improved dependancies

app.py

@@ -5,51 +5,54 @@ from mistral7b import mistral
 import time
 
 
-
 if "messages" not in st.session_state:
     st.session_state.messages = []
 
-if "tokens_used"  not in st.session_state :
+if "tokens_used" not in st.session_state:
     st.session_state.tokens_used = 0
 
-if "inference_time" not in st.session_state :
+if "inference_tipipme" not in st.session_state:
     st.session_state.inference_time = [0.00]
 
 
-if "temp" not in st.session_state :
+if "temp" not in st.session_state:
     st.session_state.temp = 0.8
 
-if "model_settings" not in st.session_state :
+if "model_settings" not in st.session_state:
     st.session_state.model_settings = {
-        "temp" : 0.9,
-        "max_tokens" : 512,
+        "temp": 0.9,
+        "max_tokens": 512,
     }
 
-if "history" not in st.session_state :
+if "history" not in st.session_state:
     st.session_state.history = []
 
-if "top_k" not in st.session_state :
+if "top_k" not in st.session_state:
     st.session_state.top_k = 5
 
 with st.sidebar:
     st.markdown("# Model Analytics")
     st.write("Tokens used :", st.session_state['tokens_used'])
 
-    st.write("Average Inference Time: ", round(sum(st.session_state["inference_time"]) / len(st.session_state["inference_time"]), 3)) 
-    st.write("Cost Incured :",round( 0.033 * st.session_state['tokens_used']/ 1000, 3), "INR")
+    st.write("Average Inference Time: ", round(sum(
+        st.session_state["inference_time"]) / len(st.session_state["inference_time"]), 3))
+    st.write("Cost Incured :", round(
+        0.033 * st.session_state['tokens_used'] / 1000, 3), "INR")
 
     st.markdown("---")
     st.markdown("# Retrieval Settings")
-    st.slider(label="Documents to retrieve", min_value=1, max_value=10, value=3)
+    st.slider(label="Documents to retrieve",
+              min_value=1, max_value=10, value=3)
     st.markdown("---")
     st.markdown("# Model Settings")
-    selected_model = st.sidebar.radio('Select one:', ["Mistral 7B", "GPT 3.5 Turbo", "GPT 4",  "Llama 7B"])
-    selected_temperature = st.slider(label="Temperature", min_value=0.0, max_value=1.0, step=0.1, value=0.5)
+    selected_model = st.sidebar.radio(
+        'Select one:', ["Mistral 7B", "GPT 3.5 Turbo", "GPT 4",  "Llama 7B"])
+    selected_temperature = st.slider(
+        label="Temperature", min_value=0.0, max_value=1.0, step=0.1, value=0.5)
     st.write(" ")
     st.info("**2023 ©️ Pragnesh Barik**")
 
 
-
 st.image("ikigai.svg")
 st.title("Ikigai Chat")
 
@@ -67,21 +70,21 @@ for message in st.session_state.messages:
 if prompt := st.chat_input("Chat with Ikigai Docs?"):
     st.chat_message("user").markdown(prompt)
     st.session_state.messages.append({"role": "user", "content": prompt})
-    
+
     tick = time.time()
-    response = mistral(prompt, st.session_state.history, temperature=st.session_state.model_settings["temp"] , max_new_tokens=st.session_state.model_settings["max_tokens"])
+    response = mistral(prompt, st.session_state.history,
+                       temperature=st.session_state.model_settings["temp"], max_new_tokens=st.session_state.model_settings["max_tokens"])
     tock = time.time()
 
-    
     st.session_state.inference_time.append(tock - tick)
     response = response.replace("</s>", "")
     len_response = len(response.split())
 
-    st.session_state["tokens_used"] =  len_response + st.session_state["tokens_used"] 
-    
-    with st.chat_message("assistant"): 
+    st.session_state["tokens_used"] = len_response + \
+        st.session_state["tokens_used"]
+
+    with st.chat_message("assistant"):
         st.markdown(response)
     st.session_state.history.append([prompt, response])
-    st.session_state.messages.append({"role": "assistant", "content": response})
-    
-
+    st.session_state.messages.append(
+        {"role": "assistant", "content": response})

mistral7b.py

@@ -42,6 +42,6 @@ def mistral(
 
     for response in stream:
         # print(response)
-        output += response.token["text"]
+        output += response.token.text
         # yield output
     return output

requirements.txt

@@ -1,91 +1,76 @@
 altair==5.1.2
+asttokens==2.2.1
 attrs==23.1.0
-av==10.0.0
-bitarray==2.8.1
+backcall==0.2.0
 blinker==1.6.3
 cachetools==5.3.1
-huggingface-hub==0.16.4
 certifi==2023.7.22
-charset-normalizer==3.2.0
+charset-normalizer==3.3.0
 click==8.1.7
-coloredlogs==15.0.1
-ctranslate2==3.19.0
-docutils==0.20.1
-filelock==3.12.3
-flatbuffers==23.5.26
-fsspec==2023.6.0
-ftfy==6.1.1
-future==0.18.3
+colorama==0.4.6
+comm==0.1.3
+debugpy==1.6.7
+decorator==5.1.1
+executing==1.2.0
+filelock==3.12.4
+fsspec==2023.9.2
 gitdb==4.0.10
 GitPython==3.1.37
-glob2==0.7
-greenlet==2.0.2
-huggingface-hub==0.16.4
-humanfriendly==10.0
+huggingface-hub==0.18.0
 idna==3.4
 importlib-metadata==6.8.0
-jaraco.classes==3.3.0
+ipykernel==6.23.3
+ipython==8.14.0
+jedi==0.18.2
 Jinja2==3.1.2
-joblib==1.3.2
 jsonschema==4.19.1
 jsonschema-specifications==2023.7.1
-keyring==24.2.0
-llvmlite==0.40.1
+jupyter_client==8.3.0
+jupyter_core==5.3.1
 markdown-it-py==3.0.0
 MarkupSafe==2.1.3
+matplotlib-inline==0.1.6
 mdurl==0.1.2
-mmh3==4.0.1
-more-itertools==10.1.0
-mpmath==1.3.0
-networkx==3.1
-nh3==0.2.14
-nltk==3.8.1
-numba==0.57.1
-numpy==1.24.4
-onnxruntime==1.15.1
-openai-whisper==20230314
+nest-asyncio==1.5.6
+numpy==1.26.0
+packaging==23.1
 pandas==2.1.1
-Pillow==10.0.0
-pkginfo==1.9.6
-protobuf==4.24.3
+parso==0.8.3
+pickleshare==0.7.5
+Pillow==10.0.1
+platformdirs==3.8.0
+prompt-toolkit==3.0.38
+protobuf==4.24.4
+psutil==5.9.5
+pure-eval==0.2.2
 pyarrow==13.0.0
 pydeck==0.8.1b0
-PyPDF2==3.0.1
-pyreadline3==3.4.1
+Pygments==2.15.1
+python-dateutil==2.8.2
 python-dotenv==1.0.0
 pytz==2023.3.post1
-readme-renderer==42.0
+pywin32==306
+PyYAML==6.0.1
+pyzmq==25.1.0
 referencing==0.30.2
-regex==2023.8.8
 requests==2.31.0
-requests-toolbelt==1.0.0
-rfc3986==2.0.0
-rich==13.5.2
+rich==13.6.0
 rpds-py==0.10.4
-safetensors==0.3.3
-scikit-learn==1.3.0
-scipy==1.11.2
-sentence-transformers==2.2.2
-sentencepiece==0.1.99
+six==1.16.0
 smmap==5.0.1
-SQLAlchemy==2.0.20
+stack-data==0.6.2
 streamlit==1.27.2
-sympy==1.12
 tenacity==8.2.3
-threadpoolctl==3.2.0
-tiktoken==0.3.1
-tokenizers==0.13.3
 toml==0.10.2
 toolz==0.12.0
-torch==2.0.1
-torchvision==0.15.2
+tornado==6.3.2
 tqdm==4.66.1
-transformers==4.32.1
-twine==4.0.2
-typing_extensions==4.7.1
+traitlets==5.9.0
+typing_extensions==4.8.0
 tzdata==2023.3
 tzlocal==5.1
-urllib3==2.0.4
+urllib3==2.0.6
 validators==0.22.0
 watchdog==3.0.0
-zipp==3.16.2
+wcwidth==0.2.6
+zipp==3.17.0