flowllm 0.1.0__py3-none-any.whl

flowllm-0.1.0.dist-info/licenses/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 Alibaba Group
+
+   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.

flowllm-0.1.0.dist-info/top_level.txt

@@ -0,0 +1 @@
+llmflow

llmflow/app.py

@@ -0,0 +1,53 @@
+import sys
+
+import uvicorn
+from dotenv import load_dotenv
+from fastapi import FastAPI
+
+from llmflow.schema.request import RetrieverRequest, SummarizerRequest, VectorStoreRequest, AgentRequest
+from llmflow.schema.response import RetrieverResponse, SummarizerResponse, VectorStoreResponse, AgentResponse
+from llmflow.service.llmflow_service import LLMFlowService
+
+load_dotenv()
+
+app = FastAPI()
+service = LLMFlowService(sys.argv[1:])
+
+
+@app.post('/retriever', response_model=RetrieverResponse)
+def call_retriever(request: RetrieverRequest):
+    return service(api="retriever", request=request)
+
+
+@app.post('/summarizer', response_model=SummarizerResponse)
+def call_summarizer(request: SummarizerRequest):
+    return service(api="summarizer", request=request)
+
+
+@app.post('/vector_store', response_model=VectorStoreResponse)
+def call_vector_store(request: VectorStoreRequest):
+    return service(api="vector_store", request=request)
+
+
+@app.post('/agent', response_model=AgentResponse)
+def call_agent(request: AgentRequest):
+    return service(api="agent", request=request)
+
+
+def main():
+    uvicorn.run(app=app,
+                host=service.http_service_config.host,
+                port=service.http_service_config.port,
+                timeout_keep_alive=service.http_service_config.timeout_keep_alive,
+                limit_concurrency=service.http_service_config.limit_concurrency)
+
+
+if __name__ == "__main__":
+    main()
+
+# start with:
+# llmflow \
+#   http_service.port=8001 \
+#   llm.default.model_name=qwen3-32b \
+#   embedding_model.default.model_name=text-embedding-v4 \
+#   vector_store.default.backend=local_file

llmflow/config/config_parser.py

@@ -0,0 +1,80 @@
+import json
+from pathlib import Path
+
+from loguru import logger
+from omegaconf import OmegaConf, DictConfig
+
+from llmflow.schema.app_config import AppConfig
+
+
+class ConfigParser:
+    """
+    Configuration parser that handles loading and merging configurations from multiple sources.
+    
+    The configuration loading priority (from lowest to highest):
+    1. Default configuration from AppConfig schema
+    2. YAML configuration file
+    3. Command line arguments
+    4. Runtime keyword arguments
+    """
+
+    def __init__(self, args: list):
+        """
+        Initialize the configuration parser with command line arguments.
+        
+        Args:
+            args: List of command line arguments in dotlist format (e.g., ['key=value'])
+        """
+        # Step 1: Initialize with default configuration from AppConfig schema
+        self.app_config: DictConfig = OmegaConf.structured(AppConfig)
+
+        # Step 2: Load configuration from YAML file
+        # First, parse CLI arguments to check if custom config path is specified
+        cli_config: DictConfig = OmegaConf.from_dotlist(args)
+        temp_config: AppConfig = OmegaConf.to_object(OmegaConf.merge(self.app_config, cli_config))
+
+        # Determine config file path: either from CLI args or use predefined config
+        if temp_config.config_path:
+            # Use custom config path if provided
+            config_path = Path(temp_config.config_path)
+        else:
+            # Use predefined config name from the config directory
+            pre_defined_config = temp_config.pre_defined_config
+            if not pre_defined_config.endswith(".yaml"):
+                pre_defined_config += ".yaml"
+            config_path = Path(__file__).parent / pre_defined_config
+
+        logger.info(f"load config from path={config_path}")
+        yaml_config = OmegaConf.load(config_path)
+        # Merge YAML config with default config
+        self.app_config = OmegaConf.merge(self.app_config, yaml_config)
+
+        # Step 3: Merge CLI arguments (highest priority)
+        self.app_config = OmegaConf.merge(self.app_config, cli_config)
+
+        # Log the final merged configuration
+        app_config_dict = OmegaConf.to_container(self.app_config, resolve=True)
+        logger.info(f"app_config=\n{json.dumps(app_config_dict, indent=2, ensure_ascii=False)}")
+
+    def get_app_config(self, **kwargs) -> AppConfig:
+        """
+        Get the application configuration with optional runtime overrides.
+        
+        Args:
+            **kwargs: Additional configuration parameters to override at runtime
+            
+        Returns:
+            AppConfig: The final application configuration object
+        """
+        # Create a copy of the current configuration
+        app_config = self.app_config.copy()
+
+        # Apply runtime overrides if provided
+        if kwargs:
+            # Convert kwargs to dotlist format for OmegaConf
+            kwargs_list = [f"{k}={v}" for k, v in kwargs.items()]
+            update_config = OmegaConf.from_dotlist(kwargs_list)
+            app_config = OmegaConf.merge(app_config, update_config)
+
+        # Convert OmegaConf DictConfig to structured AppConfig object
+        return OmegaConf.to_object(app_config)

llmflow/config/mock_config.yaml

@@ -0,0 +1,58 @@
+# demo config.yaml
+
+http_service:
+  host: "0.0.0.0"
+  port: 8001
+  timeout_keep_alive: 600
+  limit_concurrency: 64
+
+thread_pool:
+  max_workers: 10
+
+api:
+  retriever: mock1_op->[mock4_op->mock2_op|mock5_op]->[mock3_op|mock6_op]
+  summarizer: mock1_op->[mock4_op->mock2_op|mock5_op]->mock3_op
+  vector_store: mock6_op
+
+op:
+  mock1_op:
+    backend: mock1_op
+    llm: default
+    vector_store: default
+    params:
+      a: 1
+      b: 2
+  mock2_op:
+    backend: mock2_op
+    params:
+      a: 1
+  mock3_op:
+    backend: mock3_op
+  mock4_op:
+    backend: mock4_op
+  mock5_op:
+    backend: mock5_op
+  mock6_op:
+    backend: mock6_op
+
+llm:
+  default:
+    backend: openai_compatible
+    model_name: qwen3-32b
+    params:
+      temperature: 0.6
+
+embedding_model:
+  default:
+    backend: openai_compatible
+    model_name: text-embedding-v4
+    params:
+      dimensions: 1024
+
+vector_store:
+  default:
+    backend: elasticsearch
+    embedding_model: default
+    params:
+      hosts: "http://localhost:9200"
+

llmflow/embedding_model/__init__.py

@@ -0,0 +1,5 @@
+from llmflow.utils.registry import Registry
+
+EMBEDDING_MODEL_REGISTRY = Registry()
+
+from llmflow.embedding_model.openai_compatible_embedding_model import OpenAICompatibleEmbeddingModel

llmflow/embedding_model/base_embedding_model.py

@@ -0,0 +1,104 @@
+from abc import ABC
+from typing import List
+
+from loguru import logger
+from pydantic import BaseModel, Field
+
+from llmflow.schema.vector_node import VectorNode
+
+
+class BaseEmbeddingModel(BaseModel, ABC):
+    """
+    Abstract base class for embedding models.
+    
+    This class provides a common interface for various embedding model implementations,
+    including retry logic, error handling, and batch processing capabilities.
+    """
+    # Model configuration fields
+    model_name: str = Field(default=..., description="Name of the embedding model")
+    dimensions: int = Field(default=..., description="Dimensionality of the embedding vectors")
+    max_retries: int = Field(default=3, description="Maximum number of retry attempts on failure")
+    raise_exception: bool = Field(default=True, description="Whether to raise exceptions after max retries")
+    max_batch_size: int = Field(default=10,
+                                description="Maximum batch size for processing (text-embedding-v4 should not exceed 10)")
+
+    def _get_embeddings(self, input_text: str | List[str]):
+        """
+        Abstract method to get embeddings from the model.
+        
+        This method must be implemented by concrete subclasses to provide
+        the actual embedding functionality.
+        
+        Args:
+            input_text: Single text string or list of text strings to embed
+            
+        Returns:
+            Embedding vector(s) corresponding to the input text(s)
+        """
+        raise NotImplementedError
+
+    def get_embeddings(self, input_text: str | List[str]):
+        """
+        Get embeddings with retry logic and error handling.
+        
+        This method wraps the _get_embeddings method with automatic retry
+        functionality in case of failures.
+        
+        Args:
+            input_text: Single text string or list of text strings to embed
+            
+        Returns:
+            Embedding vector(s) or None if all retries failed and raise_exception is False
+        """
+        # Retry loop with exponential backoff potential
+        for i in range(self.max_retries):
+            try:
+                return self._get_embeddings(input_text)
+
+            except Exception as e:
+                logger.exception(f"embedding model name={self.model_name} encounter error with e={e.args}")
+                # If this is the last retry and raise_exception is True, re-raise the exception
+                if i == self.max_retries - 1 and self.raise_exception:
+                    raise e
+
+        # Return None if all retries failed and raise_exception is False
+        return None
+
+    def get_node_embeddings(self, nodes: VectorNode | List[VectorNode]):
+        """
+        Generate embeddings for VectorNode objects and update their vector fields.
+        
+        This method handles both single nodes and lists of nodes, with automatic
+        batching for efficient processing of large node lists.
+        
+        Args:
+            nodes: Single VectorNode or list of VectorNode objects to embed
+            
+        Returns:
+            The same node(s) with updated vector fields containing embeddings
+            
+        Raises:
+            RuntimeError: If unsupported node type is provided
+        """
+        # Handle single VectorNode
+        if isinstance(nodes, VectorNode):
+            nodes.vector = self.get_embeddings(nodes.content)
+            return nodes
+
+        # Handle list of VectorNodes with batch processing
+        elif isinstance(nodes, list):
+            # Process nodes in batches to respect max_batch_size limits
+            embeddings = [emb for i in range(0, len(nodes), self.max_batch_size) for emb in
+                          self.get_embeddings(input_text=[node.content for node in nodes[i:i + self.max_batch_size]])]
+
+            # Validate that we got the expected number of embeddings
+            if len(embeddings) != len(nodes):
+                logger.warning(f"embeddings.size={len(embeddings)} <> nodes.size={len(nodes)}")
+            else:
+                # Assign embeddings to corresponding nodes
+                for node, embedding in zip(nodes, embeddings):
+                    node.vector = embedding
+            return nodes
+
+        else:
+            raise RuntimeError(f"unsupported type={type(nodes)}")

llmflow/embedding_model/openai_compatible_embedding_model.py

@@ -0,0 +1,95 @@
+import os
+from typing import Literal, List
+
+from dotenv import load_dotenv
+from openai import OpenAI
+from pydantic import Field, PrivateAttr, model_validator
+
+from llmflow.embedding_model import EMBEDDING_MODEL_REGISTRY
+from llmflow.embedding_model.base_embedding_model import BaseEmbeddingModel
+
+
+@EMBEDDING_MODEL_REGISTRY.register("openai_compatible")
+class OpenAICompatibleEmbeddingModel(BaseEmbeddingModel):
+    """
+    OpenAI-compatible embedding model implementation.
+    
+    This class provides an implementation of BaseEmbeddingModel that works with
+    OpenAI-compatible embedding APIs, including OpenAI's official API and
+    other services that follow the same interface.
+    """
+    # API configuration fields
+    api_key: str = Field(default_factory=lambda: os.getenv("EMBEDDING_API_KEY"),
+                         description="API key for authentication")
+    base_url: str = Field(default_factory=lambda: os.getenv("EMBEDDING_BASE_URL"),
+                          description="Base URL for the API endpoint")
+    model_name: str = Field(default="", description="Name of the embedding model to use")
+    dimensions: int = Field(default=1024, description="Dimensionality of the embedding vectors")
+    encoding_format: Literal["float", "base64"] = Field(default="float", description="Encoding format for embeddings")
+
+    # Private OpenAI client instance
+    _client: OpenAI = PrivateAttr()
+
+    @model_validator(mode="after")
+    def init_client(self):
+        """
+        Initialize the OpenAI client after model validation.
+        
+        This method is called automatically after Pydantic model validation
+        to set up the OpenAI client with the provided API key and base URL.
+        
+        Returns:
+            self: The model instance for method chaining
+        """
+        self._client = OpenAI(api_key=self.api_key, base_url=self.base_url)
+        return self
+
+    def _get_embeddings(self, input_text: str | List[str]):
+        """
+        Get embeddings from the OpenAI-compatible API.
+        
+        This method implements the abstract _get_embeddings method from BaseEmbeddingModel
+        by calling the OpenAI-compatible embeddings API.
+        
+        Args:
+            input_text: Single text string or list of text strings to embed
+            
+        Returns:
+            Embedding vector(s) corresponding to the input text(s)
+            
+        Raises:
+            RuntimeError: If unsupported input type is provided
+        """
+        completion = self._client.embeddings.create(
+            model=self.model_name,
+            input=input_text,
+            dimensions=self.dimensions,
+            encoding_format=self.encoding_format
+        )
+
+        if isinstance(input_text, str):
+            return completion.data[0].embedding
+
+        elif isinstance(input_text, list):
+            result_emb = [[] for _ in range(len(input_text))]
+            for emb in completion.data:
+                result_emb[emb.index] = emb.embedding
+            return result_emb
+
+        else:
+            raise RuntimeError(f"unsupported type={type(input_text)}")
+
+
+def main():
+    load_dotenv()
+    model = OpenAICompatibleEmbeddingModel(dimensions=64, model_name="text-embedding-v4")
+    res1 = model.get_embeddings(
+        "The clothes are of good quality and look good, definitely worth the wait. I love them.")
+    res2 = model.get_embeddings(["aa", "bb"])
+    print(res1)
+    print(res2)
+
+
+if __name__ == "__main__":
+    main()
+    # launch with: python -m llmflow.model.openai_compatible_embedding_model

llmflow/enumeration/agent_state.py

@@ -0,0 +1,8 @@
+from enum import Enum
+
+
+class AgentState(str, Enum):
+    IDLE = "idle"
+    RUNNING = "running"
+    COMPLETE = "complete"
+    FAILED = "failed"

llmflow/enumeration/chunk_enum.py

@@ -0,0 +1,9 @@
+from enum import Enum
+
+
+class ChunkEnum(str, Enum):
+    THINK = "think"
+    ANSWER = "answer"
+    TOOL = "tool"
+    USAGE = "usage"
+    ERROR = "error"

llmflow/enumeration/http_enum.py

@@ -0,0 +1,9 @@
+from enum import Enum
+
+
+class HttpEnum(str, Enum):
+    GET = "get"
+    POST = "post"
+    HEAD = "head"
+    PUT = "put"
+    DELETE = "delete"

llmflow/enumeration/role.py

@@ -0,0 +1,8 @@
+from enum import Enum
+
+
+class Role(str, Enum):
+    SYSTEM = "system"
+    USER = "user"
+    ASSISTANT = "assistant"
+    TOOL = "tool"

llmflow/llm/__init__.py

@@ -0,0 +1,5 @@
+from llmflow.utils.registry import Registry
+
+LLM_REGISTRY = Registry()
+
+from llmflow.llm.openai_compatible_llm import OpenAICompatibleBaseLLM