initial gradio integration

README.md

@@ -9,5 +9,3 @@ app_file: app.py
 pinned: false
 short_description: talk about DS9 with Jammer!
 ---
-
-An example chatbot using [Gradio](https://gradio.app), [`huggingface_hub`](https://huggingface.co/docs/huggingface_hub/v0.22.2/en/index), and the [Hugging Face Inference API](https://huggingface.co/docs/api-inference/index).

app.py

@@ -1,64 +1,46 @@
-import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
+import os
+from groq import Groq
+from pinecone import Pinecone
+from langchain_pinecone import PineconeVectorStore
+from langchain_community.embeddings.sentence_transformer import SentenceTransformerEmbeddings
 
+import gradio as gr
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
+client = Groq(api_key = os.getenv('GROQ_API_KEY'))
+pc = Pinecone(api_key=os.environ.get("PINECONE_API_KEY"))
+index = pc.Index('ds9-documents')
+docsearch = PineconeVectorStore(index=index, 
+                                embedding=SentenceTransformerEmbeddings(model_name="all-MiniLM-L6-v2"))
+
+def transcript_chat_completion(user_question, history):
+    
+    relevent_docs = docsearch.similarity_search(user_question)
+    delimiter =  '\n\n------------------------------------------------------\n\n'
+    num_docs = 12
+    relevant_transcripts = delimiter.join([doc.page_content for doc in relevent_docs[:num_docs]])
+    
+    chat_completion = client.chat.completions.create(
+        messages=[
+            {
+                "role": "system",
+                "content": '''Use this transcript or transcripts to answer any user questions, citing specific quotes:
+
+                {transcript}
+                '''.format(transcript=relevant_transcripts)
+            },
+            {
+                "role": "user",
+                "content": user_question,
+            }
+        ],
+        model="llama3-8b-8192",
+    )
+
+    return chat_completion.choices[0].message.content
+
+gr.ChatInterface(
+    fn=transcript_chat_completion, 
+    type="messages"
+).launch()
 
 
-if __name__ == "__main__":
-    demo.launch()

requirements.txt

@@ -1 +1,8 @@
-huggingface_hub==0.25.2
+beautifulsoup4
+gradio==5.25.0
+groq==0.19.0
+langchain==0.3.23
+langchain-community==0.3.21
+langchain-pinecone==0.2.5
+pandas==2.2.3
+pinecone==6.0.2