From 8abc176c440499a4de8406fd58b7d2c0a4e5b9ff Mon Sep 17 00:00:00 2001
From: Nate Buttke <nate-web@riseup.net>
Date: Tue, 15 Aug 2023 23:29:58 -0700
Subject: use new 3.5 turbo chat model.

---
 server.py | 40 ++++++++++++++++++++++++++++------------
 setup.py  | 35 +++++++++++++++++------------------
 2 files changed, 45 insertions(+), 30 deletions(-)

diff --git a/server.py b/server.py
index 1cd914c..cd27865 100644
--- a/server.py
+++ b/server.py
@@ -39,18 +39,34 @@ def generate_answer(question):
     for i in range(3):
         prompt += results.iloc[i]["summary"] + "\n" + results.iloc[i]["blob"] + "\n"
     prompt += "\n" + "Answer the following question using the code context given above, and show an example with 'Example'\nQ: " + question + "\nA: "
-    response = openai.Completion.create(
-            model="text-davinci-003",
-            # model="code-davinci-002",
-            prompt=prompt,
-            temperature=0.7,
-            max_tokens=1000,
-            top_p=1.0,
-            frequency_penalty=0.0,
-            presence_penalty=0.0,
-            stop=["\"\"\""]
-            )
-    return response["choices"][0]["text"]
+
+    response = openai.ChatCompletion.create(
+      model="gpt-3.5-turbo",
+      messages=[{"role": "user", "content": prompt}],
+      temperature=0.7,
+      max_tokens=300,
+      top_p=1.0,
+      frequency_penalty=0.0,
+      presence_penalty=0.0,
+      stop=["\"\"\""]
+    )
+    resp = response["choices"][0]["message"]["content"]
+
+    counter = 0
+    outstr = ""
+    for char in resp:
+        if counter == 60:
+            outstr += "\n"
+            counter = 0
+        if char == "\n":
+            counter = 0
+            outstr += " "
+        else:
+            counter += 1
+            outstr += char
+
+    #return [response["choices"][0]["text"], ""]
+    return [outstr, ""]
 
 def add_to_tree(tree: dict, path: str):
     parts = PurePosixPath(path).parts
diff --git a/setup.py b/setup.py
index 9efb57c..7bbfd6d 100644
--- a/setup.py
+++ b/setup.py
@@ -146,21 +146,20 @@ def generate_summary(prompt):
     if (len(enc.encode(prompt)) > 3000):
         return "too long to summarize."
 
-    prompt = prompt + '\nSummarize the above code: '
-
- # response = openai.ChatCompletion.create(
- #   model="gpt-3.5-turbo",
- #   messages=[{"role": "user", "content": prompt}],
- #   temperature=0.7,
- #   max_tokens=1024,
- #   top_p=1.0,
- #   frequency_penalty=0.0,
- #   presence_penalty=0.0,
- #   stop=["\"\"\""]
- # )
-
-    #return response["choices"][0]["message"]["content"]
-    return 'herro. this is a test summary'
+    prompt = prompt + '\nSummarize the above code (be succinct): '
+
+    response = openai.ChatCompletion.create(
+      model="gpt-3.5-turbo",
+      messages=[{"role": "user", "content": prompt}],
+      temperature=0.7,
+      max_tokens=300,
+      top_p=1.0,
+      frequency_penalty=0.0,
+      presence_penalty=0.0,
+      stop=["\"\"\""]
+    )
+
+    return response["choices"][0]["message"]["content"]
 
 # create blob. the blob just contains the file path and the source code.
 def blobify(pandaSeries):
@@ -234,9 +233,9 @@ def setup(
 
     print('generating embeddings')
     embedding_model = "text-embedding-ada-002"
-    #code_df["embedding_summary"] = code_df.summary.apply(
-    #        [lambda x: get_embedding(x, engine=embedding_model)]
-    #        )
+    code_df["embedding_summary"] = code_df.summary.apply(
+            [lambda x: get_embedding(x, engine=embedding_model)]
+            )
     print('done with embeddings')
     code_df.to_csv(output_csv_filepath)
 
-- 
cgit v1.2.3