Merge remote-tracking branch 'origin/main'

# Conflicts:
#	pr_agent/tools/pr_description.py

README.md

@@ -43,6 +43,12 @@ CodiumAI PR-Agent aims to help efficiently review and handle pull requests, by p
   
 ## News and Updates
 
+### September 21, 2024
+Need help with PR-Agent? New feature - simply comment `/help "your question"` in a pull request, and PR-Agent will provide you with the [relevant documentation](https://github.com/Codium-ai/pr-agent/pull/1241#issuecomment-2365259334).
+
+<kbd><img src="https://www.codium.ai/images/pr_agent/pr_help_chat.png" width="768"></kbd>
+
+
 ### September 12, 2024
 [Dynamic context](https://pr-agent-docs.codium.ai/core-abilities/dynamic_context/) is now the default option for context extension. 
 This feature enables PR-Agent to dynamically adjusting the relevant context for each code hunk, while avoiding overflowing the model with too much information.

docker/Dockerfile

@@ -1,6 +1,7 @@
 FROM python:3.12.3 AS base
 
 WORKDIR /app
+ADD docs/chroma_db.zip /app/docs/chroma_db.zip
 ADD pyproject.toml .
 ADD requirements.txt .
 RUN pip install . && rm pyproject.toml requirements.txt

docs/docs/index.md

@@ -8,6 +8,7 @@ CodiumAI PR-Agent is an open-source tool to help efficiently review and handle p
 
 - See the [Tools Guide](./tools/index.md) for a detailed description of the different tools.
 
+To search the documentation site using natural language, simply comment `/help "your question"` in a pull request where PR-Agent is installed. PR-Agent will then provide you with an [answer](https://github.com/Codium-ai/pr-agent/pull/1241#issuecomment-2365259334), including relevant documentation links.
 
 ## PR-Agent Features
 PR-Agent offers extensive pull request functionalities across various git providers.

pr_agent/config_loader.py

@@ -27,8 +27,9 @@ global_settings = Dynaconf(
         "settings/pr_update_changelog_prompts.toml",
         "settings/pr_custom_labels.toml",
         "settings/pr_add_docs.toml",
+        "settings/custom_labels.toml",
+        "settings/pr_help_prompts.toml",
         "settings_prod/.secrets.toml",
-        "settings/custom_labels.toml"
     ]]
 )
 

pr_agent/settings/configuration.toml

@@ -183,6 +183,7 @@ enable_help_text=true
 final_update_message = false
 
 [pr_help] # /help #
+force_local_db=false
 
 [pr_config] # /config #
 

pr_agent/settings/pr_help_prompts.toml

@@ -0,0 +1,43 @@
+[pr_help_prompts]
+system="""You are Doc-helper, a language models designed to answer questions about a documentation website for an open-soure project called "PR-Agent".
+You will recieve a question, and a list of snippets that were collected for a documentation site using RAG as the retrieval method.
+Your goal is to provide the best answer to the question using the snippets provided.
+Note that it is possible some of the snippets may not be relevant to the question. In that case, you should ignore them and focus on the ones that are relevant.
+
+Try to be short and concise in your answers.
+
+The output must be a YAML object equivalent to type $doc_help, according to the following Pydantic definitions:
+
+class doc_help(BaseModel):
+    user_question: str = Field(description="The user's question")
+    response: str = Field(description="The response to the user's question")
+    relevant_snippets: List[int] = Field(description="One-based index of the relevant snippets in the list of snippets provided. Order the by relevance, with the most relevant first. If a snippet was not relevant, do not include it in the list.")
+
+Example output:
+```yaml
+user_question: |
+  ...
+response: |
+    ...
+relevant_snippets:
+    - 1
+    - 2
+    - 4
+"""
+
+user="""\
+User's Question:
+=====
+{{ question|trim }}
+=====
+
+
+Relevant doc snippets retrieved:
+=====
+{{ snippets|trim }}
+=====
+
+
+Response (should be a valid YAML, and nothing else):
+```yaml
+"""

pr_agent/tools/pr_description.py

@@ -117,8 +117,9 @@ class PRDescription:
                 pr_body += "<hr>\n\n<details> <summary><strong>✨ Describe tool usage guide:</strong></summary><hr> \n\n"
                 pr_body += HelpMessage.get_describe_usage_guide()
                 pr_body += "\n</details>\n"
-            elif get_settings().pr_description.enable_help_comment:
+            elif self.git_provider.is_supported("gfm_markdown") and get_settings().pr_description.enable_help_comment:
-                pr_body += '\n\n___\n\n> 💡 **PR-Agent usage**: Comment `/help "your question"` on any pull request to receive relevant information'
+                pr_body += "\n\n___\n\n> 💡 **PR-Agent usage**:"
+                pr_body += '\n>Need PR-Agent help? Comment `/help "your question"` on any pull request to receive relevant information'
 
             # Output the relevant configurations if enabled
             if get_settings().get('config', {}).get('output_relevant_configurations', False):

pr_agent/tools/pr_help_message.py

@@ -1,106 +1,350 @@
+import os
+import traceback
+import zipfile
+import tempfile
+import copy
+from functools import partial
+
+from jinja2 import Environment, StrictUndefined
+
+from pr_agent.algo.ai_handlers.base_ai_handler import BaseAiHandler
+from pr_agent.algo.ai_handlers.litellm_ai_handler import LiteLLMAIHandler
+from pr_agent.algo.pr_processing import retry_with_fallback_models
+from pr_agent.algo.token_handler import TokenHandler
+from pr_agent.algo.utils import ModelType, load_yaml
 from pr_agent.config_loader import get_settings
-from pr_agent.git_providers import get_git_provider, GithubProvider
+from pr_agent.git_providers import get_git_provider, GithubProvider, BitbucketServerProvider, \
+    get_git_provider_with_context
 from pr_agent.log import get_logger
 
 
+def extract_header(snippet):
+    res = ''
+    lines = snippet.split('===Snippet content===')[0].split('\n')
+    highest_header = ''
+    highest_level = float('inf')
+    for line in lines[::-1]:
+        line = line.strip()
+        if line.startswith('Header '):
+            highest_header = line.split(': ')[1]
+    if highest_header:
+        res = f"#{highest_header.lower().replace(' ', '-')}"
+    return res
+
 class PRHelpMessage:
-    def __init__(self, pr_url: str, args=None, ai_handler=None):
+    def __init__(self, pr_url: str, args=None, ai_handler: partial[BaseAiHandler,] = LiteLLMAIHandler):
-        self.git_provider = get_git_provider()(pr_url)
+        self.git_provider = get_git_provider_with_context(pr_url)
+        self.ai_handler = ai_handler()
+        self.question_str = self.parse_args(args)
+        if self.question_str:
+            self.vars = {
+                "question": self.question_str,
+                "snippets": "",
+            }
+            self.token_handler = TokenHandler(None,
+                                              self.vars,
+                                              get_settings().pr_help_prompts.system,
+                                              get_settings().pr_help_prompts.user)
+
+    async def _prepare_prediction(self, model: str):
+        try:
+            variables = copy.deepcopy(self.vars)
+            environment = Environment(undefined=StrictUndefined)
+            system_prompt = environment.from_string(get_settings().pr_help_prompts.system).render(variables)
+            user_prompt = environment.from_string(get_settings().pr_help_prompts.user).render(variables)
+            response, finish_reason = await self.ai_handler.chat_completion(
+                model=model, temperature=get_settings().config.temperature, system=system_prompt, user=user_prompt)
+            return response
+        except Exception as e:
+            get_logger().error(f"Error while preparing prediction: {e}")
+            return ""
+
+    def parse_args(self, args):
+        if args and len(args) > 0:
+            question_str = " ".join(args)
+        else:
+            question_str = ""
+        return question_str
+
+    def get_sim_results_from_s3_db(self, embeddings):
+        get_logger().info("Loading the S3 index...")
+        sim_results = []
+        try:
+            from langchain_chroma import Chroma
+            from urllib import request
+            with tempfile.TemporaryDirectory() as temp_dir:
+                # Define the local file path within the temporary directory
+                local_file_path = os.path.join(temp_dir, 'chroma_db.zip')
+
+                bucket = 'pr-agent'
+                file_name = 'chroma_db.zip'
+                s3_url = f'https://{bucket}.s3.amazonaws.com/{file_name}'
+                request.urlretrieve(s3_url, local_file_path)
+
+                # # Download the file from S3 to the temporary directory
+                # s3 = boto3.client('s3')
+                # s3.download_file(bucket, file_name, local_file_path)
+
+                # Extract the contents of the zip file
+                with zipfile.ZipFile(local_file_path, 'r') as zip_ref:
+                    zip_ref.extractall(temp_dir)
+
+                vectorstore = Chroma(persist_directory=temp_dir + "/chroma_db",
+                                     embedding_function=embeddings)
+                sim_results = vectorstore.similarity_search_with_score(self.question_str, k=4)
+        except Exception as e:
+            get_logger().error(f"Error while getting sim from S3: {e}",
+                               artifact={"traceback": traceback.format_exc()})
+        return sim_results
+
+    def get_sim_results_from_local_db(self, embeddings):
+        get_logger().info("Loading the local index...")
+        sim_results = []
+        try:
+            from langchain_chroma import Chroma
+            get_logger().info("Loading the Chroma index...")
+            db_path = "./docs/chroma_db.zip"
+            if not os.path.exists(db_path):
+                db_path= "/app/docs/chroma_db.zip"
+                if not os.path.exists(db_path):
+                    get_logger().error("Local db not found")
+                    return sim_results
+            with tempfile.TemporaryDirectory() as temp_dir:
+
+                # Extract the ZIP file
+                with zipfile.ZipFile(db_path, 'r') as zip_ref:
+                    zip_ref.extractall(temp_dir)
+
+                vectorstore = Chroma(persist_directory=temp_dir + "/chroma_db",
+                                     embedding_function=embeddings)
+
+                # Do similarity search
+                sim_results = vectorstore.similarity_search_with_score(self.question_str, k=4)
+        except Exception as e:
+            get_logger().error(f"Error while getting sim from local db: {e}",
+                               artifact={"traceback": traceback.format_exc()})
+        return sim_results
+
+    def get_sim_results_from_pinecone_db(self, embeddings):
+        get_logger().info("Loading the Pinecone index...")
+        sim_results = []
+        try:
+            from langchain_pinecone import PineconeVectorStore
+            INDEX_NAME = "pr-agent-docs"
+            vectorstore = PineconeVectorStore(
+                index_name=INDEX_NAME, embedding=embeddings,
+                pinecone_api_key=get_settings().pinecone.api_key
+            )
+
+            # Do similarity search
+            sim_results = vectorstore.similarity_search_with_score(self.question_str, k=4)
+        except Exception as e:
+            get_logger().error(f"Error while getting sim from Pinecone db: {e}",
+                               artifact={"traceback": traceback.format_exc()})
+        return sim_results
 
     async def run(self):
         try:
-            if not self.git_provider.is_supported("gfm_markdown"):
+            if self.question_str:
-                self.git_provider.publish_comment(
+                get_logger().info(f'Answering a PR question about the PR {self.git_provider.pr_url} ')
-                    "The `Help` tool requires gfm markdown, which is not supported by your code platform.")
-                return
 
-            get_logger().info('Getting PR Help Message...')
+                if not get_settings().get('openai.key'):
-            relevant_configs = {'pr_help': dict(get_settings().pr_help),
+                    if get_settings().config.publish_output:
-                                'config': dict(get_settings().config)}
+                        self.git_provider.publish_comment(
-            get_logger().debug("Relevant configs", artifacts=relevant_configs)
+                            "The `Help` tool chat feature requires an OpenAI API key for calculating embeddings")
-            pr_comment = "## PR Agent Walkthrough 🤖\n\n"
+                    else:
-            pr_comment += "Welcome to the PR Agent, an AI-powered tool for automated pull request analysis, feedback, suggestions and more."""
+                        get_logger().error("The `Help` tool chat feature requires an OpenAI API key for calculating embeddings")
-            pr_comment += "\n\nHere is a list of tools you can use to interact with the PR Agent:\n"
+                    return
-            base_path = "https://pr-agent-docs.codium.ai/tools"
 
-            tool_names = []
+                # Initialize embeddings
-            tool_names.append(f"[DESCRIBE]({base_path}/describe/)")
+                from langchain_openai import OpenAIEmbeddings
-            tool_names.append(f"[REVIEW]({base_path}/review/)")
+                embeddings = OpenAIEmbeddings(model="text-embedding-ada-002",
-            tool_names.append(f"[IMPROVE]({base_path}/improve/)")
+                                              api_key=get_settings().openai.key)
-            tool_names.append(f"[UPDATE CHANGELOG]({base_path}/update_changelog/)")
-            tool_names.append(f"[ADD DOCS]({base_path}/documentation/) 💎")
-            tool_names.append(f"[TEST]({base_path}/test/) 💎")
-            tool_names.append(f"[IMPROVE COMPONENT]({base_path}/improve_component/) 💎")
-            tool_names.append(f"[ANALYZE]({base_path}/analyze/) 💎")
-            tool_names.append(f"[ASK]({base_path}/ask/)")
-            tool_names.append(f"[GENERATE CUSTOM LABELS]({base_path}/custom_labels/) 💎")
-            tool_names.append(f"[CI FEEDBACK]({base_path}/ci_feedback/) 💎")
-            tool_names.append(f"[CUSTOM PROMPT]({base_path}/custom_prompt/) 💎")
-            tool_names.append(f"[SIMILAR ISSUE]({base_path}/similar_issues/)")
 
-            descriptions = []
+                # Get similar snippets via similarity search
-            descriptions.append("Generates PR description - title, type, summary, code walkthrough and labels")
+                if get_settings().pr_help.force_local_db:
-            descriptions.append("Adjustable feedback about the PR, possible issues, security concerns, review effort and more")
+                    sim_results = self.get_sim_results_from_local_db(embeddings)
-            descriptions.append("Code suggestions for improving the PR")
+                elif get_settings().get('pinecone.api_key'):
-            descriptions.append("Automatically updates the changelog")
+                    sim_results = self.get_sim_results_from_pinecone_db(embeddings)
-            descriptions.append("Generates documentation to methods/functions/classes that changed in the PR")
+                else:
-            descriptions.append("Generates unit tests for a specific component, based on the PR code change")
+                    sim_results = self.get_sim_results_from_s3_db(embeddings)
-            descriptions.append("Code suggestions for a specific component that changed in the PR")
+                    if not sim_results:
-            descriptions.append("Identifies code components that changed in the PR, and enables to interactively generate tests, docs, and code suggestions for each component")
+                        get_logger().info("Failed to load the S3 index. Loading the local index...")
-            descriptions.append("Answering free-text questions about the PR")
+                        sim_results = self.get_sim_results_from_local_db(embeddings)
-            descriptions.append("Generates custom labels for the PR, based on specific guidelines defined by the user")
+                if not sim_results:
-            descriptions.append("Generates feedback and analysis for a failed CI job")
+                    get_logger().error("Failed to retrieve similar snippets. Exiting...")
-            descriptions.append("Generates custom suggestions for improving the PR code, derived only from a specific guidelines prompt defined by the user")
+                    return
-            descriptions.append("Automatically retrieves and presents similar issues")
 
-            commands  =[]
+                # Prepare relevant snippets
-            commands.append("`/describe`")
+                relevant_pages_full, relevant_snippets_full_header, relevant_snippets_str =\
-            commands.append("`/review`")
+                    await self.prepare_relevant_snippets(sim_results)
-            commands.append("`/improve`")
+                self.vars['snippets'] = relevant_snippets_str.strip()
-            commands.append("`/update_changelog`")
-            commands.append("`/add_docs`")
-            commands.append("`/test`")
-            commands.append("`/improve_component`")
-            commands.append("`/analyze`")
-            commands.append("`/ask`")
-            commands.append("`/generate_labels`")
-            commands.append("`/checks`")
-            commands.append("`/custom_prompt`")
-            commands.append("`/similar_issue`")
 
-            checkbox_list = []
+                # run the AI model
-            checkbox_list.append(" - [ ] Run <!-- /describe -->")
+                response = await retry_with_fallback_models(self._prepare_prediction, model_type=ModelType.REGULAR)
-            checkbox_list.append(" - [ ] Run <!-- /review -->")
+                response_yaml = load_yaml(response)
-            checkbox_list.append(" - [ ] Run <!-- /improve -->")
+                response_str = response_yaml.get('response')
-            checkbox_list.append(" - [ ] Run <!-- /update_changelog -->")
+                relevant_snippets_numbers = response_yaml.get('relevant_snippets')
-            checkbox_list.append(" - [ ] Run <!-- /add_docs -->")
-            checkbox_list.append(" - [ ] Run <!-- /test -->")
-            checkbox_list.append(" - [ ] Run <!-- /improve_component -->")
-            checkbox_list.append(" - [ ] Run <!-- /analyze -->")
-            checkbox_list.append("[*]")
-            checkbox_list.append("[*]")
-            checkbox_list.append("[*]")
-            checkbox_list.append("[*]")
-            checkbox_list.append("[*]")
-            checkbox_list.append("[*]")
-            checkbox_list.append("[*]")
-            checkbox_list.append("[*]")
 
-            if isinstance(self.git_provider, GithubProvider) and not get_settings().config.get('disable_checkboxes', False):
+                # prepare the answer
-                pr_comment += f"<table><tr align='left'><th align='left'>Tool</th><th align='left'>Description</th><th align='left'>Trigger Interactively :gem:</th></tr>"
+                answer_str = ""
-                for i in range(len(tool_names)):
+                if response_str:
-                    pr_comment += f"\n<tr><td align='left'>\n\n<strong>{tool_names[i]}</strong></td>\n<td>{descriptions[i]}</td>\n<td>\n\n{checkbox_list[i]}\n</td></tr>"
+                    answer_str += f"### Question: \n{self.question_str}\n\n"
-                pr_comment += "</table>\n\n"
+                    answer_str += f"### Answer:\n{response_str.strip()}\n\n"
-                pr_comment += f"""\n\n(1) Note that each tool be [triggered automatically](https://pr-agent-docs.codium.ai/usage-guide/automations_and_usage/#github-app-automatic-tools-when-a-new-pr-is-opened) when a new PR is opened, or called manually by [commenting on a PR](https://pr-agent-docs.codium.ai/usage-guide/automations_and_usage/#online-usage)."""
+                    answer_str += f"#### Relevant Sources:\n\n"
-                pr_comment += f"""\n\n(2) Tools marked with [*] require additional parameters to be passed. For example, to invoke the `/ask` tool, you need to comment on a PR: `/ask "<question content>"`. See the relevant documentation for each tool for more details."""
+                    paged_published = []
+                    for page in relevant_snippets_numbers:
+                        page = int(page - 1)
+                        if page < len(relevant_pages_full) and page >= 0:
+                            if relevant_pages_full[page] in paged_published:
+                                continue
+                            link = f"{relevant_pages_full[page]}{relevant_snippets_full_header[page]}"
+                            # answer_str += f"> - [{relevant_pages_full[page]}]({link})\n"
+                            answer_str += f"> - {link}\n"
+                            paged_published.append(relevant_pages_full[page])
+
+                # publish the answer
+                if get_settings().config.publish_output:
+                    self.git_provider.publish_comment(answer_str)
+                else:
+                    get_logger().info(f"Answer: {response}")
             else:
-                pr_comment += f"<table><tr align='left'><th align='left'>Tool</th><th align='left'>Command</th><th align='left'>Description</th></tr>"
+                if not isinstance(self.git_provider, BitbucketServerProvider) and not self.git_provider.is_supported("gfm_markdown"):
-                for i in range(len(tool_names)):
+                    self.git_provider.publish_comment(
-                    pr_comment += f"\n<tr><td align='left'>\n\n<strong>{tool_names[i]}</strong></td><td>{commands[i]}</td><td>{descriptions[i]}</td></tr>"
+                        "The `Help` tool requires gfm markdown, which is not supported by your code platform.")
-                pr_comment += "</table>\n\n"
+                    return
-                pr_comment += f"""\n\nNote that each tool be [invoked automatically](https://pr-agent-docs.codium.ai/usage-guide/automations_and_usage/) when a new PR is opened, or called manually by [commenting on a PR](https://pr-agent-docs.codium.ai/usage-guide/automations_and_usage/#online-usage)."""
+
-            if get_settings().config.publish_output:
+                get_logger().info('Getting PR Help Message...')
-                self.git_provider.publish_comment(pr_comment)
+                relevant_configs = {'pr_help': dict(get_settings().pr_help),
+                                    'config': dict(get_settings().config)}
+                get_logger().debug("Relevant configs", artifacts=relevant_configs)
+                pr_comment = "## PR Agent Walkthrough 🤖\n\n"
+                pr_comment += "Welcome to the PR Agent, an AI-powered tool for automated pull request analysis, feedback, suggestions and more."""
+                pr_comment += "\n\nHere is a list of tools you can use to interact with the PR Agent:\n"
+                base_path = "https://pr-agent-docs.codium.ai/tools"
+
+                tool_names = []
+                tool_names.append(f"[DESCRIBE]({base_path}/describe/)")
+                tool_names.append(f"[REVIEW]({base_path}/review/)")
+                tool_names.append(f"[IMPROVE]({base_path}/improve/)")
+                tool_names.append(f"[UPDATE CHANGELOG]({base_path}/update_changelog/)")
+                tool_names.append(f"[ADD DOCS]({base_path}/documentation/) 💎")
+                tool_names.append(f"[TEST]({base_path}/test/) 💎")
+                tool_names.append(f"[IMPROVE COMPONENT]({base_path}/improve_component/) 💎")
+                tool_names.append(f"[ANALYZE]({base_path}/analyze/) 💎")
+                tool_names.append(f"[ASK]({base_path}/ask/)")
+                tool_names.append(f"[GENERATE CUSTOM LABELS]({base_path}/custom_labels/) 💎")
+                tool_names.append(f"[CI FEEDBACK]({base_path}/ci_feedback/) 💎")
+                tool_names.append(f"[CUSTOM PROMPT]({base_path}/custom_prompt/) 💎")
+                tool_names.append(f"[SIMILAR ISSUE]({base_path}/similar_issues/)")
+
+                descriptions = []
+                descriptions.append("Generates PR description - title, type, summary, code walkthrough and labels")
+                descriptions.append("Adjustable feedback about the PR, possible issues, security concerns, review effort and more")
+                descriptions.append("Code suggestions for improving the PR")
+                descriptions.append("Automatically updates the changelog")
+                descriptions.append("Generates documentation to methods/functions/classes that changed in the PR")
+                descriptions.append("Generates unit tests for a specific component, based on the PR code change")
+                descriptions.append("Code suggestions for a specific component that changed in the PR")
+                descriptions.append("Identifies code components that changed in the PR, and enables to interactively generate tests, docs, and code suggestions for each component")
+                descriptions.append("Answering free-text questions about the PR")
+                descriptions.append("Generates custom labels for the PR, based on specific guidelines defined by the user")
+                descriptions.append("Generates feedback and analysis for a failed CI job")
+                descriptions.append("Generates custom suggestions for improving the PR code, derived only from a specific guidelines prompt defined by the user")
+                descriptions.append("Automatically retrieves and presents similar issues")
+
+                commands  =[]
+                commands.append("`/describe`")
+                commands.append("`/review`")
+                commands.append("`/improve`")
+                commands.append("`/update_changelog`")
+                commands.append("`/add_docs`")
+                commands.append("`/test`")
+                commands.append("`/improve_component`")
+                commands.append("`/analyze`")
+                commands.append("`/ask`")
+                commands.append("`/generate_labels`")
+                commands.append("`/checks`")
+                commands.append("`/custom_prompt`")
+                commands.append("`/similar_issue`")
+
+                checkbox_list = []
+                checkbox_list.append(" - [ ] Run <!-- /describe -->")
+                checkbox_list.append(" - [ ] Run <!-- /review -->")
+                checkbox_list.append(" - [ ] Run <!-- /improve -->")
+                checkbox_list.append(" - [ ] Run <!-- /update_changelog -->")
+                checkbox_list.append(" - [ ] Run <!-- /add_docs -->")
+                checkbox_list.append(" - [ ] Run <!-- /test -->")
+                checkbox_list.append(" - [ ] Run <!-- /improve_component -->")
+                checkbox_list.append(" - [ ] Run <!-- /analyze -->")
+                checkbox_list.append("[*]")
+                checkbox_list.append("[*]")
+                checkbox_list.append("[*]")
+                checkbox_list.append("[*]")
+                checkbox_list.append("[*]")
+                checkbox_list.append("[*]")
+                checkbox_list.append("[*]")
+                checkbox_list.append("[*]")
+
+                if isinstance(self.git_provider, GithubProvider) and not get_settings().config.get('disable_checkboxes', False):
+                    pr_comment += f"<table><tr align='left'><th align='left'>Tool</th><th align='left'>Description</th><th align='left'>Trigger Interactively :gem:</th></tr>"
+                    for i in range(len(tool_names)):
+                        pr_comment += f"\n<tr><td align='left'>\n\n<strong>{tool_names[i]}</strong></td>\n<td>{descriptions[i]}</td>\n<td>\n\n{checkbox_list[i]}\n</td></tr>"
+                    pr_comment += "</table>\n\n"
+                    pr_comment += f"""\n\n(1) Note that each tool be [triggered automatically](https://pr-agent-docs.codium.ai/usage-guide/automations_and_usage/#github-app-automatic-tools-when-a-new-pr-is-opened) when a new PR is opened, or called manually by [commenting on a PR](https://pr-agent-docs.codium.ai/usage-guide/automations_and_usage/#online-usage)."""
+                    pr_comment += f"""\n\n(2) Tools marked with [*] require additional parameters to be passed. For example, to invoke the `/ask` tool, you need to comment on a PR: `/ask "<question content>"`. See the relevant documentation for each tool for more details."""
+                elif isinstance(self.git_provider, BitbucketServerProvider):
+                    # only support basic commands in BBDC
+                    pr_comment = generate_bbdc_table(tool_names[:4], descriptions[:4])
+                else:
+                    pr_comment += f"<table><tr align='left'><th align='left'>Tool</th><th align='left'>Command</th><th align='left'>Description</th></tr>"
+                    for i in range(len(tool_names)):
+                        pr_comment += f"\n<tr><td align='left'>\n\n<strong>{tool_names[i]}</strong></td><td>{commands[i]}</td><td>{descriptions[i]}</td></tr>"
+                    pr_comment += "</table>\n\n"
+                    pr_comment += f"""\n\nNote that each tool be [invoked automatically](https://pr-agent-docs.codium.ai/usage-guide/automations_and_usage/) when a new PR is opened, or called manually by [commenting on a PR](https://pr-agent-docs.codium.ai/usage-guide/automations_and_usage/#online-usage)."""
+
+                if get_settings().config.publish_output:
+                    self.git_provider.publish_comment(pr_comment)
         except Exception as e:
-            get_logger().error(f"Error while running PRHelpMessage: {e}")
+            get_logger().exception(f"Error while running PRHelpMessage: {e}")
         return ""
+
+    async def prepare_relevant_snippets(self, sim_results):
+        # Get relevant snippets
+        relevant_snippets_full = []
+        relevant_pages_full = []
+        relevant_snippets_full_header = []
+        th = 0.75
+        for s in sim_results:
+            page = s[0].metadata['source']
+            content = s[0].page_content
+            score = s[1]
+            relevant_snippets_full.append(content)
+            relevant_snippets_full_header.append(extract_header(content))
+            relevant_pages_full.append(page)
+        # build the snippets string
+        relevant_snippets_str = ""
+        for i, s in enumerate(relevant_snippets_full):
+            relevant_snippets_str += f"Snippet {i}:\n\n{s}\n\n"
+            relevant_snippets_str += "-------------------\n\n"
+        return relevant_pages_full, relevant_snippets_full_header, relevant_snippets_str
+
+
+def generate_bbdc_table(column_arr_1, column_arr_2):
+    # Generating header row
+    header_row = "| Tool  | Description | \n"
+
+    # Generating separator row
+    separator_row = "|--|--|\n"
+
+    # Generating data rows
+    data_rows = ""
+    max_len = max(len(column_arr_1), len(column_arr_2))
+    for i in range(max_len):
+        col1 = column_arr_1[i] if i < len(column_arr_1) else ""
+        col2 = column_arr_2[i] if i < len(column_arr_2) else ""
+        data_rows += f"| {col1} | {col2} |\n"
+
+    # Combine all parts to form the complete table
+    markdown_table = header_row + separator_row + data_rows
+    return markdown_table

requirements.txt

@@ -1,4 +1,4 @@
-aiohttp==3.9.4
+aiohttp==3.9.5
 anthropic[vertex]==0.21.3
 atlassian-python-api==3.41.4
 azure-devops==7.1.0b3
@@ -13,7 +13,7 @@ Jinja2==3.1.2
 litellm==1.43.13
 loguru==0.7.2
 msrest==0.7.1
-openai==1.40.6
+openai==1.46.0
 pytest==7.4.0
 PyGithub==1.59.*
 PyYAML==6.0.1
@@ -28,6 +28,12 @@ gunicorn==22.0.0
 pytest-cov==5.0.0
 pydantic==2.8.2
 html2text==2024.2.26
+# help bot
+langchain==0.3.0
+langchain-openai==0.2.0
+langchain-pinecone==0.2.0
+langchain-chroma==0.1.4
+chromadb==0.5.7
 # Uncomment the following lines to enable the 'similar issue' tool
 # pinecone-client
 # pinecone-datasets @ git+https://github.com/mrT23/pinecone-datasets.git@main