fastworkflow 2.17.26__tar.gz → 2.17.28__tar.gz

fastworkflow-2.17.26/README.md → fastworkflow-2.17.28/PKG-INFO

@@ -1,3 +1,48 @@
+Metadata-Version: 2.1
+Name: fastworkflow
+Version: 2.17.28
+Summary: A framework for rapidly building large-scale, deterministic, interactive workflows with a fault-tolerant, conversational UX
+License: Apache-2.0
+Keywords: fastworkflow,ai,workflow,llm,openai
+Author: Dhar Rawal
+Author-email: drawal@radiantlogic.com
+Requires-Python: >=3.11,<3.14
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Provides-Extra: fastapi
+Provides-Extra: training
+Requires-Dist: aiohttp (>=3.13.3)
+Requires-Dist: colorama (>=0.4.6,<0.5.0)
+Requires-Dist: datasets (>=4.0.0,<5.0.0) ; extra == "training"
+Requires-Dist: dspy (>=3.0.1,<4.0.0)
+Requires-Dist: fastapi (>=0.120.1) ; extra == "fastapi"
+Requires-Dist: fastapi-mcp (>=0.4.0,<0.5.0) ; extra == "fastapi"
+Requires-Dist: filelock (>=3.20.1)
+Requires-Dist: libcst (>=1.8.2,<2.0.0)
+Requires-Dist: litellm[proxy] (>=1.81.4,<2.0.0)
+Requires-Dist: mmh3 (>=5.1.0,<6.0.0)
+Requires-Dist: openai (>=2.8.0)
+Requires-Dist: orjson (>=3.9.15)
+Requires-Dist: prompt_toolkit (>=3.0.43,<4.0.0)
+Requires-Dist: pyasn1 (>=0.6.2)
+Requires-Dist: pydantic (>=2.9.2,<3.0.0)
+Requires-Dist: pyjwt[crypto] (>=2.4.0) ; extra == "fastapi"
+Requires-Dist: pynacl (>=1.6.2)
+Requires-Dist: python-dotenv (>=1.0.1,<2.0.0)
+Requires-Dist: python-levenshtein (>=0.27.1,<0.28.0)
+Requires-Dist: scikit-learn (>=1.6.1,<2.0.0)
+Requires-Dist: speedict (>=0.3.12,<0.4.0)
+Requires-Dist: starlette (>=0.49.1)
+Requires-Dist: torch (>=2.7.1,<3.0.0)
+Requires-Dist: transformers (>=4.48.2,<5.0.0)
+Requires-Dist: urllib3 (>=2.6.0)
+Requires-Dist: uvicorn (>=0.31.1,<0.32.0) ; extra == "fastapi"
+Project-URL: homepage, https://github.com/radiantlogicinc/fastworkflow
+Project-URL: repository, https://github.com/radiantlogicinc/fastworkflow
+Description-Content-Type: text/markdown
+
 <!-- Logo and Title -->
 <img src="logo.png" height="64" alt="fastWorkflow Logo and Title">
 
@@ -88,6 +133,9 @@ While [DSPy](https://dspy.ai) ([Why DSPy](https://x.com/lateinteraction/status/1
     - [Adding context hierarchies with context_inheritance_model.json](#adding-context-hierarchies-with-context_inheritance_modeljson)
     - [Using DSPy for Response Generation](#using-dspy-for-response-generation)
     - [Using Startup Commands and Actions](#using-startup-commands-and-actions)
+    - [Running FastWorkflow as a FastAPI Service](#running-fastworkflow-as-a-fastapi-service)
+        - [Kubernetes Liveness and Readiness Probes](#kubernetes-liveness-and-readiness-probes)
+        - [Using LiteLLM Proxy](#using-litellm-proxy)
 - [Rapidly Building Workflows with the Build Tool](#rapidly-building-workflows-with-the-build-tool)
 - [Environment Variables Reference](#environment-variables-reference)
     - [Environment Variables](#environment-variables)
@@ -537,6 +585,110 @@ For workflows with complex initialization requirements, creating a dedicated sta
 
 ---
 
+### Running FastWorkflow as a FastAPI Service
+
+For production deployments and integrations, fastWorkflow provides a FastAPI-based HTTP service via the `run_fastapi_mcp` module. This exposes your workflow as REST endpoints with JWT authentication, SSE streaming, and MCP (Model Context Protocol) support.
+
+```sh
+# Run the FastAPI service
+python -m fastworkflow.run_fastapi_mcp \
+  --workflow_path ./my_workflow \
+  --env_file_path ./fastworkflow.env \
+  --passwords_file_path ./fastworkflow.passwords.env \
+  --port 8000
+```
+
+The service provides endpoints for:
+- `/initialize` - Create a new session and obtain JWT tokens
+- `/invoke_agent` - Submit natural language queries to the agent
+- `/invoke_agent_stream` - Stream responses via SSE or NDJSON
+- `/perform_action` - Execute workflow actions directly
+- `/conversations` - Manage conversation history
+
+#### Kubernetes Liveness and Readiness Probes
+
+When deploying fastWorkflow in Kubernetes, the service provides dedicated probe endpoints for health monitoring:
+
+**Liveness Probe (`/probes/healthz`)**
+
+Determines whether the container is still running. If this probe fails, Kubernetes will restart the container.
+
+```sh
+curl http://localhost:8000/probes/healthz
+# Response: {"status": "alive"}
+```
+
+**Readiness Probe (`/probes/readyz`)**
+
+Checks whether the container is ready to accept traffic. Kubernetes only routes traffic to containers that pass this check.
+
+```sh
+curl http://localhost:8000/probes/readyz
+# Response (ready): {"status": "ready", "checks": {"ready": true, "fastworkflow_initialized": true, "workflow_path_valid": true}}
+# Response (not ready): {"status": "not_ready", "checks": {"ready": false, ...}}
+```
+
+The readiness probe returns:
+- `200 OK` when the application is ready to serve traffic
+- `503 Service Unavailable` when not ready (e.g., during startup)
+
+**Example Kubernetes Configuration**
+
+```yaml
+apiVersion: apps/v1
+kind: Deployment
+spec:
+  template:
+    spec:
+      containers:
+        - name: fastworkflow
+          livenessProbe:
+            httpGet:
+              path: /probes/healthz
+              port: 8000
+            initialDelaySeconds: 10
+            periodSeconds: 10
+            failureThreshold: 5
+            timeoutSeconds: 3
+          readinessProbe:
+            httpGet:
+              path: /probes/readyz
+              port: 8000
+            initialDelaySeconds: 5
+            periodSeconds: 5
+            failureThreshold: 3
+            timeoutSeconds: 3
+```
+
+> [!note]
+> Probe endpoints do not require authentication and are excluded from request logging when returning 200 status to avoid excessive log noise from frequent Kubernetes health checks.
+
+#### Using LiteLLM Proxy
+
+FastWorkflow supports routing LLM calls through a [LiteLLM Proxy](https://docs.litellm.ai/docs/simple_proxy) server. This is useful when you want to:
+- Centralize API key management
+- Use a unified endpoint for multiple LLM providers
+- Route requests through a corporate proxy with custom configurations
+
+To use LiteLLM Proxy, set your model strings to use the `litellm_proxy/` prefix and configure the proxy URL:
+
+```
+# In fastworkflow.env - use the litellm_proxy/ prefix for model names
+LLM_AGENT=litellm_proxy/bedrock_mistral_large_2407
+LLM_PARAM_EXTRACTION=litellm_proxy/bedrock_mistral_large_2407
+LITELLM_PROXY_API_BASE=http://127.0.0.1:4000
+
+# In fastworkflow.passwords.env - shared key for proxy authentication
+LITELLM_PROXY_API_KEY=your-proxy-api-key
+```
+
+The model name after `litellm_proxy/` (e.g., `bedrock_mistral_large_2407`) is passed to your proxy server, which routes it to the actual provider based on its configuration.
+
+> [!note]
+> When using `litellm_proxy/` models, the per-role API keys (`LITELLM_API_KEY_*`) are ignored. All proxied calls use the shared `LITELLM_PROXY_API_KEY` instead. You can mix proxied and direct models - only models with the `litellm_proxy/` prefix are routed through the proxy.
+
+---
+
 ## Rapidly Building Workflows with the Build Tool
 
 After understanding the manual process, you can use the `fastworkflow build` command to automate everything. It introspects your code and generates all the necessary files.
@@ -568,6 +720,7 @@ This single command will generate the `greet.py` command, `get_properties` and `
 | `LLM_PLANNER` | LiteLLM model string for the agent's task planner | `run` (agent mode) | `mistral/mistral-small-latest` |
 | `LLM_AGENT` | LiteLLM model string for the DSPy agent | `run` (agent mode) | `mistral/mistral-small-latest` |
 | `LLM_CONVERSATION_STORE` | LiteLLM model string for conversation topic/summary generation | FastAPI service | `mistral/mistral-small-latest` |
+| `LITELLM_PROXY_API_BASE` | URL of your LiteLLM Proxy server | When using `litellm_proxy/` models | *not set* |
 | `NOT_FOUND` | Placeholder value for missing parameters during extraction | Always | `"NOT_FOUND"` |
 | `MISSING_INFORMATION_ERRMSG` | Error message prefix for missing parameters | Always | `"Missing required..."` |
 | `INVALID_INFORMATION_ERRMSG` | Error message prefix for invalid parameters | Always | `"Invalid information..."` |
@@ -582,6 +735,7 @@ This single command will generate the `greet.py` command, `get_properties` and `
 | `LITELLM_API_KEY_PLANNER`| API key for the `LLM_PLANNER` model | `run` (agent mode) | *required* |
 | `LITELLM_API_KEY_AGENT`| API key for the `LLM_AGENT` model | `run` (agent mode) | *required* |
 | `LITELLM_API_KEY_CONVERSATION_STORE`| API key for the `LLM_CONVERSATION_STORE` model | FastAPI service | *required* |
+| `LITELLM_PROXY_API_KEY`| Shared API key for authenticating with LiteLLM Proxy | When using `litellm_proxy/` models | *optional* |
 
 > [!tip]
 > The example workflows are configured to use Mistral's models by default. You can get a free API key from [Mistral AI](https://mistral.ai) that works with the `mistral-small-latest` model.
@@ -645,4 +799,4 @@ Interested in contributing to `fastWorkflow` itself? Great!
 
 ## License
 
-`fastWorkflow` is released under the Apache License 2.0
+`fastWorkflow` is released under the Apache License 2.0

fastworkflow-2.17.26/PKG-INFO → fastworkflow-2.17.28/README.md

@@ -1,41 +1,3 @@
-Metadata-Version: 2.1
-Name: fastworkflow
-Version: 2.17.26
-Summary: A framework for rapidly building large-scale, deterministic, interactive workflows with a fault-tolerant, conversational UX
-License: Apache-2.0
-Keywords: fastworkflow,ai,workflow,llm,openai
-Author: Dhar Rawal
-Author-email: drawal@radiantlogic.com
-Requires-Python: >=3.11,<3.14
-Classifier: License :: OSI Approved :: Apache Software License
-Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.11
-Classifier: Programming Language :: Python :: 3.12
-Provides-Extra: fastapi
-Provides-Extra: training
-Requires-Dist: colorama (>=0.4.6,<0.5.0)
-Requires-Dist: datasets (>=4.0.0,<5.0.0) ; extra == "training"
-Requires-Dist: dspy (>=3.0.1,<4.0.0)
-Requires-Dist: fastapi (>=0.120.1) ; extra == "fastapi"
-Requires-Dist: fastapi-mcp (>=0.4.0,<0.5.0) ; extra == "fastapi"
-Requires-Dist: libcst (>=1.8.2,<2.0.0)
-Requires-Dist: litellm[proxy] (>=1.80.5,<2.0.0)
-Requires-Dist: mmh3 (>=5.1.0,<6.0.0)
-Requires-Dist: openai (>=2.8.0)
-Requires-Dist: prompt_toolkit (>=3.0.43,<4.0.0)
-Requires-Dist: pydantic (>=2.9.2,<3.0.0)
-Requires-Dist: python-dotenv (>=1.0.1,<2.0.0)
-Requires-Dist: python-jose[cryptography] (>=3.3.0,<4.0.0) ; extra == "fastapi"
-Requires-Dist: python-levenshtein (>=0.27.1,<0.28.0)
-Requires-Dist: scikit-learn (>=1.6.1,<2.0.0)
-Requires-Dist: speedict (>=0.3.12,<0.4.0)
-Requires-Dist: torch (>=2.7.1,<3.0.0)
-Requires-Dist: transformers (>=4.48.2,<5.0.0)
-Requires-Dist: uvicorn (>=0.31.1,<0.32.0) ; extra == "fastapi"
-Project-URL: homepage, https://github.com/radiantlogicinc/fastworkflow
-Project-URL: repository, https://github.com/radiantlogicinc/fastworkflow
-Description-Content-Type: text/markdown
-
 <!-- Logo and Title -->
 <img src="logo.png" height="64" alt="fastWorkflow Logo and Title">
 
@@ -126,6 +88,9 @@ While [DSPy](https://dspy.ai) ([Why DSPy](https://x.com/lateinteraction/status/1
     - [Adding context hierarchies with context_inheritance_model.json](#adding-context-hierarchies-with-context_inheritance_modeljson)
     - [Using DSPy for Response Generation](#using-dspy-for-response-generation)
     - [Using Startup Commands and Actions](#using-startup-commands-and-actions)
+    - [Running FastWorkflow as a FastAPI Service](#running-fastworkflow-as-a-fastapi-service)
+        - [Kubernetes Liveness and Readiness Probes](#kubernetes-liveness-and-readiness-probes)
+        - [Using LiteLLM Proxy](#using-litellm-proxy)
 - [Rapidly Building Workflows with the Build Tool](#rapidly-building-workflows-with-the-build-tool)
 - [Environment Variables Reference](#environment-variables-reference)
     - [Environment Variables](#environment-variables)
@@ -575,6 +540,110 @@ For workflows with complex initialization requirements, creating a dedicated sta
 
 ---
 
+### Running FastWorkflow as a FastAPI Service
+
+For production deployments and integrations, fastWorkflow provides a FastAPI-based HTTP service via the `run_fastapi_mcp` module. This exposes your workflow as REST endpoints with JWT authentication, SSE streaming, and MCP (Model Context Protocol) support.
+
+```sh
+# Run the FastAPI service
+python -m fastworkflow.run_fastapi_mcp \
+  --workflow_path ./my_workflow \
+  --env_file_path ./fastworkflow.env \
+  --passwords_file_path ./fastworkflow.passwords.env \
+  --port 8000
+```
+
+The service provides endpoints for:
+- `/initialize` - Create a new session and obtain JWT tokens
+- `/invoke_agent` - Submit natural language queries to the agent
+- `/invoke_agent_stream` - Stream responses via SSE or NDJSON
+- `/perform_action` - Execute workflow actions directly
+- `/conversations` - Manage conversation history
+
+#### Kubernetes Liveness and Readiness Probes
+
+When deploying fastWorkflow in Kubernetes, the service provides dedicated probe endpoints for health monitoring:
+
+**Liveness Probe (`/probes/healthz`)**
+
+Determines whether the container is still running. If this probe fails, Kubernetes will restart the container.
+
+```sh
+curl http://localhost:8000/probes/healthz
+# Response: {"status": "alive"}
+```
+
+**Readiness Probe (`/probes/readyz`)**
+
+Checks whether the container is ready to accept traffic. Kubernetes only routes traffic to containers that pass this check.
+
+```sh
+curl http://localhost:8000/probes/readyz
+# Response (ready): {"status": "ready", "checks": {"ready": true, "fastworkflow_initialized": true, "workflow_path_valid": true}}
+# Response (not ready): {"status": "not_ready", "checks": {"ready": false, ...}}
+```
+
+The readiness probe returns:
+- `200 OK` when the application is ready to serve traffic
+- `503 Service Unavailable` when not ready (e.g., during startup)
+
+**Example Kubernetes Configuration**
+
+```yaml
+apiVersion: apps/v1
+kind: Deployment
+spec:
+  template:
+    spec:
+      containers:
+        - name: fastworkflow
+          livenessProbe:
+            httpGet:
+              path: /probes/healthz
+              port: 8000
+            initialDelaySeconds: 10
+            periodSeconds: 10
+            failureThreshold: 5
+            timeoutSeconds: 3
+          readinessProbe:
+            httpGet:
+              path: /probes/readyz
+              port: 8000
+            initialDelaySeconds: 5
+            periodSeconds: 5
+            failureThreshold: 3
+            timeoutSeconds: 3
+```
+
+> [!note]
+> Probe endpoints do not require authentication and are excluded from request logging when returning 200 status to avoid excessive log noise from frequent Kubernetes health checks.
+
+#### Using LiteLLM Proxy
+
+FastWorkflow supports routing LLM calls through a [LiteLLM Proxy](https://docs.litellm.ai/docs/simple_proxy) server. This is useful when you want to:
+- Centralize API key management
+- Use a unified endpoint for multiple LLM providers
+- Route requests through a corporate proxy with custom configurations
+
+To use LiteLLM Proxy, set your model strings to use the `litellm_proxy/` prefix and configure the proxy URL:
+
+```
+# In fastworkflow.env - use the litellm_proxy/ prefix for model names
+LLM_AGENT=litellm_proxy/bedrock_mistral_large_2407
+LLM_PARAM_EXTRACTION=litellm_proxy/bedrock_mistral_large_2407
+LITELLM_PROXY_API_BASE=http://127.0.0.1:4000
+
+# In fastworkflow.passwords.env - shared key for proxy authentication
+LITELLM_PROXY_API_KEY=your-proxy-api-key
+```
+
+The model name after `litellm_proxy/` (e.g., `bedrock_mistral_large_2407`) is passed to your proxy server, which routes it to the actual provider based on its configuration.
+
+> [!note]
+> When using `litellm_proxy/` models, the per-role API keys (`LITELLM_API_KEY_*`) are ignored. All proxied calls use the shared `LITELLM_PROXY_API_KEY` instead. You can mix proxied and direct models - only models with the `litellm_proxy/` prefix are routed through the proxy.
+
+---
+
 ## Rapidly Building Workflows with the Build Tool
 
 After understanding the manual process, you can use the `fastworkflow build` command to automate everything. It introspects your code and generates all the necessary files.
@@ -606,6 +675,7 @@ This single command will generate the `greet.py` command, `get_properties` and `
 | `LLM_PLANNER` | LiteLLM model string for the agent's task planner | `run` (agent mode) | `mistral/mistral-small-latest` |
 | `LLM_AGENT` | LiteLLM model string for the DSPy agent | `run` (agent mode) | `mistral/mistral-small-latest` |
 | `LLM_CONVERSATION_STORE` | LiteLLM model string for conversation topic/summary generation | FastAPI service | `mistral/mistral-small-latest` |
+| `LITELLM_PROXY_API_BASE` | URL of your LiteLLM Proxy server | When using `litellm_proxy/` models | *not set* |
 | `NOT_FOUND` | Placeholder value for missing parameters during extraction | Always | `"NOT_FOUND"` |
 | `MISSING_INFORMATION_ERRMSG` | Error message prefix for missing parameters | Always | `"Missing required..."` |
 | `INVALID_INFORMATION_ERRMSG` | Error message prefix for invalid parameters | Always | `"Invalid information..."` |
@@ -620,6 +690,7 @@ This single command will generate the `greet.py` command, `get_properties` and `
 | `LITELLM_API_KEY_PLANNER`| API key for the `LLM_PLANNER` model | `run` (agent mode) | *required* |
 | `LITELLM_API_KEY_AGENT`| API key for the `LLM_AGENT` model | `run` (agent mode) | *required* |
 | `LITELLM_API_KEY_CONVERSATION_STORE`| API key for the `LLM_CONVERSATION_STORE` model | FastAPI service | *required* |
+| `LITELLM_PROXY_API_KEY`| Shared API key for authenticating with LiteLLM Proxy | When using `litellm_proxy/` models | *optional* |
 
 > [!tip]
 > The example workflows are configured to use Mistral's models by default. You can get a free API key from [Mistral AI](https://mistral.ai) that works with the `mistral-small-latest` model.
@@ -683,4 +754,4 @@ Interested in contributing to `fastWorkflow` itself? Great!
 
 ## License
 
-`fastWorkflow` is released under the Apache License 2.0
+`fastWorkflow` is released under the Apache License 2.0

{fastworkflow-2.17.26 → fastworkflow-2.17.28}/fastworkflow/__init__.py

@@ -132,6 +132,12 @@ def init(env_vars: dict):
     global _env_vars, CommandContextModel, RoutingDefinition, RoutingRegistry, ModelPipelineRegistry
     _env_vars = env_vars
 
+    # Reconfigure log level from env_vars (dotenv files) if LOG_LEVEL is specified
+    # This allows LOG_LEVEL to be set in fastworkflow.env files, not just OS environment
+    if log_level := env_vars.get("LOG_LEVEL"):
+        from .utils.logging import reconfigure_log_level
+        reconfigure_log_level(log_level)
+
     # init before importing other modules so env vars are available
     from .command_context_model import CommandContextModel as CommandContextModelClass
     from .command_routing import RoutingDefinition as RoutingDefinitionClass

{fastworkflow-2.17.26 → fastworkflow-2.17.28}/fastworkflow/build/command_file_template.py

@@ -16,7 +16,7 @@ def get_import_block():
         f"from fastworkflow.train.generate_synthetic import generate_diverse_utterances\n"
         f"from fastworkflow.utils.context_utils import list_context_names\n"
         f"from typing import Any, Dict, Optional\n"
-        f"from pydantic import BaseModel, Field\n"
+        f"from pydantic import BaseModel, Field, ConfigDict\n"
     )
 
 def create_function_command_file(function_info: FunctionInfo, output_dir: str, file_name: str = None, source_dir: str = None, overwrite: bool = False) -> str:
@@ -98,8 +98,10 @@ def create_function_command_file(function_info: FunctionInfo, output_dir: str, f
         call_param = ""
         call_arg = ""
 
-    # Add Output class
-    command_file_content += f"    class Output(BaseModel):\n{output_fields}\n\n"
+    # Add Output class with arbitrary_types_allowed for non-Pydantic return types
+    command_file_content += f"    class Output(BaseModel):\n"
+    command_file_content += f"        model_config = ConfigDict(arbitrary_types_allowed=True)\n"
+    command_file_content += f"{output_fields}\n\n"
 
     # Add utterances
     command_file_content += f"    plain_utterances = [\n{plain_utterances}\n    ]\n\n"
@@ -326,8 +328,10 @@ def create_command_file(class_info, method_info, output_dir, file_name=None, is_
     # Add Input class if needed
     command_file_content += input_class
 
-    # Add Output class
-    command_file_content += f"    class Output(BaseModel):\n{output_fields}\n\n"
+    # Add Output class with arbitrary_types_allowed for non-Pydantic return types
+    command_file_content += f"    class Output(BaseModel):\n"
+    command_file_content += f"        model_config = ConfigDict(arbitrary_types_allowed=True)\n"
+    command_file_content += f"{output_fields}\n\n"
 
     # Add utterances
     command_file_content += f"    plain_utterances = [\n{plain_utterances}\n    ]\n\n"

fastworkflow-2.17.28/fastworkflow/examples/fastworkflow.env

@@ -0,0 +1,35 @@
+# ============================================================================
+# LLM Model Configuration
+# ============================================================================
+# Use direct provider model strings (e.g., mistral/mistral-small-latest)
+# or LiteLLM Proxy model strings (e.g., litellm_proxy/your_model_name)
+LLM_SYNDATA_GEN=mistral/mistral-small-latest
+LLM_PARAM_EXTRACTION=mistral/mistral-small-latest
+LLM_RESPONSE_GEN=mistral/mistral-small-latest
+LLM_PLANNER=mistral/mistral-small-latest
+LLM_AGENT=mistral/mistral-small-latest
+LLM_CONVERSATION_STORE=mistral/mistral-small-latest
+
+# ============================================================================
+# LiteLLM Proxy Configuration (Optional)
+# ============================================================================
+# To route LLM calls through a LiteLLM Proxy, set the model strings above to
+# use the litellm_proxy/ prefix and configure the proxy URL below.
+# Example:
+#   LLM_AGENT=litellm_proxy/bedrock_mistral_large_2407
+#   LITELLM_PROXY_API_BASE=http://127.0.0.1:4000
+# The proxy API key should be set in fastworkflow.passwords.env
+# LITELLM_PROXY_API_BASE=http://127.0.0.1:4000
+
+# ============================================================================
+# Workflow Configuration
+# ============================================================================
+SPEEDDICT_FOLDERNAME=___workflow_contexts
+SYNTHETIC_UTTERANCE_GEN_NUMOF_PERSONAS=4
+SYNTHETIC_UTTERANCE_GEN_UTTERANCES_PER_PERSONA=5
+SYNTHETIC_UTTERANCE_GEN_PERSONAS_PER_BATCH=1
+MISSING_INFORMATION_ERRMSG="Missing parameter values: "
+INVALID_INFORMATION_ERRMSG="Invalid parameter values: "
+NOT_FOUND="NOT_FOUND"
+INVALID="INVALID"
+PARAMETER_EXTRACTION_ERROR_MSG="Error in parameter extraction: {error}"

fastworkflow-2.17.28/fastworkflow/examples/fastworkflow.passwords.env

@@ -0,0 +1,20 @@
+# ============================================================================
+# Direct Provider API Keys
+# ============================================================================
+# Tested with Mistral Small 3.1. A bigger model will produce better results, obviously
+# These keys are used when LLM_* variables use direct provider model strings
+# (e.g., mistral/mistral-small-latest, openai/gpt-4, etc.)
+LITELLM_API_KEY_SYNDATA_GEN=<API KEY for synthetic data generation model>
+LITELLM_API_KEY_PARAM_EXTRACTION=<API KEY for parameter extraction model>
+LITELLM_API_KEY_RESPONSE_GEN=<API KEY for response generation model>
+LITELLM_API_KEY_PLANNER=<API KEY for the agent's task planner model>
+LITELLM_API_KEY_AGENT=<API KEY for the agent model>
+LITELLM_API_KEY_CONVERSATION_STORE=<API KEY for conversation topic/summary generation model>
+
+# ============================================================================
+# LiteLLM Proxy API Key (Optional)
+# ============================================================================
+# When using litellm_proxy/ model strings, this shared key is used for all
+# proxied calls. The per-role keys above are ignored for proxied models.
+# Leave commented if your proxy doesn't require authentication.
+# LITELLM_PROXY_API_KEY=<API KEY for LiteLLM Proxy authentication>