Update app.py

app.py

@@ -65,6 +65,110 @@ def dspy_generate_agent_prompts(prompt):
 
     return agent_prompts
 
+def query_vectara(text):
+    user_message = text
+
+    # Read authentication parameters from the .env file
+    customer_id = os.getenv('CUSTOMER_ID')
+    corpus_id = os.getenv('CORPUS_ID')
+    api_key = os.getenv('API_KEY')
+
+    # Define the headers
+    api_key_header = {
+        "customer-id": customer_id,
+        "x-api-key": api_key
+    }
+
+    # Define the request body in the structure provided in the example
+    request_body = {
+        "query": [
+            {
+                "query": user_message,
+                "queryContext": "",
+                "start": 1,
+                "numResults": 25,
+                "contextConfig": {
+                    "charsBefore": 0,
+                    "charsAfter": 0,
+                    "sentencesBefore": 2,
+                    "sentencesAfter": 2,
+                    "startTag": "%START_SNIPPET%",
+                    "endTag": "%END_SNIPPET%",
+                },
+                "rerankingConfig": {
+                    "rerankerId": 272725718,
+                    "mmrConfig": {
+                        "diversityBias": 0.35
+                    }
+                },
+                "corpusKey": [
+                    {
+                        "customerId": customer_id,
+                        "corpusId": corpus_id,
+                        "semantics": 0,
+                        "metadataFilter": "",
+                        "lexicalInterpolationConfig": {
+                            "lambda": 0
+                        },
+                        "dim": []
+                    }
+                ],
+                "summary": [
+                    {
+                        "maxSummarizedResults": 5,
+                        "responseLang": "auto",
+                        "summarizerPromptName": "vectara-summary-ext-v1.2.0"
+                    }
+                ]
+            }
+        ]
+    }
+
+    # Make the API request using Gradio
+    response = requests.post(
+        "https://api.vectara.io/v1/query",
+        json=request_body,  # Use json to automatically serialize the request body
+        verify=True,
+        headers=api_key_header
+    )
+
+    if response.status_code == 200:
+        query_data = response.json()
+        if query_data:
+            sources_info = []
+
+            # Extract the summary.
+            summary = query_data['responseSet'][0]['summary'][0]['text']
+
+            # Iterate over all response sets
+            for response_set in query_data.get('responseSet', []):
+                # Extract sources
+                # Limit to top 5 sources.
+                for source in response_set.get('response', [])[:5]:
+                    source_metadata = source.get('metadata', [])
+                    source_info = {}
+
+                    for metadata in source_metadata:
+                        metadata_name = metadata.get('name', '')
+                        metadata_value = metadata.get('value', '')
+
+                        if metadata_name == 'title':
+                            source_info['title'] = metadata_value
+                        elif metadata_name == 'author':
+                            source_info['author'] = metadata_value
+                        elif metadata_name == 'pageNumber':
+                            source_info['page number'] = metadata_value
+
+                    if source_info:
+                        sources_info.append(source_info)
+
+            result = {"summary": summary, "sources": sources_info}
+            return f"{json.dumps(result, indent=2)}"
+        else:
+            return "No data found in the response."
+    else:
+        return f"Error: {response.status_code}"
+
 # Define the main function to be used with Gradio
 def generate_outputs(user_prompt):
     # 1. Process prompt with langchain (replace with your actual implementation)
@@ -79,11 +183,12 @@ def generate_outputs(user_prompt):
     # 4. Generate prompts for agents using DSPy
     agent_prompts = dspy_generate_agent_prompts(processed_prompt)
 
-    # 5. Use the chosen LLM for two of the prompts
-    output_1 = llm(agent_prompts[0], max_length=100)[0]["generated_text"]
-    output_2 = llm(agent_prompts[1], max_length=100)[0]["generated_text"]
+    # 5. Use the chosen LLM for two of the prompts and vectara tool use for the third agent
+    output_1 = llm(agent_prompts[0], max_length=100)[0][combined_data]
+    output_2 = llm(agent_prompts[1], max_length=100)[0][combined_data]
+    output_3 = query_vectara(prompt)
 
-    # 6. Produce outputs with Langchain or DSPy (replace with your actual implementation)
+    # 6. Produce outputs with Langchain or DSPy (stand in section)
     report, recommendations, visualization = produce_outputs(combined_data)
 
     return report, recommendations, visualization