Merge branch 'docs' of https://github.com/microsoft/TaskWeaver into docs

.github/workflows/deploy-website.yaml

@@ -0,0 +1,47 @@
+name: docs
+
+on:
+  pull_request:
+    branches: [docs]
+    path:
+      - 'website/*'
+      - '.github/workflows/deploy-website.yml'
+  push:
+    branches: [docs]
+    path:
+      - 'website/*'
+      - '.github/workflows/deploy-website.yml'
+  workflow_dispatch:
+  merge_group:
+    types: [checks_requested]
+
+jobs:
+  gh-release:
+    runs-on: ubuntu-latest
+    defaults:
+      run:
+        working-directory: website
+    steps:
+      - uses: actions/checkout@v3
+      - name: Use Node.js
+        uses: actions/setup-node@v3
+        with:
+          node-version: 20.x
+      - name: Build website
+        run: |
+          if [ -e yarn.lock ]; then
+          yarn install --frozen-lockfile --ignore-engines
+          yarn build
+          elif [ -e package-lock.json ]; then
+          npm ci
+          npm run build
+          else
+          npm i --legacy-peer-deps
+          npm run build
+          fi
+      - name: Deploy to GitHub Pages
+        uses: peaceiris/actions-gh-pages@v3
+        with:
+          github_token: ${{ secrets.GITHUB_TOKEN }}
+          # Build output to publish to the `gh-pages` branch:
+          publish_dir: ./website/build

.github/workflows/pytest.yml

@@ -0,0 +1,43 @@
+name: Python package
+
+on:
+  push:
+    branches:    
+      - main
+  pull_request:
+    branches:    
+      - main
+
+jobs:
+  pytest:
+
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.11"]
+
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Display Python version
+        run: python -c "import sys; print(sys.version)"
+      - name: Install taskweaver
+        run: |
+          python -m pip install --upgrade pip setuptools wheel
+          pip install -e .
+      - name: Test with pytest
+        run: |
+          pip install pytest pytest-cov
+          pytest tests/unit_tests --collect-only
+          pytest tests/unit_tests -v --junitxml=junit/test-results-${{ matrix.python-version }}.xml --cov=com --cov-report=xml --cov-report=html
+      - name: Upload pytest test results
+        uses: actions/upload-artifact@v3
+        with:
+          name: pytest-results-${{ matrix.python-version }}
+          path: junit/test-results-${{ matrix.python-version }}.xml
+        # Use always() to always run this step to publish test results when there are test failures
+        if: ${{ always() }}
+

project/codeinterpreter_examples/example1-codeinterpreter.yaml

@@ -8,12 +8,12 @@ rounds:
         send_from: Planner
         send_to: CodeInterpreter
         attachment_list: []
-      - message: Greetings! {ROLE_NAME} can understand the user request and generate syntactically correct python code to complete tasks and can utilize pre-defined plugins in the form of python functions to achieve tasks.
+      - message: Greetings! I can understand the user request and generate syntactically correct python code to complete tasks and can utilize pre-defined plugins in the form of python functions to achieve tasks.
         send_from: CodeInterpreter
         send_to: Planner
         attachment_list:
           - type: text
-            content: Greetings! {ROLE_NAME} can understand the user request and generate syntactically correct python code to complete tasks and can utilize pre-defined plugins in the form of python functions to achieve tasks.
+            content: Greetings! I can understand the user request and generate syntactically correct python code to complete tasks and can utilize pre-defined plugins in the form of python functions to achieve tasks.
           - type: verification
             content: NONE
           - type: code_error

project/codeinterpreter_examples/example2-codeinterpreter.yaml

@@ -41,7 +41,7 @@ rounds:
         send_to: Planner
         attachment_list:
           - type: thought
-            content: "{ROLE_NAME} understands that the execution of the previous round has fell."
+            content: "{ROLE_NAME} understands that the execution of the previous round has failed."
           - type: thought
             content: "{ROLE_NAME} understands that the file /abc/def.txt does not exist and will not attempt to read it again."
           - type: text

project/plugins/klarna_search.yaml

@@ -3,6 +3,8 @@ enabled: true
 required: false
 description: >-
   Search and compare prices from thousands of online shops. Only available in the US.
+  This plugin only takes user requests when searching for merchandise.
+  If not clear, confirm with the user if they want to search for merchandise from Klarna.
 
 parameters:
   - name: query

project/plugins/sql_pull_data.py

@@ -37,6 +37,9 @@ def __call__(self, query: str):
             {schema}
 
             Question: {question}
+            Please only write the sql query.
+            Do not add any comments or extra text.
+            Do not wrap the query in quotes or ```sql.
             SQL Query:"""
         prompt = ChatPromptTemplate.from_template(template)
 

project/plugins/sql_pull_data.yaml

@@ -2,8 +2,9 @@ name: sql_pull_data
 enabled: true
 required: false
 description: >-
-  Pull data from a SQL database. This plugin takes user requests when obtaining data from database is explicitly mentioned.
-  Otherwise, it is not sure if the user wants to pull data from database or not.
+  Pull data from a SQL database. 
+  This plugin takes user requests when obtaining data from database is explicitly mentioned.
+  Otherwise, confirm with the user if they want to pull data from this database.
   The data from this database can only used for anomaly detection.
 
 parameters:

requirements.txt

@@ -8,9 +8,10 @@ pyyaml>=6.0
 scikit-learn>=1.2.2
 click>=8.0.1
 urllib3>=1.26.17
-jsonschema==4.17.3
+jsonschema==4.20.0
 injector>=0.21.0
 ijson>=3.2.3
+requests>=2.31.0
 
 # Code Execution related
 ipykernel==6.26.0

taskweaver/code_interpreter/code_generator/code_generator.py

@@ -27,7 +27,7 @@ def _configure(self) -> None:
             "prompt_file_path",
             os.path.join(
                 os.path.dirname(os.path.abspath(__file__)),
-                "code_generator_json_prompt.yaml",
+                "code_generator_prompt.yaml",
             ),
         )
         self.example_base_path = self._get_path(
@@ -147,15 +147,15 @@ def compose_prompt(
             self.examples = self.load_examples(plugin_only=self.plugin_only)
         for i, example in enumerate(self.examples):
             chat_history.extend(
-                self.compose_conversation(example.rounds, example.plugins),
+                self.compose_conversation(example.rounds, example.plugins, add_requirements=False),
             )
 
         summary = None
         if self.config.prompt_compression:
             summary, rounds = self.round_compressor.compress_rounds(
                 rounds,
                 rounds_formatter=lambda _rounds: str(
-                    self.compose_conversation(_rounds, plugins),
+                    self.compose_conversation(_rounds, plugins, add_requirements=False),
                 ),
                 use_back_up_engine=True,
                 prompt_template=self.compression_template,
@@ -171,27 +171,36 @@ def compose_prompt(
         )
         return chat_history
 
+    def format_attachment(self, attachment: Attachment):
+        if attachment.type == AttachmentType.thought:
+            return attachment.content.format(ROLE_NAME=self.role_name)
+        else:
+            return attachment.content
+
     def compose_conversation(
         self,
         rounds: List[Round],
         plugins: List[PluginEntry],
         add_requirements: bool = False,
         summary: Optional[str] = None,
     ) -> List[ChatMessageType]:
-        def format_attachment(attachment: Attachment):
-            if attachment.type == AttachmentType.thought:
-                return attachment.content.format(ROLE_NAME=self.role_name)
-            else:
-                return attachment.content
-
         chat_history: List[ChatMessageType] = []
+        ignored_types = [
+            AttachmentType.revise_message,
+            AttachmentType.verification,
+            AttachmentType.code_error,
+            AttachmentType.execution_status,
+            AttachmentType.execution_result,
+        ]
+
         is_first_post = True
+        last_post: Post = None
         for round_index, conversation_round in enumerate(rounds):
             for post_index, post in enumerate(conversation_round.post_list):
                 # compose user query
                 user_message = ""
                 assistant_message = ""
-
+                is_final_post = round_index == len(rounds) - 1 and post_index == len(conversation_round.post_list) - 1
                 if is_first_post:
                     user_message = (
                         self.conversation_head_template.format(
@@ -209,37 +218,53 @@ def format_attachment(attachment: Attachment):
                     enrichment = ""
                     if plan is not None:
                         enrichment = (
-                            f"To complete this request:{user_query}\n\n"
+                            f"To complete this request: {user_query}\n\n"
                             f"I have drawn up a plan: \n{plan}\n\n"
                             f"Please proceed with this step of this plan:"
                         )
 
+                    user_feedback = "None"
+                    if last_post is not None and last_post.send_from == "CodeInterpreter":
+                        user_feedback = format_code_feedback(last_post)
+
                     user_message += self.user_message_head_template.format(
+                        FEEDBACK=user_feedback,
                         MESSAGE=f"{enrichment}{post.message}",
                     )
-                elif post.send_from == "CodeInterpreter" and post.send_to == "CodeInterpreter":
+                elif post.send_from == post.send_to == "CodeInterpreter":
                     # for code correction
                     user_message += self.user_message_head_template.format(
+                        FEEDBACK=format_code_feedback(post),
                         MESSAGE=f"{post.get_attachment(AttachmentType.revise_message)[0]}",
                     )
 
                     assistant_message = self.post_translator.post_to_raw_text(
                         post=post,
-                        content_formatter=format_attachment,
+                        content_formatter=self.format_attachment,
                         if_format_message=False,
                         if_format_send_to=False,
-                        ignore_types=[AttachmentType.revise_message],
+                        ignored_types=ignored_types,
                     )
                 elif post.send_from == "CodeInterpreter" and post.send_to == "Planner":
+                    if is_final_post:
+                        # This user message is added to make the conversation complete
+                        # It is used to make sure the last assistant message has a feedback
+                        # This is only used for examples or context summarization
+                        user_message += self.user_message_head_template.format(
+                            FEEDBACK=format_code_feedback(post),
+                            MESSAGE="This is the feedback.",
+                        )
+
                     assistant_message = self.post_translator.post_to_raw_text(
                         post=post,
-                        content_formatter=format_attachment,
+                        content_formatter=self.format_attachment,
                         if_format_message=False,
                         if_format_send_to=False,
-                        ignore_types=[AttachmentType.revise_message],
+                        ignored_types=ignored_types,
                     )
                 else:
                     raise ValueError(f"Invalid post: {post}")
+                last_post = post
 
                 if len(assistant_message) > 0:
                     chat_history.append(
@@ -250,11 +275,9 @@ def format_attachment(attachment: Attachment):
                     )
                 if len(user_message) > 0:
                     # add requirements to the last user message
-                    if add_requirements and post_index == len(conversation_round.post_list) - 1:
+                    if is_final_post and add_requirements:
                         user_message += "\n" + self.query_requirements_template.format(
-                            PLUGIN_ONLY_PROMPT=self.compose_verification_requirements(
-                                plugins,
-                            ),
+                            CODE_GENERATION_REQUIREMENTS=self.compose_verification_requirements(plugins),
                             ROLE_NAME=self.role_name,
                         )
                     chat_history.append(
@@ -300,7 +323,7 @@ def reply(
 
         prompt = self.compose_prompt(rounds, self.plugin_pool)
 
-        def early_stop(_type: AttachmentType, value: str):
+        def early_stop(_type: AttachmentType, value: str) -> bool:
             if _type in [AttachmentType.text, AttachmentType.python, AttachmentType.sample]:
                 return True
             else:
@@ -377,3 +400,33 @@ def format_output_revision_message() -> str:
         "Don't surround the JSON with ```json and ```, just send the JSON object directly.\n"
         "Please try again."
     )
+
+
+def format_code_feedback(post: Post) -> str:
+    feedback = ""
+    verification_status = ""
+    execution_status = ""
+    for attachment in post.attachment_list:
+        if attachment.type == AttachmentType.verification and attachment.content == "CORRECT":
+            feedback += "## Verification\nI have verified that your code is CORRECT.\n"
+            verification_status = "CORRECT"
+        elif attachment.type == AttachmentType.verification and attachment.content == "NONE":
+            feedback += "## Verification\nNo code verification.\n"
+            verification_status = "NONE"
+        elif attachment.type == AttachmentType.verification and attachment.content == "INCORRECT":
+            feedback += "## Verification\nYour code is INCORRECT with the following error:\n"
+            verification_status = "INCORRECT"
+        elif attachment.type == AttachmentType.code_error and verification_status == "INCORRECT":
+            feedback += f"{attachment.content}\n"
+        elif attachment.type == AttachmentType.execution_status and attachment.content == "NONE":
+            feedback += "## Execution\nNo code execution.\n"
+            execution_status = "NONE"
+        elif attachment.type == AttachmentType.execution_status and attachment.content == "SUCCESS":
+            feedback += "## Execution\nYour code has been executed successfully with the following result:\n"
+            execution_status = "SUCCESS"
+        elif attachment.type == AttachmentType.execution_status and attachment.content == "FAILURE":
+            feedback += "## Execution\nYour code has failed to execute with the following error:\n"
+            execution_status = "FAILURE"
+        elif attachment.type == AttachmentType.execution_result and execution_status != "NONE":
+            feedback += f"{attachment.content}\n"
+    return feedback