chATLAS_Chains 0.1.3__tar.gz

chatlas_chains-0.1.3/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 (C) 2023 CERN for the benefit of the ATLAS collaboration
+
+   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.

chatlas_chains-0.1.3/PKG-INFO

@@ -0,0 +1,113 @@
+Metadata-Version: 2.4
+Name: chATLAS_Chains
+Version: 0.1.3
+Summary: A modular Python package for implementing Retrieval Augmented Generation chains for the chATLAS project.
+Author-email: Joe Egan <joseph.caimin.egan@cern.ch>
+License: Apache-2.0
+Project-URL: Homepage, https://gitlab.cern.ch/belliot/chatlas-packages/
+Project-URL: Documentation, https://chatlas-packages.docs.cern.ch/chATLAS_Chain/
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: chATLAS_Benchmark>=0.0.9
+Requires-Dist: chATLAS_Embed>=0.1.14
+Requires-Dist: langchain~=0.3.3
+Requires-Dist: langchain_core
+Requires-Dist: langchain_openai
+Dynamic: license-file
+
+
+# chATLAS_Chains
+
+This package implements and benchmarks various Retrieval Augmented Generation (RAG) chains for use in the [chATLAS](https://chatlas-flask-chatlas.app.cern.ch) project.
+
+## Installation
+
+```bash
+conda create -n venv chatlas_chains_env python=3.10
+conda activate chatlas_chains_env
+pip install chatlas-chains
+```
+
+## Environment variables
+
+These are required for the following use cases
+
+1. Using an OpenAI LLM
+```bash
+export CHATLAS_OPENAI_KEY='your api key'
+```
+
+2. Benchmarking, set the path to the question set
+```bash
+export CHATLAS_BENCHMARK_QUESTIONS=/path/to/questions.josn
+```
+
+## Available Chains
+- chains.basic.basic_retrieval_chain
+- chains.basic_graph.basic_retrieval_graph
+
+## Benchmarking
+
+To benchmark e.g. the chains in `chATLAS_Chains.chains.basic` run this from the project root
+```bash
+python benchmark/basic.py
+```
+
+## Testing
+
+The tests require a running postgres server to work. If on lxplus you can modify `TEST_DB_CONFIG` in [tests/conftest.py](tests/conftest.py) to connect to the chATLAS server.
+
+If you want to create a local dummy postgres server, you need to install `psql`. This can be done on macOS using [homebrew](https://brew.sh):
+
+Software install
+```bash
+brew install postgresql
+brew services start postgresql
+brew install pgvector
+brew unlink pgvector && brew link pgvector
+```
+
+Create a user
+```bash
+psql -h localhost -U postgres
+ALTER USER postgres WITH PASSWORD 'Set_your_password_here';
+CREATE EXTENSION IF NOT EXISTS vector;
+```
+## CHANGELOG
+
+#### 0.1.3
+
+Fixing imports
+
+Changed output format of `basic_retrieval_chain` (`docs` key is now a list of `Document` objects, rather than a dict)
+
+Unit tests for `basic_retrieval_chain`
+
+#### 0.1.2
+
+Unit tests
+
+First Langgraph chain
+
+#### 0.1.1
+
+Initial Release
+
+---
+## 📄 License
+
+chATLAS_Benchmark is released under Apache v2.0 license.
+
+---
+
+<div align="center">
+
+**Made with ❤️ by the ATLAS Collaboration**
+
+*For questions and support, please [contact](mailto:joseph.caimin.egan@cern.ch)*
+
+</div>

chatlas_chains-0.1.3/README.md

@@ -0,0 +1,92 @@
+
+# chATLAS_Chains
+
+This package implements and benchmarks various Retrieval Augmented Generation (RAG) chains for use in the [chATLAS](https://chatlas-flask-chatlas.app.cern.ch) project.
+
+## Installation
+
+```bash
+conda create -n venv chatlas_chains_env python=3.10
+conda activate chatlas_chains_env
+pip install chatlas-chains
+```
+
+## Environment variables
+
+These are required for the following use cases
+
+1. Using an OpenAI LLM
+```bash
+export CHATLAS_OPENAI_KEY='your api key'
+```
+
+2. Benchmarking, set the path to the question set
+```bash
+export CHATLAS_BENCHMARK_QUESTIONS=/path/to/questions.josn
+```
+
+## Available Chains
+- chains.basic.basic_retrieval_chain
+- chains.basic_graph.basic_retrieval_graph
+
+## Benchmarking
+
+To benchmark e.g. the chains in `chATLAS_Chains.chains.basic` run this from the project root
+```bash
+python benchmark/basic.py
+```
+
+## Testing
+
+The tests require a running postgres server to work. If on lxplus you can modify `TEST_DB_CONFIG` in [tests/conftest.py](tests/conftest.py) to connect to the chATLAS server.
+
+If you want to create a local dummy postgres server, you need to install `psql`. This can be done on macOS using [homebrew](https://brew.sh):
+
+Software install
+```bash
+brew install postgresql
+brew services start postgresql
+brew install pgvector
+brew unlink pgvector && brew link pgvector
+```
+
+Create a user
+```bash
+psql -h localhost -U postgres
+ALTER USER postgres WITH PASSWORD 'Set_your_password_here';
+CREATE EXTENSION IF NOT EXISTS vector;
+```
+## CHANGELOG
+
+#### 0.1.3
+
+Fixing imports
+
+Changed output format of `basic_retrieval_chain` (`docs` key is now a list of `Document` objects, rather than a dict)
+
+Unit tests for `basic_retrieval_chain`
+
+#### 0.1.2
+
+Unit tests
+
+First Langgraph chain
+
+#### 0.1.1
+
+Initial Release
+
+---
+## 📄 License
+
+chATLAS_Benchmark is released under Apache v2.0 license.
+
+---
+
+<div align="center">
+
+**Made with ❤️ by the ATLAS Collaboration**
+
+*For questions and support, please [contact](mailto:joseph.caimin.egan@cern.ch)*
+
+</div>

chatlas_chains-0.1.3/benchmark/basic.py

@@ -0,0 +1,34 @@
+import os
+
+from tqdm import tqdm
+
+from chATLAS_Benchmark import BenchmarkTest
+from chATLAS_Chains.chains.basic import basic_retrieval_chain
+from chATLAS_Chains.prompt.starters import CHAT_PROMPT_TEMPLATE
+from chATLAS_Chains.vectorstore import vectorstore
+
+chain = basic_retrieval_chain(prompt=CHAT_PROMPT_TEMPLATE, vectorstore=vectorstore, model_name="gpt-4o-mini")
+
+# Initialize the test set
+questions_path = os.getenv("CHATLAS_BENCHMARK_QUESTIONS")
+test = BenchmarkTest(questions_path)
+# test = BenchmarkTest(questions_path, keys={"test_questions": "question", "test_documents":"documents", "test_answer": "answer"})
+
+# --- Run the RAG on the questions ---
+# Assuming RAG.run() returns an answer and list of docs for each question
+gen_answers = []
+gen_docs = []
+for q in tqdm(test.questions):
+    result = chain.invoke(q)
+
+    gen_answers.append(result["answer"].content)
+    gen_docs.append(result["docs"])
+
+# Set generated answers and documents on the test instance
+test.set_generated_data(gen_answers, gen_docs)
+
+# Run the scoring with any metrics you want
+scores = test.score_test_set("LexicalMetrics", "SemanticSimilarity", "DocumentMatch")
+
+# Save the results to the db
+test.store_results(scores, db_name="results.db", name="basic_retrieval_chain")

chatlas_chains-0.1.3/chATLAS_Chains/chains/basic.py

@@ -0,0 +1,42 @@
+from operator import itemgetter
+
+from langchain_core.prompts import ChatPromptTemplate
+from langchain_core.runnables import RunnableParallel
+
+from chATLAS_Chains.llm.model_selection import get_chat_model
+from chATLAS_Chains.search.basic import search_runnable
+from chATLAS_Chains.utils.doc_utils import combine_documents
+
+
+def basic_retrieval_chain(prompt: str, vectorstore, model_name: str) -> RunnableParallel:
+    """
+    Baseline RAG retrieval chain. Searches one or several vectorstores in parallel, passes retrieved documents to the model
+
+    :param prompt: The prompt template to use with the model.
+    :type prompt: str
+    :param vectorstore: The vectorstore or list of vectorstores to search over.
+    :type vectorstore: Any
+    :param model_name: The name of the chat model to use for generating responses.
+    :type model_name: str
+
+    :return: A LangChain RunnableParallel chain that performs retrieval and response generation.
+    :rtype: RunnableParallel
+
+    """
+    prompt = ChatPromptTemplate.from_template(prompt)
+    model = get_chat_model(model_name)
+
+    search = search_runnable(vectorstore)
+
+    final_inputs = {
+        "context": lambda x: combine_documents(x["docs"]),
+        "question": itemgetter("question"),
+    }
+
+    answer = {
+        "answer": final_inputs | prompt | model,
+        "docs": lambda x: x["docs"],
+    }
+
+    chain = search | answer
+    return chain

chatlas_chains-0.1.3/chATLAS_Chains/chains/basic_graph.py

@@ -0,0 +1,163 @@
+"""
+Example graph for running langgraph with this general setup and the postgres vector stores.
+"""
+
+from typing import TypedDict
+
+import langgraph.graph as lg
+from langchain_core.documents import Document
+from langchain_core.prompts import ChatPromptTemplate
+from langgraph.graph import END, StateGraph
+
+from chATLAS_Chains.llm.model_selection import get_chat_model
+from chATLAS_Chains.utils.doc_utils import combine_documents
+from chATLAS_Embed import LangChainVectorStore
+
+
+# Define TypedDict for the state
+class GraphState(TypedDict, total=False):
+    question: str
+    search_kwargs: dict
+    retrieved_docs: dict[str, list[Document]]
+    merged_docs: list[Document]
+    context: str
+    answer: str
+
+
+def basic_retrieval_graph(prompt: str, vectorstore, model_name: str) -> lg.Graph:
+    """
+    Baseline RAG retrieval graph using LangGraph. Searches one or several vectorstores,
+    passes retrieved documents to the model, and returns the final answer.
+
+    Args:
+        prompt: str, the prompt to use for the model
+        vectorstore: the vectorstore(s) to search
+        model_name: str, the name of the model to use for the response
+
+    Returns:
+        A LangGraph graph that can be executed for RAG
+    """
+    # Initialize the model and prompt template
+    model = get_chat_model(model_name)
+    prompt_template = ChatPromptTemplate.from_template(prompt)
+
+    # Create a list of retrievers from the vectorstore(s)
+    if isinstance(vectorstore, list):
+        retrievers = [LangChainVectorStore(vector_store=vs) for vs in vectorstore]
+    else:
+        retrievers = [LangChainVectorStore(vector_store=vectorstore)]
+
+    # Define the retrieval function
+    def retrieve_documents(state: GraphState) -> GraphState:
+        """Retrieve documents from all vectorstores."""
+        question = state["question"]
+        search_kwargs = state.get("search_kwargs", {})  # Get search params from state
+        docs_dict = {}
+
+        for i, retriever in enumerate(retrievers):
+            docs_dict[f"docs_{i}"] = retriever.invoke(
+                question,
+                config={"metadata": {"search_kwargs": search_kwargs}},  # Pass search params to retriever
+            )
+
+        return {
+            "question": question,
+            "search_kwargs": search_kwargs,
+            "retrieved_docs": docs_dict,
+        }
+
+    # Define the document merging function
+    def merge_docs(state: GraphState) -> GraphState:
+        """Merge all retrieved documents into a single list."""
+        docs_dict = state["retrieved_docs"]
+        all_docs = []
+
+        for i in range(len(retrievers)):
+            all_docs.extend(docs_dict[f"docs_{i}"])
+
+        return {
+            "question": state["question"],
+            "retrieved_docs": state["retrieved_docs"],
+            "merged_docs": all_docs,
+        }
+
+    # Define the document processing function
+    def process_docs(state: GraphState) -> GraphState:
+        """Process the merged documents into a context string."""
+        docs = state["merged_docs"]
+        context = combine_documents(docs)
+        return {
+            "question": state["question"],
+            "retrieved_docs": state["retrieved_docs"],
+            "merged_docs": state["merged_docs"],
+            "context": context,
+        }
+
+    # Define the answer generation function
+    def generate_answer(state: GraphState) -> GraphState:
+        """Generate an answer using the LLM."""
+        question = state["question"]
+        context = state["context"]
+
+        prompt_input = {"context": context, "question": question}
+
+        chain = prompt_template | model
+        response = chain.invoke(prompt_input)
+        answer = response.content
+
+        return {
+            "question": state["question"],
+            "retrieved_docs": state["retrieved_docs"],
+            "merged_docs": state["merged_docs"],
+            "context": state["context"],
+            "answer": answer,
+        }
+
+    # Build the graph with the defined state schema
+    graph = StateGraph(GraphState)
+
+    # Add nodes
+    graph.add_node("retrieve", retrieve_documents)
+    graph.add_node("merge", merge_docs)
+    graph.add_node("process", process_docs)
+    graph.add_node("generate", generate_answer)
+
+    # Define the edges
+    graph.add_edge("retrieve", "merge")
+    graph.add_edge("merge", "process")
+    graph.add_edge("process", "generate")
+    graph.add_edge("generate", END)
+
+    # Set the entry point
+    graph.set_entry_point("retrieve")
+
+    # Compile the graph
+    return graph.compile()
+
+
+if __name__ == "__main__":
+    # Example of how to run the graph correctly
+    import os
+
+    os.environ["CHATLAS_EMBEDDING_MODEL_PATH"] = "<PATH TO YOUR EMBEDDING MODEL>"
+    os.environ["CHATLAS_OPENAI_KEY"] = "YOUR OPENAI API KEY"
+    os.environ["CHATLAS_DB_PASSWORD"] = "<>"
+
+    from ..prompt.starters import CHAT_PROMPT_TEMPLATE
+    from ..vectorstore import vectorstore
+
+    graph = basic_retrieval_graph(prompt=CHAT_PROMPT_TEMPLATE, vectorstore=vectorstore, model_name="gpt-4o-mini")
+
+    ans = graph.invoke(
+        {
+            "question": "How many onions are in ATLAS",
+            "search_kwargs": {
+                "k_text": 3,
+                "k": 10,
+                "date_filter": "01-01-2010",
+                "type": ["CDS", "twiki", "Indico"],
+            },
+        }
+    )
+
+    print(ans)