth operations and easy troubleshooting. That's why llama-github comes equipped with comprehensive logging and error handling mechanisms. Gain deep insights into the library's behavior, quickly diagnose issues, and maintain a stable and reliable development workflow.
+
+
+## Contributing
+
+We welcome contributions to llama-github! Please see our [contributing guidelines](CONTRIBUTING.md) for more information.
+
+## License
+
+This project is licensed under the terms of the Apache 2.0 license. See the [LICENSE](LICENSE) file for more details.
+
+## Contact
+
+If you have any questions, suggestions, or feedback, please feel free to reach out to us at [Voldemort.xu@foxmail.com](mailto:Voldemort.xu@foxmail.com).
+
+---
+
+Thank you for choosing llama-github! We hope this library enhances your AI development experience and helps you build powerful applications with ease.

llama_github-0.1.0/README.md

@@ -0,0 +1,71 @@
+# llama-github
+
+[![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
+
+Llama-github is an open-source Python library that empowers LLM Chatbots, AI Agents, and Auto-dev Agents to conduct Retrieval from actively selected GitHub public contents (Repository, Issue, Code). It Augments through LLMs and Generates context for any coding question, in order to streamline the development of sophisticated AI-driven applications.
+
+## Installation
+```
+pip install llama-github
+```
+
+## Usage
+
+Here's a simple example of how to use llama-github:
+
+```python
+from llama_github import GithubRAG
+
+# Initialize GithubRAG with your credentials
+github_rag = GithubRAG(
+    github_access_token="your_github_access_token", 
+    openai_api_key="your_openai_api_key", # Optional in Simple Mode
+    jina_api_key="your_jina_api_key" # Optional - unless you want high concurrency production deployment (s.jina.ai API will be used in llama-github)
+)
+
+# Retrieve context for a coding question (simple_mode is default set to False)
+query = "How to create a NumPy array in Python?"
+context = github_rag.retrieve_context(
+    query, # In professional mode, one query will take nearly 1 min to generate final contexts. You could set log level to INFO to monitor the retrieval progress
+    # simple_mode = True
+)
+
+print(context)
+```
+
+For more advanced usage and examples, please refer to the [documentation](docs/usage.md).
+
+## Key Features
+
+- **🔍 Intelligent GitHub Retrieval**: Harness the power of llama-github to retrieve highly relevant code snippets, issues, and repository information from GitHub based on user queries. Our advanced retrieval techniques ensure you find the most pertinent information quickly and efficiently.
+
+- **⚡ Repository Pool Caching**: Llama-github has an innovative repository pool caching mechanism. By caching repositories (including READMEs, structures, code, and issues) across threads, llama-github significantly accelerates GitHub search retrieval efficiency and minimizes the consumption of GitHub API tokens. Deploy llama-github in multi-threaded production environments with confidence, knowing that it will perform optimally and save you valuable resources.
+
+- **🧠 LLM-Powered Question Analysis**: Leverage state-of-the-art language models to analyze user questions and generate highly effective search strategies and criteria. Llama-github intelligently breaks down complex queries, ensuring that you retrieve the most relevant information from GitHub's vast repository network.
+
+- **📚 Comprehensive Context Generation**: Generate rich, contextually relevant answers by seamlessly combining information retrieved from GitHub with the reasoning capabilities of advanced language models. Llama-github excels at handling even the most complex and lengthy questions, providing comprehensive and insightful responses that include extensive context to support your development needs.
+
+- **🚀 Asynchronous Processing Excellence**: Llama-github is built from the ground up to leverage the full potential of asynchronous programming. With meticulously implemented asynchronous mechanisms woven throughout the codebase, llama-github can handle multiple requests concurrently, significantly boosting overall performance. Experience the difference as llama-github efficiently manages high-volume workloads without compromising on speed or quality.
+
+- **🔧 Flexible LLM Integration**: Easily integrate llama-github with various LLM providers, embedding models, and reranking models to tailor the library's capabilities to your specific requirements. Our extensible architecture allows you to customize and enhance llama-github's functionality, ensuring that it adapts seamlessly to your unique development environment.
+
+- **🔒 Robust Authentication Options**: Llama-github supports both personal access tokens and GitHub App authentication, providing you with the flexibility to integrate it into different development setups. Whether you're an individual developer or working within an organizational context, llama-github has you covered with secure and reliable authentication mechanisms.
+
+- **🛠️ Logging and Error Handling**: We understand the importance of smooth operations and easy troubleshooting. That's why llama-github comes equipped with comprehensive logging and error handling mechanisms. Gain deep insights into the library's behavior, quickly diagnose issues, and maintain a stable and reliable development workflow.
+
+
+## Contributing
+
+We welcome contributions to llama-github! Please see our [contributing guidelines](CONTRIBUTING.md) for more information.
+
+## License
+
+This project is licensed under the terms of the Apache 2.0 license. See the [LICENSE](LICENSE) file for more details.
+
+## Contact
+
+If you have any questions, suggestions, or feedback, please feel free to reach out to us at [Voldemort.xu@foxmail.com](mailto:Voldemort.xu@foxmail.com).
+
+---
+
+Thank you for choosing llama-github! We hope this library enhances your AI development experience and helps you build powerful applications with ease.

llama_github-0.1.0/llama_github/__init__.py

@@ -0,0 +1,3 @@
+from .version import __version__
+from .github_rag import GithubRAG
+from .logger import configure_logging

llama_github-0.1.0/llama_github/config/config.json

@@ -0,0 +1,20 @@
+{
+    "general_prompt": "You are a highly intelligent assistant with expertise in GitHub repositories and coding practices. Your task is to analyze questions related to GitHub projects, coding issues, or programming concepts. Using your extensive knowledge base, you will provide detailed, accurate, and contextually relevant answers. You have the ability to understand complex coding queries, retrieve pertinent information from GitHub repositories, and augment this data with your advanced reasoning capabilities. Your responses should guide developers towards solving their problems, understanding new concepts, or finding the information they seek related to GitHub projects and software development.",
+    "always_answer_prompt": "**Instructions:**\nAs an advanced AI assistant with deep expertise in GitHub repositories, coding practices, and programming concepts, your primary goal is to provide concise, accurate, and contextually relevant answers to complex coding queries. When presented with a question, your first step is to analyze the query and generate a succinct abstraction that captures its core essence by using only one sentence, especially if the original question is lengthy or convoluted.\n\nNext, leverage your extensive knowledge base and reasoning capabilities to craft a coherent and informative response. If possible, enhance your answer with sample code snippets that demonstrate the practical application of the concepts discussed. Remember, your responses should guide developers towards solving their problems, understanding new concepts, or finding the information they seek related to GitHub projects and software development. Please keep your responses concise and to the point, focusing on the most essential information needed to address the query. Avoid generating long articles or overly detailed explanations.\n\nIn addition to the answer itself, provide a brief analysis of how you would approach searching for relevant code and issues within GitHub repositories. This analysis should outline your thought process and the key factors you would consider when conducting these searches. However, keep this analysis concise and focused on the high-level logic rather than delving into specific search criteria or keywords.\n\nThroughout your responses, prioritize clarity and brevity. Focus on delivering the most essential information needed to address the query effectively. Even if certain details are unknown, ensure that your answers are plausible, useful, and serve as a foundation for further exploration and context generation.\n\nRemember, your ultimate aim is to empower developers with the knowledge and guidance they need to overcome challenges, expand their understanding, and navigate the vast landscape of GitHub repositories and software development practices.",
+    "code_search_criteria_prompt": "**Instructions:**\n- **Expertise-Driven Github Code Search Criteria Generation:** Generate GitHub code search criteria strings based on the provided question and its draft answer. Analyze both the question and answer to identify key concepts, technologies, and coding practices that can help locate relevant code snippets on GitHub. Always include the `language:` qualifier to focus your search on language-related content.\n\n**Output Format:** Present each search criteria string on a new line, formatted for immediate use in GitHub's code search, without additional explanations or commentary.\n\n**Optimization Considerations:**\n- **Keyword Relevance:** Extract keywords and phrases tightly related to the question from the question and answer that are likely to appear in relevant code and code comments. Prioritize terms that reflect specific coding concepts, libraries, or techniques. Avoid generic terms like \"example\" or \"integration\" that may not be present in actual code.\n- **Contextual Understanding:** Use the provided answer as additional context to inform your keyword selection. Identify key insights, technologies, or approaches mentioned in the answer tightly related to the question that can help refine the search criteria.\n- **Language and Platform Specificity:** If the question is specific to a certain programming language or platform, ensure to include relevant language or platform-specific keywords, libraries, or frameworks in the search criteria. This helps filter out irrelevant results from other languages or platforms.\n- **Simplicity and Effectiveness:** Craft search criteria with simple and limited keywords which could lead to precise search results to relevant code snippets tightly related to original question. Strike a balance between specificity and breadth to ensure the criteria capture the essential aspects of the question and answer. The search criteria should be neither too narrow that no results are returned, nor too broad that many irrelevant results are included.\n- **Multiple Perspectives:** Generate multiple search criteria strings that approach the question from different angles or emphasize different aspects mentioned in the question and answer. This increases the chances of finding relevant code snippets.",
+    "issue_search_criteria_prompt": "**Instructions:**\n- **Question-Driven GitHub Issue Search Criteria Generation:** Generate GitHub issue search criteria strings based on the provided question. Analyze the question to identify key concepts, technologies, and problem-solving approaches that can help locate relevant issues on GitHub. Consider using relevant `label:` or `is:` qualifiers when applicable.\n\n**Output Format:** Present each search criteria string on a new line, formatted for immediate use in GitHub's issue search, without additional explanations or commentary.\n\n**Optimization Considerations:**\n- **Keyword Relevance:** Extract keywords and phrases tightly related to the question that are likely to appear in issue titles, descriptions, and discussions. Prioritize terms that reflect specific problems, error messages, or technologies. Avoid generic terms like \"help\" or \"problem\" that may not effectively narrow down the search results.\n- **Contextual Understanding:** Use the question's draft answer to inform your keyword selection. Identify key aspects, technologies, or potential troubleshooting areas tightly related to the question but not only specific aspects of answers that can help refine the search criteria.\n- **Simplicity and Effectiveness:** Craft search criteria with simple and limited keywords which could lead to precise search results relevant to the original question. Strike a balance between specificity and breadth to ensure the criteria capture the essential aspects of the question without being overly restrictive.\n- **Multiple Perspectives:** Generate multiple search criteria strings that approach the question from different angles or emphasize different aspects mentioned in the question. This increases the chances of finding relevant issues that discuss similar problems or solutions.\n- **Leveraging Labels:** When appropriate, include relevant `label:` qualifiers in the search criteria to narrow down the results to issues with specific labels, such as \"bug,\" \"enhancement,\" or \"documentation.\" This can help focus the search on issues that align with the nature of the question.\n- **Considering Issue Discussions:** Keep in mind that issue discussions often contain valuable information, experiences, and workarounds shared by other developers. Craft search criteria that not only match the issue title and description but also consider the likelihood of the keywords appearing in the issue's comments and discussions.",
+    "repo_search_criteria_prompt": "**Instructions:**\n- **Expertise-Driven Github Repository Search Criteria Generation:** Generate GitHub repo search criteria strings based on the provided question. Analyze the question leverage your expertise for related key concepts, technologies, and problem-solving approaches that can help locate relevant repositories on GitHub. Focus on practical keywords and phrases likely to be present in repository names, descriptions, and topics. Use the `language:` qualifier to direct your search toward repositories written in a specific language, keeping the criteria simple and effective.\n- **Necessity Score Determination:** Evaluate the necessity of conducting a GitHub repository search based on the difficulty of question. Determine if repository-level information is essential to comprehensively address the question. Assign a necessity score indicating the importance of performing a repository search.\n\n**Output Format:**\n- **Necessity Score:** Begin your output with a necessity score (0-100) indicating the importance of performing a separate GitHub repository search. Use the following scale:\n  - 0-59: Low necessity - Only code and issue search results is sufficient.\n  - 60-79: Medium necessity - One repository search may offer additional insights and context.\n  - 80-100: High necessity - Two repository searches are crucial to gather comprehensive information, such as project structure, documentation, or community engagement, to thoroughly address the question.\n\n- **Search Criteria:** Present each search criteria string on a new line, formatted for immediate use in GitHub's repository search, without additional explanations or commentary.\n**Optimization Considerations:**\n- **Keyword Relevance:** Generate search criteria keywords and phrases from the question that are uniquely relevant to repository names, descriptions, and topics. Prioritize terms that reflect the broader context, expertise, and strategic thinking required to address the question effectively. Avoid generic terms that may lead to irrelevant search results.\n- **Simplicity and Effectiveness:** Craft search criteria that are simple yet effective in narrowing down the repository search results to the most relevant and informative ones. Strike a balance between specificity and breadth, ensuring that the criteria capture the essential aspects of the question without being overly restrictive. Aim for criteria that yield a manageable number of high-quality repository results.\n- **Language and Platform Specificity:** If the question pertains to a specific programming language or platform, incorporate relevant language or platform-specific keywords in the search criteria. Use the `language:` qualifier to filter repositories based on the language of interest. This helps focus the search on repositories that are more likely to contain relevant code, documentation, and community expertise.\n- **Multiple Criteria Flexibility:** Generate multiple search criteria strings that approach the question from different angles or emphasize different aspects mentioned in the question. This flexibility allows for a more comprehensive repository search, increasing the chances of discovering relevant repositories that may offer valuable insights, code samples, or best practices related to the question at hand.",
+    "scoring_context_prompt": "You are an expert in evaluating the relevance of coding-related contexts to given questions. Your primary function is to analyze the provided context and question, and output a single integer score between 0 and 100, indicating how well the context supports answering the question.\n\nScoring criteria:\n0-20: The context is completely irrelevant to the question and provides no useful information to answer it.\n21-40: The context is slightly relevant to the question but lacks crucial information to provide a complete answer.\n41-60: The context is somewhat relevant to the question and provides some useful information, but it may not be sufficient to fully answer the question.\n61-80: The context is highly relevant to the question and provides most of the necessary information to answer it, but some minor details may be missing.\n81-100: The context is extremely relevant to the question and provides all the necessary information to comprehensively answer it.\n\nRemember, your output should consist of only a single integer score without any additional text or explanation. Analyze the context and question carefully, and provide a score that accurately reflects the relevance of the context in answering the question.",
+    "default_embedding": "jinaai/jina-embeddings-v2-base-code",
+    "default_reranker": "jinaai/jina-reranker-v1-turbo-en",
+    "min_stars_to_keep_result": 20,
+    "max_workers": 8,
+    "code_search_max_hits": 30,
+    "issue_search_max_hits": 30,
+    "repo_search_max_hits": 10,
+    "chunk_size": 2000,
+    "issue_chunk_size": 7000,
+    "repo_chunk_size": 7000,
+    "google_chunk_size": 7000,
+    "top_n_contexts": 5
+}

llama_github-0.1.0/llama_github/config/config.py

@@ -0,0 +1,30 @@
+# config.py
+import json
+from importlib import resources
+from llama_github.logger import logger
+
+# utils.py
+class SingletonMeta(type):
+    _instances = {}
+    def __call__(cls, *args, **kwargs):
+        if cls not in cls._instances:
+            instance = super().__call__(*args, **kwargs)
+            cls._instances[cls] = instance
+        return cls._instances[cls]
+
+class Config(metaclass=SingletonMeta):
+    _config = None
+
+    def __init__(self):
+        if Config._config is None:
+            with resources.open_text('llama_github.config', 'config.json') as file:
+                Config._config = json.load(file)
+
+    @classmethod
+    def get(cls, key, default=None):
+        # Ensure the singleton instance is created
+        if cls._config is None:
+            cls()
+        return cls._config.get(key, default)
+
+config = Config()