Synced repo using 'sync_with_huggingface' Github Action

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 [yyyy] [name of copyright owner]
+
+   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.

app.py

@@ -0,0 +1,488 @@
+import os
+import streamlit as st
+import random
+from typing import Tuple, Dict
+from langchain_core.messages import SystemMessage, HumanMessage, AIMessage
+from langchain.chat_models import init_chat_model
+from atla import Atla
+from dotenv import load_dotenv
+
+load_dotenv()
+
+# Set page config
+st.set_page_config(page_title="Meta-ChatGPT", layout="wide")
+
+# Configuration parameters
+QUALITY_THRESHOLD = 4.0  # Threshold for acceptable response quality
+MAX_ITERATIONS = 3  # Maximum number of refinement iterations
+EVAL_PROMPT = """
+    Evaluate the response on the following dimensions, scoring each from 1-5 (where 5 is excellent):
+
+    1. Accuracy: Is the response factually correct and free from hallucination or misinformation?
+    2. Relevance: Does the response directly answer the user's question effectively?
+    3. Clarity: Is the response clearly structured and easily understandable?
+    4. Depth: Does the response provide sufficient detail, insight, or useful context?
+
+    For each dimension, provide:
+    - A numeric score (1-5)
+    - A brief explanation justifying the score
+    - Specific suggestions for improvement
+
+    Then provide an overall average score and a concise summary of your evaluation.
+    Your overall average score should be a single floating-point number between 1 and 5.
+"""
+
+
+# Initialize API keys from environment variables or Streamlit secrets
+def initialize_api_keys():
+    # Check if we're running in Streamlit Cloud with secrets
+    try:
+        if hasattr(st, "secrets") and "OPENAI_API_KEY" in st.secrets:
+            os.environ["OPENAI_API_KEY"] = st.secrets["OPENAI_API_KEY"]
+            os.environ["ANTHROPIC_API_KEY"] = st.secrets["ANTHROPIC_API_KEY"]
+            os.environ["TOGETHER_API_KEY"] = st.secrets["TOGETHER_API_KEY"]
+            os.environ["ATLA_API_KEY"] = st.secrets["ATLA_API_KEY"]
+        # Keys should be loaded from environment variables or .env file
+        # No UI for API key input needed
+    except Exception as e:
+        st.sidebar.error(f"Error loading API keys: {e}")
+
+
+# Initialize models and session state
+def initialize_app():
+    initialize_api_keys()
+
+    # Initialize LLM clients if they don't exist or if API keys have been updated
+    if "initialized" not in st.session_state:
+        try:
+            st.session_state.gpt4o = init_chat_model("gpt-4o", model_provider="openai")
+            st.session_state.claude = init_chat_model(
+                "claude-3-7-sonnet-20250219", model_provider="anthropic"
+            )
+            st.session_state.deepseek = init_chat_model(
+                "deepseek-ai/DeepSeek-V3", model_provider="together"
+            )
+            st.session_state.atla = Atla()
+            st.session_state.initialized = True
+
+            # Initialize chat messages
+            if "chat_messages" not in st.session_state:
+                st.session_state.chat_messages = [
+                    SystemMessage(
+                        content="You are a helpful assistant that can answer questions and help with tasks."
+                    )
+                ]
+
+            # Initialize chat history for display
+            if "chat_history" not in st.session_state:
+                st.session_state.chat_history = []
+
+            # Initialize latest result
+            if "latest_result" not in st.session_state:
+                st.session_state.latest_result = None
+
+        except Exception as e:
+            st.error(f"Error initializing models: {e}")
+            st.warning("Please check your API keys in the sidebar.")
+            st.session_state.initialized = False
+
+
+def evaluate_with_atla(inputs: dict[str, str]) -> Tuple[float, str]:
+    """Evaluate response using Atla's Selene model."""
+    response = st.session_state.atla.evaluation.create(
+        model_id="atla-selene",
+        model_input=inputs["question"],
+        model_output=inputs["response"],
+        evaluation_criteria=EVAL_PROMPT,
+    )
+    evaluation = response.result.evaluation
+    return float(evaluation.score), evaluation.critique
+
+
+def get_responses(
+    question: str, feedback: str = "", with_status: bool = True
+) -> Dict[str, str]:
+    """Get responses from all LLMs for a given question."""
+    st.session_state.chat_messages.append(HumanMessage(content=question))
+    if feedback:
+        st.session_state.chat_messages.append(HumanMessage(content=feedback))
+    responses = {}
+
+    if with_status:
+        # Create progress trackers for each model
+        with st.status(
+            "Generating responses from all models...", expanded=True
+        ) as status:
+            # Get response from GPT-4o
+            status.update(label="Getting response from GPT-4o...")
+            gpt_response = st.session_state.gpt4o.invoke(st.session_state.chat_messages)
+            responses["GPT-4o"] = gpt_response.content
+
+            # Get response from Claude
+            status.update(label="Getting response from Claude 3.7...")
+            claude_response = st.session_state.claude.invoke(
+                st.session_state.chat_messages
+            )
+            responses["Claude 3.7"] = claude_response.content
+
+            # Get response from DeepSeek
+            status.update(label="Getting response from DeepSeekV3.0...")
+            deepseek_response = st.session_state.deepseek.invoke(
+                st.session_state.chat_messages
+            )
+            responses["DeepSeekV3.0"] = deepseek_response.content
+
+            status.update(label="All responses generated successfully!", state="complete")
+    else:
+        # Get responses without status bar (for refinement)
+        st.write("Getting response from models...")
+
+        # Get response from GPT-4o
+        gpt_response = st.session_state.gpt4o.invoke(st.session_state.chat_messages)
+        responses["GPT-4o"] = gpt_response.content
+
+        # Get response from Claude
+        claude_response = st.session_state.claude.invoke(st.session_state.chat_messages)
+        responses["Claude 3.7"] = claude_response.content
+
+        # Get response from DeepSeek
+        deepseek_response = st.session_state.deepseek.invoke(
+            st.session_state.chat_messages
+        )
+        responses["DeepSeekV3.0"] = deepseek_response.content
+
+    return responses
+
+
+def evaluate_response(question: str, response: str) -> Dict:
+    """Evaluate a single response using Selene."""
+    inputs = {"question": question, "response": response}
+    score, critique = evaluate_with_atla(inputs)
+    return {"score": score, "critique": critique}
+
+
+def evaluate_all_responses(
+    question: str, responses: Dict[str, str], use_status: bool = True
+) -> Dict[str, Dict]:
+    """Evaluate all responses and return their evaluations."""
+    evaluations = {}
+
+    if (
+        use_status and len(st.session_state.chat_history) <= 1
+    ):  # Only use status on initial response
+        with st.status("Evaluating responses with Selene...", expanded=True) as status:
+            for model_name, response in responses.items():
+                status.update(label=f"Evaluating {model_name} response...")
+                evaluation = evaluate_response(question, response)
+                evaluations[model_name] = evaluation
+
+            status.update(label="All evaluations complete!", state="complete")
+    else:
+        # Simple version without status
+        st.write("Evaluating responses with Selene...")
+        for model_name, response in responses.items():
+            evaluation = evaluate_response(question, response)
+            evaluations[model_name] = evaluation
+        st.write("All evaluations complete!")
+
+    return evaluations
+
+
+def select_best_response(evaluations: Dict[str, Dict]) -> Tuple[str, Dict]:
+    """Select the best response based on overall score. Randomly choose if tied."""
+    best_score = -1
+    tied_models = []
+
+    for model_name, evaluation in evaluations.items():
+        overall_score = evaluation["score"]
+
+        if overall_score > best_score:
+            # New highest score - clear previous ties and start fresh
+            best_score = overall_score
+            tied_models = [(model_name, evaluation)]
+        elif overall_score == best_score:
+            # Tie detected - add to the list of tied models
+            tied_models.append((model_name, evaluation))
+
+    # If there are multiple models tied for the highest score, randomly select one
+    if tied_models:
+        best_model, best_evaluation = random.choice(tied_models)
+
+    return best_model, best_evaluation
+
+
+def refine_responses(question: str, model: str, evaluation: Dict) -> Tuple[str, Dict]:
+    """Refine a response based on Selene's critique."""
+    critique = evaluation["critique"]
+    feedback = f"Please improve your previous response based on this feedback: {critique}"
+
+    # Display refining message
+    st.write(f"Refining response with {model}...")
+
+    # Get improved responses without status bar (to avoid nesting)
+    improved_responses = get_responses(question, feedback, with_status=False)
+    improved_response = improved_responses[model]
+
+    # Re-evaluate the improved response
+    st.write("Re-evaluating refined response...")
+    new_evaluation = evaluate_response(question, improved_response)
+
+    st.write("Refinement complete!")
+
+    return improved_response, new_evaluation
+
+
+def meta_chat(question: str) -> Dict:
+    """Process user question through the Meta-ChatGPT system."""
+    iteration = 0
+    refinement_history = []
+
+    # Step 1: Get initial responses from all models
+    responses = get_responses(question)
+
+    # Step 2: Evaluate all responses
+    # Use status only for the first message
+    evaluations = evaluate_all_responses(
+        question, responses, use_status=len(st.session_state.chat_history) <= 1
+    )
+
+    # Step 3: Select best response
+    best_model, best_evaluation = select_best_response(evaluations)
+    best_response = responses[best_model]
+    st.session_state.chat_messages.append(AIMessage(content=best_response))
+    best_score = best_evaluation["score"]
+
+    # Record initial state
+    refinement_history.append(
+        {
+            "iteration": iteration,
+            "model": best_model,
+            "response": best_response,
+            "evaluation": best_evaluation,
+            "score": best_score,
+        }
+    )
+
+    # Step 4: Iterative refinement if score is below threshold
+    while best_score < QUALITY_THRESHOLD and iteration < MAX_ITERATIONS:
+        iteration += 1
+        st.info(
+            f"Response quality ({best_score:.2f}/5) below threshold ({QUALITY_THRESHOLD}/5). Refining..."
+        )
+
+        # Refine the best response based on feedback
+        improved_response, new_evaluation = refine_responses(
+            question, best_model, best_evaluation
+        )
+        new_score = new_evaluation["score"]
+
+        # Update best response if improved
+        if new_score > best_score:
+            best_response = improved_response
+            best_evaluation = new_evaluation
+            best_score = new_score
+            # Update the AI message in chat_messages
+            st.session_state.chat_messages[-1] = AIMessage(content=best_response)
+
+        # Record refinement state
+        refinement_history.append(
+            {
+                "iteration": iteration,
+                "model": best_model,
+                "response": improved_response,
+                "evaluation": new_evaluation,
+                "score": new_score,
+            }
+        )
+
+    # Step 5: Return final result
+    result = {
+        "question": question,
+        "best_model": best_model,
+        "best_response": best_response,
+        "best_score": best_score,
+        "iterations_required": iteration,
+        "all_evaluations": evaluations,
+        "refinement_history": refinement_history,
+        "threshold_met": best_score >= QUALITY_THRESHOLD,
+        "all_initial_responses": responses,
+    }
+
+    return result
+
+
+def display_chat():
+    """Display the chat interface and history."""
+    # Display chat history
+    for entry in st.session_state.chat_history:
+        if entry["role"] == "user":
+            with st.chat_message("user"):
+                st.markdown(entry["content"])
+        else:
+            # Use just "assistant" for avatar to avoid errors
+            with st.chat_message("assistant"):
+                st.markdown(entry["content"])
+
+                # Add a footnote with model and score info
+                st.caption(f"{entry['model']} (Score: {entry['score']:.2f}/5)")
+
+
+def display_evaluation_details():
+    """Display detailed evaluation information."""
+    if st.session_state.latest_result:
+        result = st.session_state.latest_result
+
+        # Display best model and score
+        st.subheader(f"Best Model: {result['best_model']}")
+        st.metric("Overall Score", f"{result['best_score']:.2f}/5")
+
+        # Refinement information
+        if result["iterations_required"] > 0:
+            st.subheader("Refinement Process")
+            st.write(
+                f"Required {result['iterations_required']} refinements to reach quality threshold."
+            )
+
+            # Create tabs for each refinement iteration
+            tabs = st.tabs(
+                ["Initial"]
+                + [f"Refinement {i+1}" for i in range(result["iterations_required"])]
+            )
+
+            for i, tab in enumerate(tabs):
+                if i < len(result["refinement_history"]):
+                    refinement = result["refinement_history"][i]
+                    with tab:
+                        st.metric("Score", f"{refinement['score']:.2f}/5")
+
+                        st.write("**Response:**")
+                        st.text_area(
+                            "Response Text",
+                            value=refinement["response"],
+                            height=150,
+                            key=f"refinement_response_{i}",
+                            disabled=True,
+                        )
+
+                        st.write("**Atla Critique:**")
+                        st.write(refinement["evaluation"]["critique"])
+
+        # Model comparison
+        st.subheader("Model Comparison")
+        for model, eval_data in result["all_evaluations"].items():
+            with st.expander(f"{model}: {eval_data['score']:.2f}/5"):
+                st.write("**Initial Response:**")
+                st.text_area(
+                    "Response",
+                    value=result["all_initial_responses"][model],
+                    height=150,
+                    key=f"response_{model}",
+                    disabled=True,
+                )
+
+                st.write("**Atla Critique:**")
+                st.write(eval_data["critique"])
+
+
+def main():
+    """Main app function"""
+    # Initialize the app
+    initialize_app()
+
+    # Initialize session state for sidebar visibility if not exists
+    if "show_analysis" not in st.session_state:
+        st.session_state.show_analysis = False
+
+    # Main content takes full width when analysis is collapsed
+    if st.session_state.get("latest_result") and st.session_state.show_analysis:
+        col1, col2 = st.columns([2, 1])
+    else:
+        # Use full width for main content when analysis is collapsed
+        col1 = st.container()
+        col2 = None  # We won't use col2 when analysis is collapsed
+
+    with col1:
+        # Display header
+        st.title("🤖 Meta-ChatGPT with Selene")
+        st.markdown(
+            """
+        This app uses multiple LLMs (GPT-4o, Claude 3.7, and DeepSeekV3.0) to answer your questions.
+        Selene evaluates each response, and the best one is selected and refined if needed.
+        """
+        )
+
+        # Add toggle for analysis panel if we have results
+        if st.session_state.get("latest_result"):
+            toggle_col1, toggle_col2 = st.columns([4, 1])
+            with toggle_col2:
+                if st.button(
+                    "📊 "
+                    + (
+                        "Hide Analysis"
+                        if st.session_state.show_analysis
+                        else "Show Analysis"
+                    )
+                ):
+                    st.session_state.show_analysis = not st.session_state.show_analysis
+                    st.rerun()
+
+        # Display chat interface
+        display_chat()
+
+        # Check if API keys are configured
+        if not st.session_state.get("initialized", False):
+            st.warning("Please configure your API keys in the sidebar to continue.")
+            return
+
+        # Chat input
+        user_input = st.chat_input("Ask a question...")
+
+    # Use a separate column for evaluation details
+    if (
+        st.session_state.get("latest_result")
+        and st.session_state.show_analysis
+        and col2 is not None
+    ):
+        with col2:
+            st.title("Response Analysis")
+            display_evaluation_details()
+
+    if user_input:
+        # Display user message
+        with st.chat_message("user"):
+            st.markdown(user_input)
+
+        # Add to history
+        st.session_state.chat_history.append({"role": "user", "content": user_input})
+
+        # Get meta chat response
+        with st.spinner("Processing your question..."):
+            result = meta_chat(user_input)
+
+        # Store latest result for sidebar display
+        st.session_state.latest_result = result
+
+        # Auto-expand the analysis panel when a new response comes in
+        st.session_state.show_analysis = True
+
+        # Display assistant message
+        with st.chat_message("assistant"):
+            st.markdown(result["best_response"])
+            st.caption(f"{result['best_model']} (Score: {result['best_score']:.2f}/5)")
+
+        # Add to history
+        st.session_state.chat_history.append(
+            {
+                "role": "assistant",
+                "content": result["best_response"],
+                "model": result["best_model"],
+                "score": result["best_score"],
+            }
+        )
+
+        # Force a refresh to update the evaluation details
+        st.rerun()
+
+
+if __name__ == "__main__":
+    main()

requirements.txt

@@ -0,0 +1,7 @@
+streamlit>=1.30.0
+langchain
+langchain-core
+langchain-openai
+langchain-anthropic
+langchain-together
+python-dotenv